Hugging Face's logo

CyborgPaloma
/
0Shot1Shot-v0.1

Audio Classification
Transformers
music
code
Inference Endpoints
Model card Files Community
CyborgPaloma commited on
Commit
c0d8e31
·
verified ·
1 Parent(s): f159298

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +16 -0
  2. finish_training.log +249 -0
  3. finish_training.py +127 -0
  4. sorter.py +191 -0
  5. training.log +935 -0
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "directory": "F:\\DATASET\\v1",
3
+ "output_directory": "F:\\DATASET\\v1\\Spectrograms",
4
+ "augment": true,
5
+ "noise_snr": 10,
6
+ "pitch_steps": 2,
7
+ "time_stretch_rate": 1.25,
8
+ "sample_rate": 44100,
9
+ "n_fft": 2048,
10
+ "hop_length": 256,
11
+ "n_mels": 128,
12
+ "max_frames": 500,
13
+ "batch_size": 256,
14
+ "min_duration": 0.1,
15
+ "patience": 20
16
+ }
finish_training.log ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-05-16 22:00:46,650 - root - INFO - Initializing SpectrogramDataset...
2
+ 2024-05-16 22:00:47,165 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
3
+ 2024-05-16 22:00:47,171 - root - INFO - SpectrogramDataset initialized successfully
4
+ 2024-05-16 22:00:47,377 - root - ERROR - An error occurred: name 'nn' is not defined
5
+ 2024-05-16 22:01:22,777 - root - INFO - Initializing SpectrogramDataset...
6
+ 2024-05-16 22:01:23,295 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
7
+ 2024-05-16 22:01:23,300 - root - INFO - SpectrogramDataset initialized successfully
8
+ 2024-05-16 22:01:42,720 - root - INFO - Epoch 1:
9
+ Training Loss: 1.5260, Training Accuracy: 0.3385, Validation Loss: 1.6393, Validation Accuracy: 0.2624
10
+
11
+ 2024-05-16 22:01:42,722 - root - INFO - Current learning rate: 0.00014687223021475341
12
+ 2024-05-16 22:02:00,523 - root - INFO - Epoch 2:
13
+ Training Loss: 1.2230, Training Accuracy: 0.5228, Validation Loss: 1.5649, Validation Accuracy: 0.3120
14
+
15
+ 2024-05-16 22:02:00,524 - root - INFO - Current learning rate: 0.00014687223021475341
16
+ 2024-05-16 22:02:18,855 - root - INFO - Epoch 3:
17
+ Training Loss: 1.0560, Training Accuracy: 0.5853, Validation Loss: 1.5721, Validation Accuracy: 0.2886
18
+
19
+ 2024-05-16 22:02:18,856 - root - INFO - Current learning rate: 0.00014687223021475341
20
+ 2024-05-16 22:02:37,163 - root - INFO - Epoch 4:
21
+ Training Loss: 0.9178, Training Accuracy: 0.6221, Validation Loss: 1.5178, Validation Accuracy: 0.3644
22
+
23
+ 2024-05-16 22:02:37,165 - root - INFO - Current learning rate: 0.00014687223021475341
24
+ 2024-05-16 22:06:42,042 - root - INFO - Initializing SpectrogramDataset...
25
+ 2024-05-16 22:06:42,551 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
26
+ 2024-05-16 22:06:42,556 - root - INFO - SpectrogramDataset initialized successfully
27
+ 2024-05-16 22:06:42,755 - root - ERROR - An error occurred: name 'nn' is not defined
28
+ 2024-05-16 22:07:15,641 - root - INFO - Initializing SpectrogramDataset...
29
+ 2024-05-16 22:07:16,161 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
30
+ 2024-05-16 22:07:16,166 - root - INFO - SpectrogramDataset initialized successfully
31
+ 2024-05-16 22:07:16,465 - root - INFO - Loaded the best model from previous training.
32
+ 2024-05-16 22:07:34,862 - root - INFO - Epoch 1:
33
+ Training Loss: 0.5570, Training Accuracy: 0.7951, Validation Loss: 1.7239, Validation Accuracy: 0.5539
34
+
35
+ 2024-05-16 22:07:34,863 - root - INFO - Current learning rate: 0.00014687223021475341
36
+ 2024-05-16 22:07:51,864 - root - INFO - Epoch 2:
37
+ Training Loss: 0.5908, Training Accuracy: 0.7851, Validation Loss: 0.7348, Validation Accuracy: 0.7318
38
+
39
+ 2024-05-16 22:07:51,865 - root - INFO - Current learning rate: 0.00014687223021475341
40
+ 2024-05-16 22:08:09,242 - root - INFO - Epoch 3:
41
+ Training Loss: 0.5201, Training Accuracy: 0.8201, Validation Loss: 0.7574, Validation Accuracy: 0.7114
42
+
43
+ 2024-05-16 22:08:09,244 - root - INFO - Current learning rate: 0.00014687223021475341
44
+ 2024-05-16 22:08:25,962 - root - INFO - Epoch 4:
45
+ Training Loss: 0.4979, Training Accuracy: 0.8176, Validation Loss: 0.7149, Validation Accuracy: 0.7143
46
+
47
+ 2024-05-16 22:08:25,963 - root - INFO - Current learning rate: 0.00014687223021475341
48
+ 2024-05-16 22:08:43,336 - root - INFO - Epoch 5:
49
+ Training Loss: 0.4966, Training Accuracy: 0.8189, Validation Loss: 0.6777, Validation Accuracy: 0.7522
50
+
51
+ 2024-05-16 22:08:43,337 - root - INFO - Current learning rate: 0.00014687223021475341
52
+ 2024-05-16 22:09:00,375 - root - INFO - Epoch 6:
53
+ Training Loss: 0.4906, Training Accuracy: 0.8276, Validation Loss: 0.6189, Validation Accuracy: 0.7551
54
+
55
+ 2024-05-16 22:09:00,376 - root - INFO - Current learning rate: 0.00014687223021475341
56
+ 2024-05-16 22:09:17,365 - root - INFO - Epoch 7:
57
+ Training Loss: 0.4680, Training Accuracy: 0.8289, Validation Loss: 0.5583, Validation Accuracy: 0.7784
58
+
59
+ 2024-05-16 22:09:17,367 - root - INFO - Current learning rate: 0.00014687223021475341
60
+ 2024-05-16 22:09:34,205 - root - INFO - Epoch 8:
61
+ Training Loss: 0.4521, Training Accuracy: 0.8326, Validation Loss: 0.6058, Validation Accuracy: 0.7755
62
+
63
+ 2024-05-16 22:09:34,207 - root - INFO - Current learning rate: 0.00014687223021475341
64
+ 2024-05-16 22:09:51,165 - root - INFO - Epoch 9:
65
+ Training Loss: 0.4068, Training Accuracy: 0.8501, Validation Loss: 0.4922, Validation Accuracy: 0.8163
66
+
67
+ 2024-05-16 22:09:51,167 - root - INFO - Current learning rate: 0.00014687223021475341
68
+ 2024-05-16 22:10:08,186 - root - INFO - Epoch 10:
69
+ Training Loss: 0.4259, Training Accuracy: 0.8463, Validation Loss: 0.5306, Validation Accuracy: 0.8076
70
+
71
+ 2024-05-16 22:10:08,187 - root - INFO - Current learning rate: 0.00014687223021475341
72
+ 2024-05-16 22:10:08,260 - root - INFO - Model saved to checkpoint_epoch_10.pth
73
+ 2024-05-16 22:10:25,419 - root - INFO - Epoch 11:
74
+ Training Loss: 0.4122, Training Accuracy: 0.8451, Validation Loss: 0.5452, Validation Accuracy: 0.8105
75
+
76
+ 2024-05-16 22:10:25,421 - root - INFO - Current learning rate: 0.00014687223021475341
77
+ 2024-05-16 22:10:42,549 - root - INFO - Epoch 12:
78
+ Training Loss: 0.4157, Training Accuracy: 0.8432, Validation Loss: 0.6177, Validation Accuracy: 0.7930
79
+
80
+ 2024-05-16 22:10:42,550 - root - INFO - Current learning rate: 0.00014687223021475341
81
+ 2024-05-16 22:10:59,620 - root - INFO - Epoch 13:
82
+ Training Loss: 0.3727, Training Accuracy: 0.8595, Validation Loss: 0.7197, Validation Accuracy: 0.7405
83
+
84
+ 2024-05-16 22:10:59,621 - root - INFO - Current learning rate: 1.4687223021475341e-05
85
+ 2024-05-16 22:11:17,022 - root - INFO - Epoch 14:
86
+ Training Loss: 0.4019, Training Accuracy: 0.8638, Validation Loss: 0.5073, Validation Accuracy: 0.8076
87
+
88
+ 2024-05-16 22:11:17,023 - root - INFO - Current learning rate: 1.4687223021475341e-05
89
+ 2024-05-16 22:11:34,626 - root - INFO - Epoch 15:
90
+ Training Loss: 0.3273, Training Accuracy: 0.8832, Validation Loss: 0.4066, Validation Accuracy: 0.8601
91
+
92
+ 2024-05-16 22:11:34,628 - root - INFO - Current learning rate: 1.4687223021475341e-05
93
+ 2024-05-16 22:11:51,725 - root - INFO - Epoch 16:
94
+ Training Loss: 0.3409, Training Accuracy: 0.8713, Validation Loss: 0.4711, Validation Accuracy: 0.8280
95
+
96
+ 2024-05-16 22:11:51,726 - root - INFO - Current learning rate: 1.4687223021475341e-05
97
+ 2024-05-16 22:12:09,010 - root - INFO - Epoch 17:
98
+ Training Loss: 0.3207, Training Accuracy: 0.8826, Validation Loss: 0.4586, Validation Accuracy: 0.8338
99
+
100
+ 2024-05-16 22:12:09,011 - root - INFO - Current learning rate: 1.4687223021475341e-05
101
+ 2024-05-16 22:12:25,474 - root - INFO - Epoch 18:
102
+ Training Loss: 0.3405, Training Accuracy: 0.8738, Validation Loss: 0.4560, Validation Accuracy: 0.8222
103
+
104
+ 2024-05-16 22:12:25,476 - root - INFO - Current learning rate: 1.4687223021475341e-05
105
+ 2024-05-16 22:12:42,848 - root - INFO - Epoch 19:
106
+ Training Loss: 0.3721, Training Accuracy: 0.8657, Validation Loss: 0.4278, Validation Accuracy: 0.8426
107
+
108
+ 2024-05-16 22:12:42,849 - root - INFO - Current learning rate: 1.4687223021475343e-06
109
+ 2024-05-16 22:13:00,038 - root - INFO - Epoch 20:
110
+ Training Loss: 0.3588, Training Accuracy: 0.8701, Validation Loss: 0.4247, Validation Accuracy: 0.8397
111
+
112
+ 2024-05-16 22:13:00,039 - root - INFO - Current learning rate: 1.4687223021475343e-06
113
+ 2024-05-16 22:13:00,114 - root - INFO - Model saved to checkpoint_epoch_20.pth
114
+ 2024-05-16 22:13:17,127 - root - INFO - Epoch 21:
115
+ Training Loss: 0.3153, Training Accuracy: 0.8745, Validation Loss: 0.4080, Validation Accuracy: 0.8571
116
+
117
+ 2024-05-16 22:13:17,129 - root - INFO - Current learning rate: 1.4687223021475343e-06
118
+ 2024-05-16 22:13:33,743 - root - INFO - Epoch 22:
119
+ Training Loss: 0.3187, Training Accuracy: 0.8876, Validation Loss: 0.4765, Validation Accuracy: 0.8251
120
+
121
+ 2024-05-16 22:13:33,744 - root - INFO - Current learning rate: 1.4687223021475343e-06
122
+ 2024-05-16 22:13:50,886 - root - INFO - Epoch 23:
123
+ Training Loss: 0.3215, Training Accuracy: 0.8795, Validation Loss: 0.4566, Validation Accuracy: 0.8251
124
+
125
+ 2024-05-16 22:13:50,888 - root - INFO - Current learning rate: 1.4687223021475343e-07
126
+ 2024-05-16 22:14:08,209 - root - INFO - Epoch 24:
127
+ Training Loss: 0.3030, Training Accuracy: 0.8938, Validation Loss: 0.4290, Validation Accuracy: 0.8222
128
+
129
+ 2024-05-16 22:14:08,211 - root - INFO - Current learning rate: 1.4687223021475343e-07
130
+ 2024-05-16 22:14:25,025 - root - INFO - Epoch 25:
131
+ Training Loss: 0.3203, Training Accuracy: 0.8869, Validation Loss: 0.4327, Validation Accuracy: 0.8484
132
+
133
+ 2024-05-16 22:14:25,027 - root - INFO - Current learning rate: 1.4687223021475343e-07
134
+ 2024-05-16 22:14:42,254 - root - INFO - Epoch 26:
135
+ Training Loss: 0.3120, Training Accuracy: 0.8938, Validation Loss: 0.4477, Validation Accuracy: 0.8280
136
+
137
+ 2024-05-16 22:14:42,255 - root - INFO - Current learning rate: 1.4687223021475343e-07
138
+ 2024-05-16 22:14:59,624 - root - INFO - Epoch 27:
139
+ Training Loss: 0.3136, Training Accuracy: 0.8913, Validation Loss: 0.4614, Validation Accuracy: 0.8309
140
+
141
+ 2024-05-16 22:14:59,626 - root - INFO - Current learning rate: 1.4687223021475344e-08
142
+ 2024-05-16 22:15:16,671 - root - INFO - Epoch 28:
143
+ Training Loss: 0.3044, Training Accuracy: 0.8938, Validation Loss: 0.4706, Validation Accuracy: 0.8251
144
+
145
+ 2024-05-16 22:15:16,673 - root - INFO - Current learning rate: 1.4687223021475344e-08
146
+ 2024-05-16 22:15:33,835 - root - INFO - Epoch 29:
147
+ Training Loss: 0.3022, Training Accuracy: 0.8938, Validation Loss: 0.4032, Validation Accuracy: 0.8455
148
+
149
+ 2024-05-16 22:15:33,836 - root - INFO - Current learning rate: 1.4687223021475344e-08
150
+ 2024-05-16 22:15:51,218 - root - INFO - Epoch 30:
151
+ Training Loss: 0.2987, Training Accuracy: 0.8982, Validation Loss: 0.4105, Validation Accuracy: 0.8426
152
+
153
+ 2024-05-16 22:15:51,219 - root - INFO - Current learning rate: 1.4687223021475344e-08
154
+ 2024-05-16 22:15:51,293 - root - INFO - Model saved to checkpoint_epoch_30.pth
155
+ 2024-05-16 22:16:07,971 - root - INFO - Epoch 31:
156
+ Training Loss: 0.3077, Training Accuracy: 0.8869, Validation Loss: 0.4213, Validation Accuracy: 0.8251
157
+
158
+ 2024-05-16 22:16:07,973 - root - INFO - Current learning rate: 1.4687223021475344e-08
159
+ 2024-05-16 22:16:24,561 - root - INFO - Epoch 32:
160
+ Training Loss: 0.3193, Training Accuracy: 0.8838, Validation Loss: 0.4009, Validation Accuracy: 0.8455
161
+
162
+ 2024-05-16 22:16:24,563 - root - INFO - Current learning rate: 1.4687223021475344e-08
163
+ 2024-05-16 22:16:42,053 - root - INFO - Epoch 33:
164
+ Training Loss: 0.3314, Training Accuracy: 0.8869, Validation Loss: 0.4344, Validation Accuracy: 0.8397
165
+
166
+ 2024-05-16 22:16:42,055 - root - INFO - Current learning rate: 1.4687223021475344e-08
167
+ 2024-05-16 22:16:59,057 - root - INFO - Epoch 34:
168
+ Training Loss: 0.2837, Training Accuracy: 0.9001, Validation Loss: 0.4218, Validation Accuracy: 0.8280
169
+
170
+ 2024-05-16 22:16:59,059 - root - INFO - Current learning rate: 1.4687223021475344e-08
171
+ 2024-05-16 22:17:16,041 - root - INFO - Epoch 35:
172
+ Training Loss: 0.3607, Training Accuracy: 0.8701, Validation Loss: 0.4585, Validation Accuracy: 0.8134
173
+
174
+ 2024-05-16 22:17:16,042 - root - INFO - Current learning rate: 1.4687223021475344e-08
175
+ 2024-05-16 22:17:33,182 - root - INFO - Epoch 36:
176
+ Training Loss: 0.2987, Training Accuracy: 0.8919, Validation Loss: 0.4383, Validation Accuracy: 0.8251
177
+
178
+ 2024-05-16 22:17:33,184 - root - INFO - Current learning rate: 1.4687223021475344e-09
179
+ 2024-05-16 22:17:50,259 - root - INFO - Epoch 37:
180
+ Training Loss: 0.3294, Training Accuracy: 0.8682, Validation Loss: 0.4253, Validation Accuracy: 0.8309
181
+
182
+ 2024-05-16 22:17:50,260 - root - INFO - Current learning rate: 1.4687223021475344e-09
183
+ 2024-05-16 22:18:06,981 - root - INFO - Epoch 38:
184
+ Training Loss: 0.2821, Training Accuracy: 0.9019, Validation Loss: 0.4611, Validation Accuracy: 0.8251
185
+
186
+ 2024-05-16 22:18:06,982 - root - INFO - Current learning rate: 1.4687223021475344e-09
187
+ 2024-05-16 22:18:23,998 - root - INFO - Epoch 39:
188
+ Training Loss: 0.3158, Training Accuracy: 0.8869, Validation Loss: 0.4367, Validation Accuracy: 0.8280
189
+
190
+ 2024-05-16 22:18:24,000 - root - INFO - Current learning rate: 1.4687223021475344e-09
191
+ 2024-05-16 22:18:41,011 - root - INFO - Epoch 40:
192
+ Training Loss: 0.3254, Training Accuracy: 0.8888, Validation Loss: 0.3913, Validation Accuracy: 0.8513
193
+
194
+ 2024-05-16 22:18:41,012 - root - INFO - Current learning rate: 1.4687223021475344e-09
195
+ 2024-05-16 22:18:41,155 - root - INFO - Model saved to checkpoint_epoch_40.pth
196
+ 2024-05-16 22:18:58,103 - root - INFO - Epoch 41:
197
+ Training Loss: 0.3082, Training Accuracy: 0.8857, Validation Loss: 0.3953, Validation Accuracy: 0.8542
198
+
199
+ 2024-05-16 22:18:58,105 - root - INFO - Current learning rate: 1.4687223021475344e-09
200
+ 2024-05-16 22:19:14,938 - root - INFO - Epoch 42:
201
+ Training Loss: 0.2816, Training Accuracy: 0.9007, Validation Loss: 0.4112, Validation Accuracy: 0.8484
202
+
203
+ 2024-05-16 22:19:14,939 - root - INFO - Current learning rate: 1.4687223021475344e-09
204
+ 2024-05-16 22:19:32,077 - root - INFO - Epoch 43:
205
+ Training Loss: 0.3457, Training Accuracy: 0.8788, Validation Loss: 0.4241, Validation Accuracy: 0.8455
206
+
207
+ 2024-05-16 22:19:32,078 - root - INFO - Current learning rate: 1.4687223021475344e-09
208
+ 2024-05-16 22:19:49,354 - root - INFO - Epoch 44:
209
+ Training Loss: 0.3149, Training Accuracy: 0.8826, Validation Loss: 0.4160, Validation Accuracy: 0.8542
210
+
211
+ 2024-05-16 22:19:49,356 - root - INFO - Current learning rate: 1.4687223021475344e-09
212
+ 2024-05-16 22:20:06,691 - root - INFO - Epoch 45:
213
+ Training Loss: 0.3011, Training Accuracy: 0.8894, Validation Loss: 0.4293, Validation Accuracy: 0.8484
214
+
215
+ 2024-05-16 22:20:06,692 - root - INFO - Current learning rate: 1.4687223021475344e-09
216
+ 2024-05-16 22:20:23,367 - root - INFO - Epoch 46:
217
+ Training Loss: 0.3327, Training Accuracy: 0.8795, Validation Loss: 0.3971, Validation Accuracy: 0.8630
218
+
219
+ 2024-05-16 22:20:23,369 - root - INFO - Current learning rate: 1.4687223021475344e-09
220
+ 2024-05-16 22:20:40,496 - root - INFO - Epoch 47:
221
+ Training Loss: 0.3180, Training Accuracy: 0.8894, Validation Loss: 0.4143, Validation Accuracy: 0.8513
222
+
223
+ 2024-05-16 22:20:40,497 - root - INFO - Current learning rate: 1.4687223021475344e-09
224
+ 2024-05-16 22:20:58,098 - root - INFO - Epoch 48:
225
+ Training Loss: 0.2915, Training Accuracy: 0.8969, Validation Loss: 0.4355, Validation Accuracy: 0.8455
226
+
227
+ 2024-05-16 22:20:58,100 - root - INFO - Current learning rate: 1.4687223021475344e-09
228
+ 2024-05-16 22:21:15,492 - root - INFO - Epoch 49:
229
+ Training Loss: 0.3160, Training Accuracy: 0.8882, Validation Loss: 0.4601, Validation Accuracy: 0.8163
230
+
231
+ 2024-05-16 22:21:15,494 - root - INFO - Current learning rate: 1.4687223021475344e-09
232
+ 2024-05-16 22:21:32,535 - root - INFO - Epoch 50:
233
+ Training Loss: 0.3085, Training Accuracy: 0.8832, Validation Loss: 0.4587, Validation Accuracy: 0.8105
234
+
235
+ 2024-05-16 22:21:32,537 - root - INFO - Current learning rate: 1.4687223021475344e-09
236
+ 2024-05-16 22:21:32,613 - root - INFO - Model saved to checkpoint_epoch_50.pth
237
+ 2024-05-16 22:21:33,771 - root - INFO - precision recall f1-score support
238
+
239
+ 808 0.88 0.88 0.88 43
240
+ Clap 0.62 0.78 0.69 27
241
+ Closed Hat 0.89 0.86 0.87 63
242
+ Kick 0.94 0.93 0.94 120
243
+ Open Hat 0.76 0.87 0.81 15
244
+ Snare 0.84 0.78 0.81 76
245
+
246
+ accuracy 0.86 344
247
+ macro avg 0.82 0.85 0.83 344
248
+ weighted avg 0.87 0.86 0.86 344
249
+
finish_training.py ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+ import torch.nn as nn
3
+ import torch.optim as optim
4
+ import logging
5
+ import argparse
6
+ import json
7
+ from datetime import datetime
8
+ from torch.utils.data import DataLoader, WeightedRandomSampler, random_split, RandomSampler, SequentialSampler
9
+ from prepare_data import SpectrogramDataset, collate_fn
10
+ from train_model import (
11
+ AudioResNet,
12
+ train_one_epoch,
13
+ validate_one_epoch,
14
+ evaluate_model,
15
+ plot_confusion_matrix,
16
+ device
17
+ )
18
+ from sklearn.metrics import classification_report, confusion_matrix
19
+ import numpy as np
20
+ import os
21
+
22
+ # Configure logging
23
+ logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
24
+ logger = logging.getLogger()
25
+ fh = logging.FileHandler('finish_training.log')
26
+ fh.setLevel(logging.INFO)
27
+ ch = logging.StreamHandler()
28
+ ch.setLevel(logging.INFO)
29
+ formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
30
+ fh.setFormatter(formatter)
31
+ ch.setFormatter(formatter)
32
+ logger.addHandler(fh)
33
+ logger.addHandler(ch)
34
+
35
+ def parse_args():
36
+ parser = argparse.ArgumentParser(description='Train Sample Classifier Model')
37
+ parser.add_argument('--config', type=str, required=True, help='Path to the config file')
38
+ return parser.parse_args()
39
+
40
+ def load_config(config_path):
41
+ if not os.path.exists(config_path):
42
+ raise FileNotFoundError(f"Config file not found: {config_path}")
43
+ with open(config_path, 'r') as f:
44
+ config = json.load(f)
45
+ return config
46
+
47
+ def train_model(model, train_loader, val_loader, criterion, optimizer, scheduler, device, patience=10, max_epochs=50):
48
+ best_loss = float('inf')
49
+ patience_counter = 0
50
+
51
+ for epoch in range(max_epochs):
52
+ train_loss, train_accuracy = train_one_epoch(model, train_loader, criterion, optimizer, device)
53
+ val_loss, val_accuracy = validate_one_epoch(model, val_loader, criterion, device)
54
+
55
+ log_message = (f'Epoch {epoch + 1}:\n'
56
+ f'Training Loss: {train_loss:.4f}, Training Accuracy: {train_accuracy:.4f}, '
57
+ f'Validation Loss: {val_loss:.4f}, Validation Accuracy: {val_accuracy:.4f}\n')
58
+ logging.info(log_message)
59
+
60
+ scheduler.step(val_loss)
61
+ current_lr = optimizer.param_groups[0]['lr']
62
+ logging.info(f'Current learning rate: {current_lr}')
63
+
64
+ if val_loss < best_loss:
65
+ best_loss = val_loss
66
+ patience_counter = 0
67
+ torch.save(model.state_dict(), 'best_model.pth')
68
+ else:
69
+ patience_counter += 1
70
+
71
+ if patience_counter >= patience:
72
+ logging.info('Early stopping triggered')
73
+ break
74
+
75
+ if (epoch + 1) % 10 == 0:
76
+ checkpoint_path = f'checkpoint_epoch_{epoch + 1}.pth'
77
+ torch.save(model.state_dict(), checkpoint_path)
78
+ logging.info(f'Model saved to {checkpoint_path}')
79
+
80
+ def main():
81
+ try:
82
+ args = parse_args()
83
+ config = load_config(args.config)
84
+
85
+ dataset = SpectrogramDataset(config, config['directory'], process_new=True)
86
+ if len(dataset) == 0:
87
+ raise ValueError("The dataset is empty. Please check the data loading process.")
88
+ num_classes = len(dataset.label_to_index)
89
+ class_names = list(dataset.label_to_index.keys())
90
+
91
+ train_size = int(0.7 * len(dataset))
92
+ val_size = int(0.15 * len(dataset))
93
+ test_size = len(dataset) - train_size - val_size
94
+ train_dataset, val_dataset, test_dataset = random_split(dataset, [train_size, val_size, test_size])
95
+
96
+ train_labels = [dataset.labels[i] for i in train_dataset.indices]
97
+ class_counts = np.bincount(train_labels)
98
+ class_weights = 1. / class_counts
99
+ sample_weights = class_weights[train_labels]
100
+ sampler = WeightedRandomSampler(sample_weights, len(sample_weights))
101
+
102
+ train_loader = DataLoader(train_dataset, batch_size=config['batch_size'], collate_fn=collate_fn, sampler=sampler)
103
+ val_loader = DataLoader(val_dataset, batch_size=config['batch_size'], collate_fn=collate_fn, sampler=RandomSampler(val_dataset))
104
+ test_loader = DataLoader(test_dataset, batch_size=config['batch_size'], collate_fn=collate_fn, sampler=SequentialSampler(test_dataset))
105
+
106
+ # Load best hyperparameters
107
+ best_params = {'learning_rate': 0.00014687223021475341, 'weight_decay': 2.970399818935859e-05, 'dropout_rate': 0.36508234143710705}
108
+
109
+ model = AudioResNet(num_classes=num_classes, dropout_rate=best_params['dropout_rate']).to(device)
110
+ criterion = nn.NLLLoss()
111
+ optimizer = optim.Adam(model.parameters(), lr=best_params['learning_rate'], weight_decay=best_params['weight_decay'])
112
+ scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min', patience=3)
113
+
114
+ # Load the previously saved best model
115
+ if os.path.exists('checkpoint_epoch_50.pth'):
116
+ model.load_state_dict(torch.load('checkpoint_epoch_50.pth'))
117
+ logging.info("Loaded the best model from previous training.")
118
+
119
+ train_model(model, train_loader, val_loader, criterion, optimizer, scheduler, device, patience=config['patience'], max_epochs=50)
120
+
121
+ model.load_state_dict(torch.load('checkpoint_epoch_50.pth'))
122
+ evaluate_model(model, test_loader, device, class_names)
123
+ except Exception as e:
124
+ logging.error(f"An error occurred: {e}")
125
+
126
+ if __name__ == '__main__':
127
+ main()
sorter.py ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ import torch
3
+ import torch.nn as nn
4
+ import torch.nn.functional as F
5
+ import tkinter as tk
6
+ from tkinter import ttk, filedialog, messagebox
7
+ import shutil
8
+ from pathlib import Path
9
+ import numpy as np
10
+ import librosa
11
+ import torchaudio
12
+ from torchvision import transforms
13
+ from tqdm import tqdm
14
+
15
+ class ResidualBlock(nn.Module):
16
+ def __init__(self, in_channels, out_channels, stride=1):
17
+ super(ResidualBlock, self).__init__()
18
+ self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
19
+ self.bn1 = nn.BatchNorm2d(out_channels)
20
+ self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
21
+ self.bn2 = nn.BatchNorm2d(out_channels)
22
+ if stride != 1 or in_channels != out_channels:
23
+ self.shortcut = nn.Sequential(
24
+ nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False),
25
+ nn.BatchNorm2d(out_channels)
26
+ )
27
+ else:
28
+ self.shortcut = nn.Identity()
29
+
30
+ def forward(self, x):
31
+ out = F.relu(self.bn1(self.conv1(x)))
32
+ out = self.bn2(self.conv2(out))
33
+ out += self.shortcut(x)
34
+ out = F.relu(out)
35
+ return out
36
+
37
+ class AudioResNet(nn.Module):
38
+ def __init__(self, num_classes=6, dropout_rate=0.5):
39
+ super(AudioResNet, self).__init__()
40
+ self.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False)
41
+ self.bn1 = nn.BatchNorm2d(64)
42
+ self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
43
+ self.layer1 = self._make_layer(64, 64, num_blocks=2, stride=1)
44
+ self.layer2 = self._make_layer(64, 128, num_blocks=2, stride=2)
45
+ self.layer3 = self._make_layer(128, 256, num_blocks=2, stride=2)
46
+ self.layer4 = self._make_layer(256, 512, num_blocks=2, stride=2)
47
+
48
+ self.dropout = nn.Dropout(dropout_rate)
49
+ self.gap = nn.AdaptiveAvgPool2d((1, 1)) # Global Average Pooling
50
+ self.fc1 = nn.Linear(512, 1024)
51
+ self.fc2 = nn.Linear(1024, num_classes)
52
+
53
+ def _make_layer(self, in_channels, out_channels, num_blocks, stride):
54
+ layers = []
55
+ for i in range(num_blocks):
56
+ layers.append(ResidualBlock(in_channels if i == 0 else out_channels, out_channels, stride if i == 0 else 1))
57
+ return nn.Sequential(*layers)
58
+
59
+ def forward(self, x):
60
+ x = F.relu(self.bn1(self.conv1(x)))
61
+ x = self.maxpool(x)
62
+ x = self.layer1(x)
63
+ x = self.layer2(x)
64
+ x = self.layer3(x)
65
+ x = self.layer4(x)
66
+
67
+ x = self.gap(x) # Apply Global Average Pooling
68
+ x = x.view(x.size(0), -1)
69
+
70
+ x = F.relu(self.fc1(x))
71
+ x = self.dropout(x)
72
+ x = self.fc2(x)
73
+ return F.log_softmax(x, dim=1)
74
+
75
+ def load_model(model_path='checkpoint_epoch_50.pth', num_classes=6, dropout_rate=0.5):
76
+ model = AudioResNet(num_classes=num_classes, dropout_rate=dropout_rate)
77
+ model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
78
+ model.eval()
79
+ return model
80
+
81
+ def validate_audio(y, sr, target_sr=44100, min_duration=0.1):
82
+ if sr != target_sr:
83
+ y = librosa.resample(y, orig_sr=sr, target_sr=target_sr)
84
+ if len(y) < min_duration * target_sr:
85
+ pad_length = int(min_duration * target_sr - len(y))
86
+ y = np.pad(y, (0, pad_length), mode='constant')
87
+ return y, target_sr
88
+
89
+ def strip_silence(y, sr, top_db=20, pad_duration=0.1):
90
+ y_trimmed, _ = librosa.effects.trim(y, top_db=top_db)
91
+ pad_length = int(pad_duration * sr)
92
+ y_padded = np.pad(y_trimmed, pad_length, mode='constant')
93
+ return y_padded
94
+
95
+ def audio_to_spectrogram(file_path, n_fft=2048, hop_length=256, n_mels=128, target_sr=44100, min_duration=0.1):
96
+ try:
97
+ y, sr = librosa.load(file_path, sr=None)
98
+ y, sr = validate_audio(y, sr, target_sr, min_duration)
99
+ y = strip_silence(y, sr)
100
+ except Exception as e:
101
+ print(f"Error reading {file_path}: {e}")
102
+ return None
103
+
104
+ y = librosa.util.normalize(y)
105
+ S = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=n_fft, hop_length=hop_length, n_mels=n_mels)
106
+ S_dB = librosa.power_to_db(S, ref=np.max)
107
+ return S_dB
108
+
109
+ def classify_file(model, file_path, spectrogram_save_path):
110
+ spectrogram = audio_to_spectrogram(file_path)
111
+ if spectrogram is None:
112
+ return None, None
113
+ os.makedirs(os.path.dirname(spectrogram_save_path), exist_ok=True)
114
+ np.save(spectrogram_save_path, spectrogram)
115
+ spectrogram = torch.tensor(spectrogram, dtype=torch.float32).unsqueeze(0).unsqueeze(0)
116
+ with torch.no_grad():
117
+ output = model(spectrogram)
118
+ probabilities = torch.exp(output)
119
+ confidence, predicted = torch.max(probabilities, 1)
120
+ return confidence.item(), predicted.item()
121
+
122
+ def sort_files(model, input_folder, output_folder, confidence_threshold=0.9, progress_callback=None):
123
+ spectrogram_folder = os.path.join(output_folder, "Spectrograms")
124
+ if not os.path.exists(output_folder):
125
+ os.makedirs(output_folder)
126
+
127
+ files = list(Path(input_folder).rglob('*.wav'))
128
+ total_files = len(files)
129
+
130
+ for idx, file in enumerate(files):
131
+ spectrogram_save_path = os.path.join(spectrogram_folder, os.path.relpath(file, input_folder)) + '.npy'
132
+ confidence, label = classify_file(model, file, spectrogram_save_path)
133
+ if confidence is not None and confidence >= confidence_threshold:
134
+ label_folder = os.path.join(output_folder, str(label))
135
+ if not os.path.exists(label_folder):
136
+ os.makedirs(label_folder)
137
+ shutil.copy(file, label_folder)
138
+ if progress_callback:
139
+ progress_callback(idx + 1, total_files)
140
+
141
+ class Application(tk.Frame):
142
+ def __init__(self, master=None):
143
+ super().__init__(master)
144
+ self.master = master
145
+ self.pack()
146
+ self.create_widgets()
147
+
148
+ def create_widgets(self):
149
+ self.label = tk.Label(self, text="Select Folder:")
150
+ self.label.pack()
151
+
152
+ self.entry = tk.Entry(self, width=50)
153
+ self.entry.pack()
154
+
155
+ self.browse_button = tk.Button(self, text="Browse", command=self.browse_folder)
156
+ self.browse_button.pack()
157
+
158
+ self.progress = tk.IntVar()
159
+ self.progress_bar = ttk.Progressbar(self, orient="horizontal", length=400, mode="determinate", variable=self.progress)
160
+ self.progress_bar.pack()
161
+
162
+ self.sort_button = tk.Button(self, text="Sort Files", command=self.sort_files)
163
+ self.sort_button.pack()
164
+
165
+ self.quit = tk.Button(self, text="Quit", fg="red", command=self.master.destroy)
166
+ self.quit.pack()
167
+
168
+ def browse_folder(self):
169
+ folder_selected = filedialog.askdirectory()
170
+ self.entry.delete(0, tk.END)
171
+ self.entry.insert(0, folder_selected)
172
+
173
+ def update_progress(self, current, total):
174
+ self.progress.set(int(current / total * 100))
175
+ self.progress_bar.update()
176
+
177
+ def sort_files(self):
178
+ input_folder = self.entry.get()
179
+ output_folder = os.path.join(input_folder, "Sorted")
180
+ model_path = "0Shot1Shot2ShotV0.1.pth"
181
+ model = load_model(model_path)
182
+ try:
183
+ sort_files(model, input_folder, output_folder, progress_callback=self.update_progress)
184
+ messagebox.showinfo("Success", "Files sorted successfully!")
185
+ except Exception as e:
186
+ messagebox.showerror("Error", str(e))
187
+
188
+ root = tk.Tk()
189
+ app = Application(master=root)
190
+ app.master.title("Sample Sorter")
191
+ app.mainloop()
training.log ADDED
@@ -0,0 +1,935 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-05-16 15:08:45,991 - root - ERROR - An error occurred: name 'os' is not defined
2
+ 2024-05-16 15:09:09,391 - root - INFO - Initializing SpectrogramDataset...
3
+ 2024-05-16 15:09:09,929 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
4
+ 2024-05-16 15:09:09,934 - root - INFO - SpectrogramDataset initialized successfully
5
+ 2024-05-16 15:09:09,934 - root - ERROR - An error occurred: name 'np' is not defined
6
+ 2024-05-16 15:09:43,969 - root - INFO - Initializing SpectrogramDataset...
7
+ 2024-05-16 15:09:44,476 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
8
+ 2024-05-16 15:09:44,481 - root - INFO - SpectrogramDataset initialized successfully
9
+ 2024-05-16 15:09:44,490 - root - ERROR - An error occurred: name 'RandomSampler' is not defined
10
+ 2024-05-16 15:10:48,213 - root - INFO - Initializing SpectrogramDataset...
11
+ 2024-05-16 15:10:48,734 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
12
+ 2024-05-16 15:10:48,739 - root - INFO - SpectrogramDataset initialized successfully
13
+ 2024-05-16 15:10:48,741 - root - ERROR - An error occurred: name 'SequentialSampler' is not defined
14
+ 2024-05-16 15:11:11,518 - root - INFO - Initializing SpectrogramDataset...
15
+ 2024-05-16 15:11:12,025 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
16
+ 2024-05-16 15:11:12,031 - root - INFO - SpectrogramDataset initialized successfully
17
+ 2024-05-16 15:11:12,337 - root - ERROR - An error occurred: list index out of range
18
+ 2024-05-16 15:19:51,771 - root - INFO - Initializing SpectrogramDataset...
19
+ 2024-05-16 15:19:52,293 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
20
+ 2024-05-16 15:19:52,298 - root - INFO - SpectrogramDataset initialized successfully
21
+ 2024-05-16 15:19:52,569 - root - ERROR - An error occurred: list index out of range
22
+ 2024-05-16 15:25:26,353 - root - INFO - Initializing SpectrogramDataset...
23
+ 2024-05-16 15:25:26,884 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
24
+ 2024-05-16 15:25:26,890 - root - INFO - SpectrogramDataset initialized successfully
25
+ 2024-05-16 15:25:26,892 - root - INFO - Dataset length: 2288
26
+ 2024-05-16 15:25:26,893 - root - INFO - Train dataset length: 1601
27
+ 2024-05-16 15:25:26,894 - root - INFO - Validation dataset length: 343
28
+ 2024-05-16 15:25:26,894 - root - INFO - Test dataset length: 344
29
+ 2024-05-16 15:25:30,518 - root - INFO - Train dataset verification passed
30
+ 2024-05-16 15:25:31,162 - root - INFO - Validation dataset verification passed
31
+ 2024-05-16 15:25:32,096 - root - INFO - Test dataset verification passed
32
+ 2024-05-16 15:25:32,406 - root - ERROR - An error occurred: list index out of range
33
+ 2024-05-16 15:31:30,879 - root - INFO - Initializing SpectrogramDataset...
34
+ 2024-05-16 15:31:31,394 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
35
+ 2024-05-16 15:31:31,400 - root - INFO - SpectrogramDataset initialized successfully
36
+ 2024-05-16 15:31:31,402 - root - ERROR - An error occurred: name 'verify_dataset_and_loader' is not defined
37
+ 2024-05-16 15:35:01,395 - root - INFO - Initializing SpectrogramDataset...
38
+ 2024-05-16 15:35:01,929 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
39
+ 2024-05-16 15:35:01,934 - root - INFO - SpectrogramDataset initialized successfully
40
+ 2024-05-16 15:35:01,937 - root - INFO - Dataset length: 2288
41
+ 2024-05-16 15:35:01,938 - root - INFO - Train dataset length: 1601
42
+ 2024-05-16 15:35:01,939 - root - INFO - Validation dataset length: 343
43
+ 2024-05-16 15:35:01,939 - root - INFO - Test dataset length: 344
44
+ 2024-05-16 15:35:05,709 - root - INFO - Train dataset verification passed
45
+ 2024-05-16 15:35:06,364 - root - INFO - Validation dataset verification passed
46
+ 2024-05-16 15:35:07,138 - root - INFO - Test dataset verification passed
47
+ 2024-05-16 15:35:07,141 - root - INFO - Train sampler indices: [1715, 212, 1663, 1641, 874, 2133, 230, 1692, 1653, 1717]... (total: 2288)
48
+ 2024-05-16 15:35:07,142 - root - ERROR - Train sampler index out of range: 2287 >= 1601
49
+ 2024-05-16 15:35:07,143 - root - INFO - Validation sampler indices: [230, 218, 4, 229, 290, 64, 207, 188, 115, 212]... (total: 343)
50
+ 2024-05-16 15:35:07,143 - root - INFO - Validation sampler indices within range.
51
+ 2024-05-16 15:35:07,144 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
52
+ 2024-05-16 15:35:07,145 - root - INFO - Test sampler indices within range.
53
+ 2024-05-16 15:35:07,435 - root - ERROR - An error occurred: list index out of range
54
+ 2024-05-16 15:38:08,245 - root - INFO - Initializing SpectrogramDataset...
55
+ 2024-05-16 15:38:08,784 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
56
+ 2024-05-16 15:38:08,789 - root - INFO - SpectrogramDataset initialized successfully
57
+ 2024-05-16 15:38:08,791 - root - ERROR - An error occurred: 'SpectrogramDataset' object has no attribute 'indices'
58
+ 2024-05-16 15:39:41,986 - root - INFO - Initializing SpectrogramDataset...
59
+ 2024-05-16 15:39:42,584 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
60
+ 2024-05-16 15:39:42,588 - root - INFO - SpectrogramDataset initialized successfully
61
+ 2024-05-16 15:39:42,591 - root - INFO - Dataset length: 2288
62
+ 2024-05-16 15:39:42,592 - root - INFO - Train dataset length: 1601
63
+ 2024-05-16 15:39:42,592 - root - INFO - Validation dataset length: 343
64
+ 2024-05-16 15:39:42,593 - root - INFO - Test dataset length: 344
65
+ 2024-05-16 15:39:46,571 - root - INFO - Train dataset verification passed
66
+ 2024-05-16 15:39:47,363 - root - INFO - Validation dataset verification passed
67
+ 2024-05-16 15:39:48,276 - root - INFO - Test dataset verification passed
68
+ 2024-05-16 15:39:48,278 - root - INFO - Train sampler indices: [57, 621, 222, 1233, 1204, 758, 1312, 357, 1105, 1504]... (total: 1601)
69
+ 2024-05-16 15:39:48,279 - root - INFO - Train sampler indices within range.
70
+ 2024-05-16 15:39:48,280 - root - INFO - Validation sampler indices: [208, 54, 29, 193, 121, 156, 339, 189, 301, 166]... (total: 343)
71
+ 2024-05-16 15:39:48,281 - root - INFO - Validation sampler indices within range.
72
+ 2024-05-16 15:39:48,282 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
73
+ 2024-05-16 15:39:48,283 - root - INFO - Test sampler indices within range.
74
+ 2024-05-16 15:39:50,020 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
75
+ 2024-05-16 15:41:07,216 - root - INFO - Initializing SpectrogramDataset...
76
+ 2024-05-16 15:41:07,794 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
77
+ 2024-05-16 15:41:07,799 - root - INFO - SpectrogramDataset initialized successfully
78
+ 2024-05-16 15:41:07,802 - root - INFO - Dataset length: 2288
79
+ 2024-05-16 15:41:07,802 - root - INFO - Train dataset length: 1601
80
+ 2024-05-16 15:41:07,803 - root - INFO - Validation dataset length: 343
81
+ 2024-05-16 15:41:07,804 - root - INFO - Test dataset length: 344
82
+ 2024-05-16 15:41:11,881 - root - INFO - Train dataset verification passed
83
+ 2024-05-16 15:41:12,832 - root - INFO - Validation dataset verification passed
84
+ 2024-05-16 15:41:13,661 - root - INFO - Test dataset verification passed
85
+ 2024-05-16 15:41:13,663 - root - INFO - Train sampler indices: [1180, 1565, 821, 15, 559, 111, 128, 1387, 1325, 1509]... (total: 1601)
86
+ 2024-05-16 15:41:13,664 - root - INFO - Train sampler indices within range.
87
+ 2024-05-16 15:41:13,665 - root - INFO - Validation sampler indices: [252, 171, 14, 36, 193, 141, 57, 38, 219, 65]... (total: 343)
88
+ 2024-05-16 15:41:13,665 - root - INFO - Validation sampler indices within range.
89
+ 2024-05-16 15:41:13,666 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
90
+ 2024-05-16 15:41:13,667 - root - INFO - Test sampler indices within range.
91
+ 2024-05-16 15:41:15,654 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
92
+ 2024-05-16 15:43:06,699 - root - INFO - Initializing SpectrogramDataset...
93
+ 2024-05-16 15:43:07,225 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
94
+ 2024-05-16 15:43:07,230 - root - INFO - SpectrogramDataset initialized successfully
95
+ 2024-05-16 15:43:07,232 - root - INFO - Dataset length: 2288
96
+ 2024-05-16 15:43:07,233 - root - INFO - Train dataset length: 1601
97
+ 2024-05-16 15:43:07,234 - root - INFO - Validation dataset length: 343
98
+ 2024-05-16 15:43:07,234 - root - INFO - Test dataset length: 344
99
+ 2024-05-16 15:43:10,655 - root - INFO - Train dataset verification passed
100
+ 2024-05-16 15:43:11,554 - root - INFO - Validation dataset verification passed
101
+ 2024-05-16 15:43:12,261 - root - INFO - Test dataset verification passed
102
+ 2024-05-16 15:43:12,264 - root - INFO - Train sampler indices: [976, 895, 296, 857, 1419, 1508, 1235, 341, 1009, 78]... (total: 1601)
103
+ 2024-05-16 15:43:12,265 - root - INFO - Train sampler indices within range.
104
+ 2024-05-16 15:43:12,267 - root - INFO - Validation sampler indices: [142, 152, 107, 169, 147, 12, 161, 15, 61, 141]... (total: 343)
105
+ 2024-05-16 15:43:12,267 - root - INFO - Validation sampler indices within range.
106
+ 2024-05-16 15:43:12,268 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
107
+ 2024-05-16 15:43:12,269 - root - INFO - Test sampler indices within range.
108
+ 2024-05-16 15:43:12,828 - root - ERROR - An error occurred: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
109
+ 2024-05-16 15:46:38,338 - root - INFO - Initializing SpectrogramDataset...
110
+ 2024-05-16 15:46:38,853 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
111
+ 2024-05-16 15:46:38,905 - root - INFO - SpectrogramDataset initialized successfully
112
+ 2024-05-16 15:46:38,909 - root - INFO - Dataset length: 2288
113
+ 2024-05-16 15:46:38,910 - root - INFO - Train dataset length: 1601
114
+ 2024-05-16 15:46:38,912 - root - INFO - Validation dataset length: 343
115
+ 2024-05-16 15:46:38,913 - root - INFO - Test dataset length: 344
116
+ 2024-05-16 15:46:42,470 - root - INFO - Train dataset verification passed
117
+ 2024-05-16 15:46:43,177 - root - INFO - Validation dataset verification passed
118
+ 2024-05-16 15:46:43,924 - root - INFO - Test dataset verification passed
119
+ 2024-05-16 15:46:43,927 - root - INFO - Train sampler indices: [772, 408, 1328, 1382, 558, 1027, 1482, 1487, 198, 69]... (total: 1601)
120
+ 2024-05-16 15:46:43,928 - root - INFO - Train sampler indices within range.
121
+ 2024-05-16 15:46:43,929 - root - INFO - Validation sampler indices: [13, 20, 65, 277, 248, 107, 263, 31, 179, 159]... (total: 343)
122
+ 2024-05-16 15:46:43,929 - root - INFO - Validation sampler indices within range.
123
+ 2024-05-16 15:46:43,930 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
124
+ 2024-05-16 15:46:43,931 - root - INFO - Test sampler indices within range.
125
+ 2024-05-16 15:46:44,414 - root - ERROR - An error occurred: 'AudioResNet' object has no attribute 'fc1'
126
+ 2024-05-16 15:50:57,787 - root - INFO - Initializing SpectrogramDataset...
127
+ 2024-05-16 15:50:58,328 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
128
+ 2024-05-16 15:50:58,333 - root - INFO - SpectrogramDataset initialized successfully
129
+ 2024-05-16 15:50:58,335 - root - INFO - Dataset length: 2288
130
+ 2024-05-16 15:50:58,336 - root - INFO - Train dataset length: 1601
131
+ 2024-05-16 15:50:58,337 - root - INFO - Validation dataset length: 343
132
+ 2024-05-16 15:50:58,337 - root - INFO - Test dataset length: 344
133
+ 2024-05-16 15:51:01,977 - root - INFO - Train dataset verification passed
134
+ 2024-05-16 15:51:02,979 - root - INFO - Validation dataset verification passed
135
+ 2024-05-16 15:51:03,681 - root - INFO - Test dataset verification passed
136
+ 2024-05-16 15:51:03,684 - root - INFO - Train sampler indices: [857, 128, 1276, 675, 178, 746, 1561, 1386, 1350, 1563]... (total: 1601)
137
+ 2024-05-16 15:51:03,685 - root - INFO - Train sampler indices within range.
138
+ 2024-05-16 15:51:03,686 - root - INFO - Validation sampler indices: [183, 83, 79, 230, 84, 20, 227, 30, 273, 196]... (total: 343)
139
+ 2024-05-16 15:51:03,686 - root - INFO - Validation sampler indices within range.
140
+ 2024-05-16 15:51:03,687 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
141
+ 2024-05-16 15:51:03,688 - root - INFO - Test sampler indices within range.
142
+ 2024-05-16 15:51:05,540 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
143
+ 2024-05-16 15:52:16,452 - root - INFO - Initializing SpectrogramDataset...
144
+ 2024-05-16 15:52:16,965 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
145
+ 2024-05-16 15:52:16,971 - root - INFO - SpectrogramDataset initialized successfully
146
+ 2024-05-16 15:52:16,973 - root - INFO - Dataset length: 2288
147
+ 2024-05-16 15:52:16,974 - root - INFO - Train dataset length: 1601
148
+ 2024-05-16 15:52:16,975 - root - INFO - Validation dataset length: 343
149
+ 2024-05-16 15:52:16,976 - root - INFO - Test dataset length: 344
150
+ 2024-05-16 15:52:20,456 - root - INFO - Train dataset verification passed
151
+ 2024-05-16 15:52:21,253 - root - INFO - Validation dataset verification passed
152
+ 2024-05-16 15:52:21,949 - root - INFO - Test dataset verification passed
153
+ 2024-05-16 15:52:21,952 - root - INFO - Train sampler indices: [299, 79, 986, 896, 1037, 1500, 744, 719, 643, 617]... (total: 1601)
154
+ 2024-05-16 15:52:21,953 - root - INFO - Train sampler indices within range.
155
+ 2024-05-16 15:52:21,954 - root - INFO - Validation sampler indices: [306, 310, 294, 202, 235, 302, 263, 115, 269, 131]... (total: 343)
156
+ 2024-05-16 15:52:21,954 - root - INFO - Validation sampler indices within range.
157
+ 2024-05-16 15:52:21,955 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
158
+ 2024-05-16 15:52:21,956 - root - INFO - Test sampler indices within range.
159
+ 2024-05-16 15:52:23,868 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
160
+ 2024-05-16 15:53:57,879 - root - INFO - Initializing SpectrogramDataset...
161
+ 2024-05-16 15:53:58,421 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
162
+ 2024-05-16 15:53:58,426 - root - INFO - SpectrogramDataset initialized successfully
163
+ 2024-05-16 15:53:58,428 - root - INFO - Dataset length: 2288
164
+ 2024-05-16 15:53:58,429 - root - INFO - Train dataset length: 1601
165
+ 2024-05-16 15:53:58,430 - root - INFO - Validation dataset length: 343
166
+ 2024-05-16 15:53:58,431 - root - INFO - Test dataset length: 344
167
+ 2024-05-16 15:54:01,990 - root - INFO - Train dataset verification passed
168
+ 2024-05-16 15:54:02,647 - root - INFO - Validation dataset verification passed
169
+ 2024-05-16 15:54:03,543 - root - INFO - Test dataset verification passed
170
+ 2024-05-16 15:54:03,546 - root - INFO - Train sampler indices: [1546, 728, 897, 1176, 902, 685, 927, 191, 553, 1434]... (total: 1601)
171
+ 2024-05-16 15:54:03,546 - root - INFO - Train sampler indices within range.
172
+ 2024-05-16 15:54:03,548 - root - INFO - Validation sampler indices: [293, 119, 112, 212, 257, 185, 237, 77, 285, 248]... (total: 343)
173
+ 2024-05-16 15:54:03,548 - root - INFO - Validation sampler indices within range.
174
+ 2024-05-16 15:54:03,549 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
175
+ 2024-05-16 15:54:03,550 - root - INFO - Test sampler indices within range.
176
+ 2024-05-16 15:54:05,500 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
177
+ 2024-05-16 16:40:54,571 - root - INFO - Initializing SpectrogramDataset...
178
+ 2024-05-16 16:40:55,090 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
179
+ 2024-05-16 16:40:55,095 - root - INFO - SpectrogramDataset initialized successfully
180
+ 2024-05-16 16:40:55,098 - root - INFO - Dataset length: 2288
181
+ 2024-05-16 16:40:55,099 - root - INFO - Train dataset length: 1601
182
+ 2024-05-16 16:40:55,099 - root - INFO - Validation dataset length: 343
183
+ 2024-05-16 16:40:55,100 - root - INFO - Test dataset length: 344
184
+ 2024-05-16 16:40:58,581 - root - INFO - Train dataset verification passed
185
+ 2024-05-16 16:40:59,386 - root - INFO - Validation dataset verification passed
186
+ 2024-05-16 16:41:00,025 - root - INFO - Test dataset verification passed
187
+ 2024-05-16 16:41:00,028 - root - INFO - Train sampler indices: [1258, 418, 585, 1154, 76, 11, 847, 845, 612, 483]... (total: 1601)
188
+ 2024-05-16 16:41:00,028 - root - INFO - Train sampler indices within range.
189
+ 2024-05-16 16:41:00,029 - root - INFO - Validation sampler indices: [185, 112, 269, 159, 203, 219, 94, 240, 34, 252]... (total: 343)
190
+ 2024-05-16 16:41:00,030 - root - INFO - Validation sampler indices within range.
191
+ 2024-05-16 16:41:00,030 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
192
+ 2024-05-16 16:41:00,031 - root - INFO - Test sampler indices within range.
193
+ 2024-05-16 16:41:01,972 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
194
+ 2024-05-16 16:42:14,104 - root - INFO - Initializing SpectrogramDataset...
195
+ 2024-05-16 16:42:14,609 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
196
+ 2024-05-16 16:42:14,615 - root - INFO - SpectrogramDataset initialized successfully
197
+ 2024-05-16 16:42:14,618 - root - INFO - Dataset length: 2288
198
+ 2024-05-16 16:42:14,619 - root - INFO - Train dataset length: 1601
199
+ 2024-05-16 16:42:14,619 - root - INFO - Validation dataset length: 343
200
+ 2024-05-16 16:42:14,620 - root - INFO - Test dataset length: 344
201
+ 2024-05-16 16:42:18,231 - root - INFO - Train dataset verification passed
202
+ 2024-05-16 16:42:18,857 - root - INFO - Validation dataset verification passed
203
+ 2024-05-16 16:42:19,612 - root - INFO - Test dataset verification passed
204
+ 2024-05-16 16:42:19,614 - root - INFO - Train sampler indices: [1079, 1334, 1520, 1425, 1063, 958, 1569, 283, 389, 1485]... (total: 1601)
205
+ 2024-05-16 16:42:19,615 - root - INFO - Train sampler indices within range.
206
+ 2024-05-16 16:42:19,616 - root - INFO - Validation sampler indices: [80, 280, 119, 79, 32, 196, 221, 326, 128, 141]... (total: 343)
207
+ 2024-05-16 16:42:19,616 - root - INFO - Validation sampler indices within range.
208
+ 2024-05-16 16:42:19,617 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
209
+ 2024-05-16 16:42:19,618 - root - INFO - Test sampler indices within range.
210
+ 2024-05-16 16:42:21,472 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
211
+ 2024-05-16 16:45:00,618 - root - INFO - Initializing SpectrogramDataset...
212
+ 2024-05-16 16:45:01,133 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
213
+ 2024-05-16 16:45:01,138 - root - INFO - SpectrogramDataset initialized successfully
214
+ 2024-05-16 16:45:01,141 - root - INFO - Dataset length: 2288
215
+ 2024-05-16 16:45:01,142 - root - INFO - Train dataset length: 1601
216
+ 2024-05-16 16:45:01,143 - root - INFO - Validation dataset length: 343
217
+ 2024-05-16 16:45:01,144 - root - INFO - Test dataset length: 344
218
+ 2024-05-16 16:45:04,845 - root - INFO - Train dataset verification passed
219
+ 2024-05-16 16:45:05,730 - root - INFO - Validation dataset verification passed
220
+ 2024-05-16 16:45:06,456 - root - INFO - Test dataset verification passed
221
+ 2024-05-16 16:45:06,459 - root - INFO - Train sampler indices: [1162, 1145, 1130, 1430, 470, 1266, 178, 1590, 1313, 1475]... (total: 1601)
222
+ 2024-05-16 16:45:06,459 - root - INFO - Train sampler indices within range.
223
+ 2024-05-16 16:45:06,461 - root - INFO - Validation sampler indices: [310, 213, 333, 315, 25, 224, 304, 210, 136, 134]... (total: 343)
224
+ 2024-05-16 16:45:06,461 - root - INFO - Validation sampler indices within range.
225
+ 2024-05-16 16:45:06,462 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
226
+ 2024-05-16 16:45:06,462 - root - INFO - Test sampler indices within range.
227
+ 2024-05-16 16:45:08,309 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (256x32768 and 8192x1024)
228
+ 2024-05-16 16:48:33,071 - root - INFO - Initializing SpectrogramDataset...
229
+ 2024-05-16 16:48:33,582 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
230
+ 2024-05-16 16:48:33,587 - root - INFO - SpectrogramDataset initialized successfully
231
+ 2024-05-16 16:48:33,590 - root - INFO - Dataset length: 2288
232
+ 2024-05-16 16:48:33,591 - root - INFO - Train dataset length: 1601
233
+ 2024-05-16 16:48:33,591 - root - INFO - Validation dataset length: 343
234
+ 2024-05-16 16:48:33,592 - root - INFO - Test dataset length: 344
235
+ 2024-05-16 16:48:37,170 - root - INFO - Train dataset verification passed
236
+ 2024-05-16 16:48:38,002 - root - INFO - Validation dataset verification passed
237
+ 2024-05-16 16:48:38,710 - root - INFO - Test dataset verification passed
238
+ 2024-05-16 16:48:38,713 - root - INFO - Train sampler indices: [937, 1119, 318, 526, 1492, 643, 231, 300, 479, 1239]... (total: 1601)
239
+ 2024-05-16 16:48:38,713 - root - INFO - Train sampler indices within range.
240
+ 2024-05-16 16:48:38,714 - root - INFO - Validation sampler indices: [240, 43, 198, 107, 57, 126, 341, 52, 128, 172]... (total: 343)
241
+ 2024-05-16 16:48:38,715 - root - INFO - Validation sampler indices within range.
242
+ 2024-05-16 16:48:38,716 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
243
+ 2024-05-16 16:48:38,716 - root - INFO - Test sampler indices within range.
244
+ 2024-05-16 16:53:13,787 - root - INFO - Initializing SpectrogramDataset...
245
+ 2024-05-16 16:53:14,367 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
246
+ 2024-05-16 16:53:14,373 - root - INFO - SpectrogramDataset initialized successfully
247
+ 2024-05-16 16:53:14,376 - root - INFO - Dataset length: 2288
248
+ 2024-05-16 16:53:14,377 - root - INFO - Train dataset length: 1601
249
+ 2024-05-16 16:53:14,378 - root - INFO - Validation dataset length: 343
250
+ 2024-05-16 16:53:14,378 - root - INFO - Test dataset length: 344
251
+ 2024-05-16 16:53:18,114 - root - INFO - Train dataset verification passed
252
+ 2024-05-16 16:53:18,700 - root - INFO - Validation dataset verification passed
253
+ 2024-05-16 16:53:19,364 - root - INFO - Test dataset verification passed
254
+ 2024-05-16 16:53:19,367 - root - INFO - Train sampler indices: [417, 305, 1305, 1228, 557, 285, 665, 354, 630, 7]... (total: 1601)
255
+ 2024-05-16 16:53:19,367 - root - INFO - Train sampler indices within range.
256
+ 2024-05-16 16:53:19,368 - root - INFO - Validation sampler indices: [132, 250, 298, 27, 275, 336, 224, 12, 267, 110]... (total: 343)
257
+ 2024-05-16 16:53:19,369 - root - INFO - Validation sampler indices within range.
258
+ 2024-05-16 16:53:19,369 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
259
+ 2024-05-16 16:53:19,370 - root - INFO - Test sampler indices within range.
260
+ 2024-05-16 16:54:30,006 - root - ERROR - An error occurred: mat1 and mat2 shapes cannot be multiplied (65x28672 and 32768x1024)
261
+ 2024-05-16 16:58:46,198 - root - INFO - Initializing SpectrogramDataset...
262
+ 2024-05-16 16:58:46,715 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
263
+ 2024-05-16 16:58:46,720 - root - INFO - SpectrogramDataset initialized successfully
264
+ 2024-05-16 16:58:46,723 - root - INFO - Dataset length: 2288
265
+ 2024-05-16 16:58:46,723 - root - INFO - Train dataset length: 1601
266
+ 2024-05-16 16:58:46,724 - root - INFO - Validation dataset length: 343
267
+ 2024-05-16 16:58:46,725 - root - INFO - Test dataset length: 344
268
+ 2024-05-16 16:58:50,330 - root - INFO - Train dataset verification passed
269
+ 2024-05-16 16:58:51,110 - root - INFO - Validation dataset verification passed
270
+ 2024-05-16 16:58:51,943 - root - INFO - Test dataset verification passed
271
+ 2024-05-16 16:58:51,945 - root - INFO - Train sampler indices: [963, 1570, 599, 1093, 923, 1455, 61, 711, 76, 753]... (total: 1601)
272
+ 2024-05-16 16:58:51,946 - root - INFO - Train sampler indices within range.
273
+ 2024-05-16 16:58:51,947 - root - INFO - Validation sampler indices: [93, 4, 216, 142, 203, 314, 263, 222, 326, 199]... (total: 343)
274
+ 2024-05-16 16:58:51,948 - root - INFO - Validation sampler indices within range.
275
+ 2024-05-16 16:58:51,948 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
276
+ 2024-05-16 16:58:51,949 - root - INFO - Test sampler indices within range.
277
+ 2024-05-16 17:01:19,991 - root - INFO - Initializing SpectrogramDataset...
278
+ 2024-05-16 17:01:20,507 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
279
+ 2024-05-16 17:01:20,512 - root - INFO - SpectrogramDataset initialized successfully
280
+ 2024-05-16 17:01:20,515 - root - INFO - Dataset length: 2288
281
+ 2024-05-16 17:01:20,516 - root - INFO - Train dataset length: 1601
282
+ 2024-05-16 17:01:20,516 - root - INFO - Validation dataset length: 343
283
+ 2024-05-16 17:01:20,517 - root - INFO - Test dataset length: 344
284
+ 2024-05-16 17:01:23,995 - root - INFO - Train dataset verification passed
285
+ 2024-05-16 17:01:24,677 - root - INFO - Validation dataset verification passed
286
+ 2024-05-16 17:01:25,476 - root - INFO - Test dataset verification passed
287
+ 2024-05-16 17:01:25,479 - root - INFO - Train sampler indices: [1387, 1163, 1160, 689, 400, 288, 1388, 1466, 1248, 921]... (total: 1601)
288
+ 2024-05-16 17:01:25,479 - root - INFO - Train sampler indices within range.
289
+ 2024-05-16 17:01:25,480 - root - INFO - Validation sampler indices: [18, 46, 244, 12, 240, 334, 280, 73, 322, 177]... (total: 343)
290
+ 2024-05-16 17:01:25,481 - root - INFO - Validation sampler indices within range.
291
+ 2024-05-16 17:01:25,481 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
292
+ 2024-05-16 17:01:25,482 - root - INFO - Test sampler indices within range.
293
+ 2024-05-16 17:09:53,291 - root - INFO - Initializing SpectrogramDataset...
294
+ 2024-05-16 17:09:53,807 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
295
+ 2024-05-16 17:09:53,965 - root - INFO - SpectrogramDataset initialized successfully
296
+ 2024-05-16 17:09:53,968 - root - INFO - Dataset length: 2288
297
+ 2024-05-16 17:09:53,969 - root - INFO - Train dataset length: 1601
298
+ 2024-05-16 17:09:53,970 - root - INFO - Validation dataset length: 343
299
+ 2024-05-16 17:09:53,971 - root - INFO - Test dataset length: 344
300
+ 2024-05-16 17:09:57,660 - root - INFO - Train dataset verification passed
301
+ 2024-05-16 17:09:58,343 - root - INFO - Validation dataset verification passed
302
+ 2024-05-16 17:09:59,001 - root - INFO - Test dataset verification passed
303
+ 2024-05-16 17:09:59,004 - root - INFO - Train sampler indices: [1020, 1164, 378, 1445, 1077, 545, 635, 390, 489, 52]... (total: 1601)
304
+ 2024-05-16 17:09:59,004 - root - INFO - Train sampler indices within range.
305
+ 2024-05-16 17:09:59,006 - root - INFO - Validation sampler indices: [317, 276, 168, 294, 80, 262, 68, 152, 337, 193]... (total: 343)
306
+ 2024-05-16 17:09:59,006 - root - INFO - Validation sampler indices within range.
307
+ 2024-05-16 17:09:59,007 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
308
+ 2024-05-16 17:09:59,007 - root - INFO - Test sampler indices within range.
309
+ 2024-05-16 17:14:42,976 - root - INFO - Initializing SpectrogramDataset...
310
+ 2024-05-16 17:14:43,536 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
311
+ 2024-05-16 17:14:43,541 - root - INFO - SpectrogramDataset initialized successfully
312
+ 2024-05-16 17:14:43,544 - root - INFO - Dataset length: 2288
313
+ 2024-05-16 17:14:43,544 - root - INFO - Train dataset length: 1601
314
+ 2024-05-16 17:14:43,545 - root - INFO - Validation dataset length: 343
315
+ 2024-05-16 17:14:43,546 - root - INFO - Test dataset length: 344
316
+ 2024-05-16 17:14:47,402 - root - INFO - Train dataset verification passed
317
+ 2024-05-16 17:14:48,119 - root - INFO - Validation dataset verification passed
318
+ 2024-05-16 17:14:48,836 - root - INFO - Test dataset verification passed
319
+ 2024-05-16 17:14:48,839 - root - INFO - Train sampler indices: [51, 468, 1020, 401, 1069, 884, 566, 1287, 1280, 514]... (total: 1601)
320
+ 2024-05-16 17:14:48,839 - root - INFO - Train sampler indices within range.
321
+ 2024-05-16 17:14:48,840 - root - INFO - Validation sampler indices: [40, 77, 104, 254, 113, 284, 119, 195, 133, 4]... (total: 343)
322
+ 2024-05-16 17:14:48,841 - root - INFO - Validation sampler indices within range.
323
+ 2024-05-16 17:14:48,841 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
324
+ 2024-05-16 17:14:48,842 - root - INFO - Test sampler indices within range.
325
+ 2024-05-16 17:16:34,292 - root - INFO - Initializing SpectrogramDataset...
326
+ 2024-05-16 17:16:34,820 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
327
+ 2024-05-16 17:16:34,825 - root - INFO - SpectrogramDataset initialized successfully
328
+ 2024-05-16 17:16:34,828 - root - INFO - Dataset length: 2288
329
+ 2024-05-16 17:16:34,829 - root - INFO - Train dataset length: 1601
330
+ 2024-05-16 17:16:34,830 - root - INFO - Validation dataset length: 343
331
+ 2024-05-16 17:16:34,831 - root - INFO - Test dataset length: 344
332
+ 2024-05-16 17:16:38,483 - root - INFO - Train dataset verification passed
333
+ 2024-05-16 17:16:39,261 - root - INFO - Validation dataset verification passed
334
+ 2024-05-16 17:16:40,178 - root - INFO - Test dataset verification passed
335
+ 2024-05-16 17:16:40,182 - root - INFO - Train sampler indices: [161, 1459, 1297, 1364, 621, 261, 361, 1526, 159, 676]... (total: 1601)
336
+ 2024-05-16 17:16:40,182 - root - INFO - Train sampler indices within range.
337
+ 2024-05-16 17:16:40,183 - root - INFO - Validation sampler indices: [108, 159, 16, 2, 255, 169, 322, 176, 257, 319]... (total: 343)
338
+ 2024-05-16 17:16:40,184 - root - INFO - Validation sampler indices within range.
339
+ 2024-05-16 17:16:40,185 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
340
+ 2024-05-16 17:16:40,185 - root - INFO - Test sampler indices within range.
341
+ 2024-05-16 17:22:38,962 - root - INFO - Initializing SpectrogramDataset...
342
+ 2024-05-16 17:22:39,476 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
343
+ 2024-05-16 17:22:39,482 - root - INFO - SpectrogramDataset initialized successfully
344
+ 2024-05-16 17:22:39,484 - root - INFO - Dataset length: 2288
345
+ 2024-05-16 17:22:39,485 - root - INFO - Train dataset length: 1601
346
+ 2024-05-16 17:22:39,486 - root - INFO - Validation dataset length: 343
347
+ 2024-05-16 17:22:39,486 - root - INFO - Test dataset length: 344
348
+ 2024-05-16 17:22:43,533 - root - INFO - Train dataset verification passed
349
+ 2024-05-16 17:22:44,327 - root - INFO - Validation dataset verification passed
350
+ 2024-05-16 17:22:45,030 - root - INFO - Test dataset verification passed
351
+ 2024-05-16 17:22:45,033 - root - INFO - Train sampler indices: [118, 829, 811, 1417, 665, 623, 127, 1084, 1138, 1530]... (total: 1601)
352
+ 2024-05-16 17:22:45,033 - root - INFO - Train sampler indices within range.
353
+ 2024-05-16 17:22:45,035 - root - INFO - Validation sampler indices: [143, 9, 118, 218, 205, 141, 320, 39, 336, 33]... (total: 343)
354
+ 2024-05-16 17:22:45,035 - root - INFO - Validation sampler indices within range.
355
+ 2024-05-16 17:22:45,036 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
356
+ 2024-05-16 17:22:45,036 - root - INFO - Test sampler indices within range.
357
+ 2024-05-16 17:25:24,529 - root - INFO - Initializing SpectrogramDataset...
358
+ 2024-05-16 17:25:25,119 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
359
+ 2024-05-16 17:25:25,125 - root - INFO - SpectrogramDataset initialized successfully
360
+ 2024-05-16 17:25:25,128 - root - INFO - Dataset length: 2288
361
+ 2024-05-16 17:25:25,129 - root - INFO - Train dataset length: 1601
362
+ 2024-05-16 17:25:25,130 - root - INFO - Validation dataset length: 343
363
+ 2024-05-16 17:25:25,131 - root - INFO - Test dataset length: 344
364
+ 2024-05-16 17:25:28,714 - root - INFO - Train dataset verification passed
365
+ 2024-05-16 17:25:29,462 - root - INFO - Validation dataset verification passed
366
+ 2024-05-16 17:25:30,173 - root - INFO - Test dataset verification passed
367
+ 2024-05-16 17:25:30,176 - root - INFO - Train sampler indices: [902, 936, 524, 793, 626, 1586, 205, 1589, 421, 1497]... (total: 1601)
368
+ 2024-05-16 17:25:30,176 - root - INFO - Train sampler indices within range.
369
+ 2024-05-16 17:25:30,177 - root - INFO - Validation sampler indices: [231, 277, 199, 19, 226, 308, 339, 291, 36, 148]... (total: 343)
370
+ 2024-05-16 17:25:30,178 - root - INFO - Validation sampler indices within range.
371
+ 2024-05-16 17:25:30,178 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
372
+ 2024-05-16 17:25:30,179 - root - INFO - Test sampler indices within range.
373
+ 2024-05-16 17:27:12,712 - root - INFO - Initializing SpectrogramDataset...
374
+ 2024-05-16 17:27:13,220 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
375
+ 2024-05-16 17:27:13,226 - root - INFO - SpectrogramDataset initialized successfully
376
+ 2024-05-16 17:27:13,229 - root - INFO - Dataset length: 2288
377
+ 2024-05-16 17:27:13,230 - root - INFO - Train dataset length: 1601
378
+ 2024-05-16 17:27:13,231 - root - INFO - Validation dataset length: 343
379
+ 2024-05-16 17:27:13,231 - root - INFO - Test dataset length: 344
380
+ 2024-05-16 17:27:16,751 - root - INFO - Train dataset verification passed
381
+ 2024-05-16 17:27:17,505 - root - INFO - Validation dataset verification passed
382
+ 2024-05-16 17:27:18,216 - root - INFO - Test dataset verification passed
383
+ 2024-05-16 17:27:18,219 - root - INFO - Train sampler indices: [554, 203, 939, 1461, 214, 1459, 1, 114, 1008, 835]... (total: 1601)
384
+ 2024-05-16 17:27:18,219 - root - INFO - Train sampler indices within range.
385
+ 2024-05-16 17:27:18,221 - root - INFO - Validation sampler indices: [134, 260, 160, 205, 259, 177, 241, 41, 48, 58]... (total: 343)
386
+ 2024-05-16 17:27:18,221 - root - INFO - Validation sampler indices within range.
387
+ 2024-05-16 17:27:18,222 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
388
+ 2024-05-16 17:27:18,222 - root - INFO - Test sampler indices within range.
389
+ 2024-05-16 17:32:36,459 - root - INFO - Initializing SpectrogramDataset...
390
+ 2024-05-16 17:32:37,002 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
391
+ 2024-05-16 17:32:37,008 - root - INFO - SpectrogramDataset initialized successfully
392
+ 2024-05-16 17:32:37,011 - root - INFO - Dataset length: 2288
393
+ 2024-05-16 17:32:37,012 - root - INFO - Train dataset length: 1601
394
+ 2024-05-16 17:32:37,013 - root - INFO - Validation dataset length: 343
395
+ 2024-05-16 17:32:37,014 - root - INFO - Test dataset length: 344
396
+ 2024-05-16 17:32:40,988 - root - INFO - Train dataset verification passed
397
+ 2024-05-16 17:32:41,669 - root - INFO - Validation dataset verification passed
398
+ 2024-05-16 17:32:42,237 - root - INFO - Test dataset verification passed
399
+ 2024-05-16 17:32:42,239 - root - INFO - Train sampler indices: [1107, 648, 26, 1289, 277, 753, 139, 1574, 579, 566]... (total: 1601)
400
+ 2024-05-16 17:32:42,240 - root - INFO - Train sampler indices within range.
401
+ 2024-05-16 17:32:42,241 - root - INFO - Validation sampler indices: [324, 93, 175, 231, 205, 84, 1, 66, 140, 120]... (total: 343)
402
+ 2024-05-16 17:32:42,242 - root - INFO - Validation sampler indices within range.
403
+ 2024-05-16 17:32:42,242 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
404
+ 2024-05-16 17:32:42,243 - root - INFO - Test sampler indices within range.
405
+ 2024-05-16 17:35:48,077 - root - INFO - Initializing SpectrogramDataset...
406
+ 2024-05-16 17:35:48,610 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
407
+ 2024-05-16 17:35:48,614 - root - INFO - SpectrogramDataset initialized successfully
408
+ 2024-05-16 17:35:48,617 - root - INFO - Dataset length: 2288
409
+ 2024-05-16 17:35:48,618 - root - INFO - Train dataset length: 1601
410
+ 2024-05-16 17:35:48,619 - root - INFO - Validation dataset length: 343
411
+ 2024-05-16 17:35:48,619 - root - INFO - Test dataset length: 344
412
+ 2024-05-16 17:35:52,394 - root - INFO - Train dataset verification passed
413
+ 2024-05-16 17:35:53,318 - root - INFO - Validation dataset verification passed
414
+ 2024-05-16 17:35:54,123 - root - INFO - Test dataset verification passed
415
+ 2024-05-16 17:35:54,127 - root - INFO - Train sampler indices: [927, 1138, 180, 622, 0, 824, 702, 784, 273, 1378]... (total: 1601)
416
+ 2024-05-16 17:35:54,127 - root - INFO - Train sampler indices within range.
417
+ 2024-05-16 17:35:54,129 - root - INFO - Validation sampler indices: [192, 283, 183, 187, 227, 32, 199, 268, 174, 259]... (total: 343)
418
+ 2024-05-16 17:35:54,130 - root - INFO - Validation sampler indices within range.
419
+ 2024-05-16 17:35:54,131 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
420
+ 2024-05-16 17:35:54,132 - root - INFO - Test sampler indices within range.
421
+ 2024-05-16 17:36:27,073 - root - INFO - Initializing SpectrogramDataset...
422
+ 2024-05-16 17:36:27,582 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
423
+ 2024-05-16 17:36:27,587 - root - INFO - SpectrogramDataset initialized successfully
424
+ 2024-05-16 17:36:27,590 - root - INFO - Dataset length: 2288
425
+ 2024-05-16 17:36:27,591 - root - INFO - Train dataset length: 1601
426
+ 2024-05-16 17:36:27,592 - root - INFO - Validation dataset length: 343
427
+ 2024-05-16 17:36:27,593 - root - INFO - Test dataset length: 344
428
+ 2024-05-16 17:36:31,059 - root - INFO - Train dataset verification passed
429
+ 2024-05-16 17:36:31,803 - root - INFO - Validation dataset verification passed
430
+ 2024-05-16 17:36:32,610 - root - INFO - Test dataset verification passed
431
+ 2024-05-16 17:36:32,613 - root - INFO - Train sampler indices: [837, 328, 1195, 909, 1489, 664, 151, 1415, 267, 484]... (total: 1601)
432
+ 2024-05-16 17:36:32,613 - root - INFO - Train sampler indices within range.
433
+ 2024-05-16 17:36:32,615 - root - INFO - Validation sampler indices: [123, 143, 321, 66, 222, 160, 292, 324, 64, 103]... (total: 343)
434
+ 2024-05-16 17:36:32,615 - root - INFO - Validation sampler indices within range.
435
+ 2024-05-16 17:36:32,616 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
436
+ 2024-05-16 17:36:32,617 - root - INFO - Test sampler indices within range.
437
+ 2024-05-16 17:38:25,497 - root - INFO - Initializing SpectrogramDataset...
438
+ 2024-05-16 17:38:26,055 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
439
+ 2024-05-16 17:38:26,060 - root - INFO - SpectrogramDataset initialized successfully
440
+ 2024-05-16 17:38:26,063 - root - INFO - Dataset length: 2288
441
+ 2024-05-16 17:38:26,064 - root - INFO - Train dataset length: 1601
442
+ 2024-05-16 17:38:26,064 - root - INFO - Validation dataset length: 343
443
+ 2024-05-16 17:38:26,065 - root - INFO - Test dataset length: 344
444
+ 2024-05-16 17:38:29,643 - root - INFO - Train dataset verification passed
445
+ 2024-05-16 17:38:30,352 - root - INFO - Validation dataset verification passed
446
+ 2024-05-16 17:38:31,124 - root - INFO - Test dataset verification passed
447
+ 2024-05-16 17:38:31,127 - root - INFO - Train sampler indices: [175, 1137, 485, 1569, 1512, 540, 916, 448, 467, 1365]... (total: 1601)
448
+ 2024-05-16 17:38:31,127 - root - INFO - Train sampler indices within range.
449
+ 2024-05-16 17:38:31,129 - root - INFO - Validation sampler indices: [79, 304, 232, 145, 290, 57, 301, 45, 261, 97]... (total: 343)
450
+ 2024-05-16 17:38:31,129 - root - INFO - Validation sampler indices within range.
451
+ 2024-05-16 17:38:31,130 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
452
+ 2024-05-16 17:38:31,130 - root - INFO - Test sampler indices within range.
453
+ 2024-05-16 17:42:09,758 - root - INFO - Initializing SpectrogramDataset...
454
+ 2024-05-16 17:42:10,265 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
455
+ 2024-05-16 17:42:10,270 - root - INFO - SpectrogramDataset initialized successfully
456
+ 2024-05-16 17:42:10,273 - root - INFO - Dataset length: 2288
457
+ 2024-05-16 17:42:10,274 - root - INFO - Train dataset length: 1601
458
+ 2024-05-16 17:42:10,274 - root - INFO - Validation dataset length: 343
459
+ 2024-05-16 17:42:10,275 - root - INFO - Test dataset length: 344
460
+ 2024-05-16 17:42:13,857 - root - INFO - Train dataset verification passed
461
+ 2024-05-16 17:42:14,445 - root - INFO - Validation dataset verification passed
462
+ 2024-05-16 17:42:15,193 - root - INFO - Test dataset verification passed
463
+ 2024-05-16 17:42:15,195 - root - INFO - Train sampler indices: [480, 1221, 1063, 1056, 567, 1140, 877, 909, 686, 1147]... (total: 1601)
464
+ 2024-05-16 17:42:15,195 - root - INFO - Train sampler indices within range.
465
+ 2024-05-16 17:42:15,196 - root - INFO - Validation sampler indices: [12, 273, 22, 283, 14, 231, 4, 316, 229, 232]... (total: 343)
466
+ 2024-05-16 17:42:15,197 - root - INFO - Validation sampler indices within range.
467
+ 2024-05-16 17:42:15,198 - root - INFO - Test sampler indices: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]... (total: 344)
468
+ 2024-05-16 17:42:15,198 - root - INFO - Test sampler indices within range.
469
+ 2024-05-16 19:59:59,273 - root - INFO - Epoch 1:
470
+ Training Loss: 1.5577, Training Accuracy: 0.3242, Validation Loss: 1.6561, Validation Accuracy: 0.1603
471
+
472
+ 2024-05-16 19:59:59,275 - root - INFO - Current learning rate: 0.00014687223021475341
473
+ 2024-05-16 20:00:16,791 - root - INFO - Epoch 2:
474
+ Training Loss: 1.1934, Training Accuracy: 0.5572, Validation Loss: 1.6995, Validation Accuracy: 0.1545
475
+
476
+ 2024-05-16 20:00:16,792 - root - INFO - Current learning rate: 0.00014687223021475341
477
+ 2024-05-16 20:00:33,986 - root - INFO - Epoch 3:
478
+ Training Loss: 1.0130, Training Accuracy: 0.6140, Validation Loss: 1.6373, Validation Accuracy: 0.1983
479
+
480
+ 2024-05-16 20:00:33,987 - root - INFO - Current learning rate: 0.00014687223021475341
481
+ 2024-05-16 20:00:51,043 - root - INFO - Epoch 4:
482
+ Training Loss: 0.9106, Training Accuracy: 0.6452, Validation Loss: 1.6587, Validation Accuracy: 0.3586
483
+
484
+ 2024-05-16 20:00:51,044 - root - INFO - Current learning rate: 0.00014687223021475341
485
+ 2024-05-16 20:01:07,976 - root - INFO - Epoch 5:
486
+ Training Loss: 0.8757, Training Accuracy: 0.6377, Validation Loss: 0.9697, Validation Accuracy: 0.6501
487
+
488
+ 2024-05-16 20:01:07,977 - root - INFO - Current learning rate: 0.00014687223021475341
489
+ 2024-05-16 20:01:25,453 - root - INFO - Epoch 6:
490
+ Training Loss: 0.7976, Training Accuracy: 0.6677, Validation Loss: 0.8183, Validation Accuracy: 0.6618
491
+
492
+ 2024-05-16 20:01:25,454 - root - INFO - Current learning rate: 0.00014687223021475341
493
+ 2024-05-16 20:01:42,979 - root - INFO - Epoch 7:
494
+ Training Loss: 0.7621, Training Accuracy: 0.7021, Validation Loss: 0.8188, Validation Accuracy: 0.6822
495
+
496
+ 2024-05-16 20:01:42,980 - root - INFO - Current learning rate: 0.00014687223021475341
497
+ 2024-05-16 20:02:00,123 - root - INFO - Epoch 8:
498
+ Training Loss: 0.7261, Training Accuracy: 0.7164, Validation Loss: 0.8117, Validation Accuracy: 0.6939
499
+
500
+ 2024-05-16 20:02:00,124 - root - INFO - Current learning rate: 0.00014687223021475341
501
+ 2024-05-16 20:02:17,571 - root - INFO - Epoch 9:
502
+ Training Loss: 0.6669, Training Accuracy: 0.7439, Validation Loss: 1.3692, Validation Accuracy: 0.4111
503
+
504
+ 2024-05-16 20:02:17,572 - root - INFO - Current learning rate: 0.00014687223021475341
505
+ 2024-05-16 20:02:35,083 - root - INFO - Epoch 10:
506
+ Training Loss: 0.6629, Training Accuracy: 0.7383, Validation Loss: 1.0841, Validation Accuracy: 0.5656
507
+
508
+ 2024-05-16 20:02:35,084 - root - INFO - Current learning rate: 0.00014687223021475341
509
+ 2024-05-16 20:02:35,156 - root - INFO - Model saved to checkpoint_epoch_10.pth
510
+ 2024-05-16 20:02:52,706 - root - INFO - Epoch 11:
511
+ Training Loss: 0.6576, Training Accuracy: 0.7639, Validation Loss: 1.1429, Validation Accuracy: 0.4985
512
+
513
+ 2024-05-16 20:02:52,706 - root - INFO - Current learning rate: 0.00014687223021475341
514
+ 2024-05-16 20:03:09,804 - root - INFO - Epoch 12:
515
+ Training Loss: 0.6069, Training Accuracy: 0.7758, Validation Loss: 0.6139, Validation Accuracy: 0.7580
516
+
517
+ 2024-05-16 20:03:09,805 - root - INFO - Current learning rate: 0.00014687223021475341
518
+ 2024-05-16 20:03:27,549 - root - INFO - Epoch 13:
519
+ Training Loss: 0.6503, Training Accuracy: 0.7676, Validation Loss: 0.7179, Validation Accuracy: 0.7405
520
+
521
+ 2024-05-16 20:03:27,550 - root - INFO - Current learning rate: 0.00014687223021475341
522
+ 2024-05-16 20:03:45,089 - root - INFO - Epoch 14:
523
+ Training Loss: 0.6080, Training Accuracy: 0.7739, Validation Loss: 0.8486, Validation Accuracy: 0.6735
524
+
525
+ 2024-05-16 20:03:45,090 - root - INFO - Current learning rate: 0.00014687223021475341
526
+ 2024-05-16 20:04:02,210 - root - INFO - Epoch 15:
527
+ Training Loss: 0.5748, Training Accuracy: 0.7901, Validation Loss: 0.5868, Validation Accuracy: 0.7813
528
+
529
+ 2024-05-16 20:04:02,211 - root - INFO - Current learning rate: 0.00014687223021475341
530
+ 2024-05-16 20:04:20,031 - root - INFO - Epoch 16:
531
+ Training Loss: 0.5869, Training Accuracy: 0.7914, Validation Loss: 0.6960, Validation Accuracy: 0.7551
532
+
533
+ 2024-05-16 20:04:20,033 - root - INFO - Current learning rate: 0.00014687223021475341
534
+ 2024-05-16 20:04:37,050 - root - INFO - Epoch 17:
535
+ Training Loss: 0.5558, Training Accuracy: 0.8082, Validation Loss: 0.8577, Validation Accuracy: 0.6297
536
+
537
+ 2024-05-16 20:04:37,051 - root - INFO - Current learning rate: 0.00014687223021475341
538
+ 2024-05-16 20:04:54,387 - root - INFO - Epoch 18:
539
+ Training Loss: 0.4989, Training Accuracy: 0.8126, Validation Loss: 0.7182, Validation Accuracy: 0.7230
540
+
541
+ 2024-05-16 20:04:54,388 - root - INFO - Current learning rate: 0.00014687223021475341
542
+ 2024-05-16 20:05:11,701 - root - INFO - Epoch 19:
543
+ Training Loss: 0.4998, Training Accuracy: 0.8239, Validation Loss: 1.1774, Validation Accuracy: 0.5073
544
+
545
+ 2024-05-16 20:05:11,702 - root - INFO - Current learning rate: 1.4687223021475341e-05
546
+ 2024-05-16 20:05:28,909 - root - INFO - Epoch 20:
547
+ Training Loss: 0.4958, Training Accuracy: 0.8245, Validation Loss: 0.6923, Validation Accuracy: 0.7201
548
+
549
+ 2024-05-16 20:05:28,910 - root - INFO - Current learning rate: 1.4687223021475341e-05
550
+ 2024-05-16 20:05:29,023 - root - INFO - Model saved to checkpoint_epoch_20.pth
551
+ 2024-05-16 20:05:46,100 - root - INFO - Epoch 21:
552
+ Training Loss: 0.4622, Training Accuracy: 0.8332, Validation Loss: 0.5315, Validation Accuracy: 0.8017
553
+
554
+ 2024-05-16 20:05:46,101 - root - INFO - Current learning rate: 1.4687223021475341e-05
555
+ 2024-05-16 20:06:03,727 - root - INFO - Epoch 22:
556
+ Training Loss: 0.4357, Training Accuracy: 0.8463, Validation Loss: 0.4926, Validation Accuracy: 0.8163
557
+
558
+ 2024-05-16 20:06:03,728 - root - INFO - Current learning rate: 1.4687223021475341e-05
559
+ 2024-05-16 20:06:21,316 - root - INFO - Epoch 23:
560
+ Training Loss: 0.4551, Training Accuracy: 0.8332, Validation Loss: 0.5084, Validation Accuracy: 0.8105
561
+
562
+ 2024-05-16 20:06:21,318 - root - INFO - Current learning rate: 1.4687223021475341e-05
563
+ 2024-05-16 20:06:38,567 - root - INFO - Epoch 24:
564
+ Training Loss: 0.4457, Training Accuracy: 0.8326, Validation Loss: 0.4975, Validation Accuracy: 0.8309
565
+
566
+ 2024-05-16 20:06:38,568 - root - INFO - Current learning rate: 1.4687223021475341e-05
567
+ 2024-05-16 20:06:55,865 - root - INFO - Epoch 25:
568
+ Training Loss: 0.4442, Training Accuracy: 0.8445, Validation Loss: 0.5614, Validation Accuracy: 0.7726
569
+
570
+ 2024-05-16 20:06:55,866 - root - INFO - Current learning rate: 1.4687223021475341e-05
571
+ 2024-05-16 20:07:12,862 - root - INFO - Epoch 26:
572
+ Training Loss: 0.4198, Training Accuracy: 0.8482, Validation Loss: 0.5582, Validation Accuracy: 0.7872
573
+
574
+ 2024-05-16 20:07:12,863 - root - INFO - Current learning rate: 1.4687223021475343e-06
575
+ 2024-05-16 20:07:29,969 - root - INFO - Epoch 27:
576
+ Training Loss: 0.4044, Training Accuracy: 0.8576, Validation Loss: 0.5670, Validation Accuracy: 0.7784
577
+
578
+ 2024-05-16 20:07:29,970 - root - INFO - Current learning rate: 1.4687223021475343e-06
579
+ 2024-05-16 20:07:47,649 - root - INFO - Epoch 28:
580
+ Training Loss: 0.3945, Training Accuracy: 0.8638, Validation Loss: 0.5677, Validation Accuracy: 0.7930
581
+
582
+ 2024-05-16 20:07:47,650 - root - INFO - Current learning rate: 1.4687223021475343e-06
583
+ 2024-05-16 20:08:05,090 - root - INFO - Epoch 29:
584
+ Training Loss: 0.4371, Training Accuracy: 0.8463, Validation Loss: 0.5071, Validation Accuracy: 0.8105
585
+
586
+ 2024-05-16 20:08:05,091 - root - INFO - Current learning rate: 1.4687223021475343e-06
587
+ 2024-05-16 20:08:22,390 - root - INFO - Epoch 30:
588
+ Training Loss: 0.3655, Training Accuracy: 0.8713, Validation Loss: 0.5345, Validation Accuracy: 0.8105
589
+
590
+ 2024-05-16 20:08:22,391 - root - INFO - Current learning rate: 1.4687223021475343e-07
591
+ 2024-05-16 20:08:22,461 - root - INFO - Model saved to checkpoint_epoch_30.pth
592
+ 2024-05-16 20:08:39,718 - root - INFO - Epoch 31:
593
+ Training Loss: 0.4207, Training Accuracy: 0.8376, Validation Loss: 0.4701, Validation Accuracy: 0.8426
594
+
595
+ 2024-05-16 20:08:39,719 - root - INFO - Current learning rate: 1.4687223021475343e-07
596
+ 2024-05-16 20:08:57,038 - root - INFO - Epoch 32:
597
+ Training Loss: 0.4016, Training Accuracy: 0.8588, Validation Loss: 0.5002, Validation Accuracy: 0.8251
598
+
599
+ 2024-05-16 20:08:57,039 - root - INFO - Current learning rate: 1.4687223021475343e-07
600
+ 2024-05-16 20:09:14,469 - root - INFO - Epoch 33:
601
+ Training Loss: 0.3913, Training Accuracy: 0.8507, Validation Loss: 0.5197, Validation Accuracy: 0.8192
602
+
603
+ 2024-05-16 20:09:14,470 - root - INFO - Current learning rate: 1.4687223021475343e-07
604
+ 2024-05-16 20:09:31,318 - root - INFO - Epoch 34:
605
+ Training Loss: 0.3930, Training Accuracy: 0.8582, Validation Loss: 0.5009, Validation Accuracy: 0.8163
606
+
607
+ 2024-05-16 20:09:31,319 - root - INFO - Current learning rate: 1.4687223021475343e-07
608
+ 2024-05-16 20:09:48,349 - root - INFO - Epoch 35:
609
+ Training Loss: 0.4068, Training Accuracy: 0.8582, Validation Loss: 0.5252, Validation Accuracy: 0.8017
610
+
611
+ 2024-05-16 20:09:48,350 - root - INFO - Current learning rate: 1.4687223021475344e-08
612
+ 2024-05-16 20:10:05,715 - root - INFO - Epoch 36:
613
+ Training Loss: 0.3837, Training Accuracy: 0.8626, Validation Loss: 0.4920, Validation Accuracy: 0.8222
614
+
615
+ 2024-05-16 20:10:05,716 - root - INFO - Current learning rate: 1.4687223021475344e-08
616
+ 2024-05-16 20:10:22,830 - root - INFO - Epoch 37:
617
+ Training Loss: 0.3958, Training Accuracy: 0.8551, Validation Loss: 0.5132, Validation Accuracy: 0.8017
618
+
619
+ 2024-05-16 20:10:22,831 - root - INFO - Current learning rate: 1.4687223021475344e-08
620
+ 2024-05-16 20:10:39,743 - root - INFO - Epoch 38:
621
+ Training Loss: 0.4118, Training Accuracy: 0.8545, Validation Loss: 0.4982, Validation Accuracy: 0.8222
622
+
623
+ 2024-05-16 20:10:39,744 - root - INFO - Current learning rate: 1.4687223021475344e-08
624
+ 2024-05-16 20:10:56,961 - root - INFO - Epoch 39:
625
+ Training Loss: 0.3992, Training Accuracy: 0.8501, Validation Loss: 0.5586, Validation Accuracy: 0.7813
626
+
627
+ 2024-05-16 20:10:56,962 - root - INFO - Current learning rate: 1.4687223021475344e-09
628
+ 2024-05-16 20:11:14,143 - root - INFO - Epoch 40:
629
+ Training Loss: 0.4223, Training Accuracy: 0.8407, Validation Loss: 0.5121, Validation Accuracy: 0.8017
630
+
631
+ 2024-05-16 20:11:14,144 - root - INFO - Current learning rate: 1.4687223021475344e-09
632
+ 2024-05-16 20:11:14,223 - root - INFO - Model saved to checkpoint_epoch_40.pth
633
+ 2024-05-16 20:11:31,461 - root - INFO - Epoch 41:
634
+ Training Loss: 0.4029, Training Accuracy: 0.8570, Validation Loss: 0.4884, Validation Accuracy: 0.8280
635
+
636
+ 2024-05-16 20:11:31,462 - root - INFO - Current learning rate: 1.4687223021475344e-09
637
+ 2024-05-16 20:11:48,923 - root - INFO - Epoch 42:
638
+ Training Loss: 0.3903, Training Accuracy: 0.8526, Validation Loss: 0.5349, Validation Accuracy: 0.8017
639
+
640
+ 2024-05-16 20:11:48,924 - root - INFO - Current learning rate: 1.4687223021475344e-09
641
+ 2024-05-16 20:12:06,239 - root - INFO - Epoch 43:
642
+ Training Loss: 0.3991, Training Accuracy: 0.8595, Validation Loss: 0.5401, Validation Accuracy: 0.7784
643
+
644
+ 2024-05-16 20:12:06,240 - root - INFO - Current learning rate: 1.4687223021475344e-09
645
+ 2024-05-16 20:12:23,515 - root - INFO - Epoch 44:
646
+ Training Loss: 0.4197, Training Accuracy: 0.8395, Validation Loss: 0.5497, Validation Accuracy: 0.7872
647
+
648
+ 2024-05-16 20:12:23,516 - root - INFO - Current learning rate: 1.4687223021475344e-09
649
+ 2024-05-16 20:12:40,642 - root - INFO - Epoch 45:
650
+ Training Loss: 0.4323, Training Accuracy: 0.8438, Validation Loss: 0.5315, Validation Accuracy: 0.8076
651
+
652
+ 2024-05-16 20:12:40,643 - root - INFO - Current learning rate: 1.4687223021475344e-09
653
+ 2024-05-16 20:12:58,112 - root - INFO - Epoch 46:
654
+ Training Loss: 0.3983, Training Accuracy: 0.8557, Validation Loss: 0.5449, Validation Accuracy: 0.7959
655
+
656
+ 2024-05-16 20:12:58,113 - root - INFO - Current learning rate: 1.4687223021475344e-09
657
+ 2024-05-16 20:13:15,440 - root - INFO - Epoch 47:
658
+ Training Loss: 0.3883, Training Accuracy: 0.8545, Validation Loss: 0.5234, Validation Accuracy: 0.8076
659
+
660
+ 2024-05-16 20:13:15,441 - root - INFO - Current learning rate: 1.4687223021475344e-09
661
+ 2024-05-16 20:13:32,209 - root - INFO - Epoch 48:
662
+ Training Loss: 0.4173, Training Accuracy: 0.8432, Validation Loss: 0.5416, Validation Accuracy: 0.7930
663
+
664
+ 2024-05-16 20:13:32,210 - root - INFO - Current learning rate: 1.4687223021475344e-09
665
+ 2024-05-16 20:13:49,067 - root - INFO - Epoch 49:
666
+ Training Loss: 0.4379, Training Accuracy: 0.8389, Validation Loss: 0.5227, Validation Accuracy: 0.8076
667
+
668
+ 2024-05-16 20:13:49,068 - root - INFO - Current learning rate: 1.4687223021475344e-09
669
+ 2024-05-16 20:14:06,293 - root - INFO - Epoch 50:
670
+ Training Loss: 0.4189, Training Accuracy: 0.8389, Validation Loss: 0.5142, Validation Accuracy: 0.8076
671
+
672
+ 2024-05-16 20:14:06,294 - root - INFO - Current learning rate: 1.4687223021475344e-09
673
+ 2024-05-16 20:14:06,363 - root - INFO - Model saved to checkpoint_epoch_50.pth
674
+ 2024-05-16 20:14:07,450 - root - INFO - precision recall f1-score support
675
+
676
+ 808 0.89 0.93 0.91 44
677
+ Clap 0.51 0.79 0.62 24
678
+ Closed Hat 0.77 0.81 0.79 54
679
+ Kick 0.93 0.89 0.91 114
680
+ Open Hat 0.80 0.76 0.78 21
681
+ Snare 0.80 0.69 0.74 87
682
+
683
+ accuracy 0.82 344
684
+ macro avg 0.78 0.81 0.79 344
685
+ weighted avg 0.83 0.82 0.82 344
686
+
687
+ 2024-05-16 22:00:46,650 - root - INFO - Initializing SpectrogramDataset...
688
+ 2024-05-16 22:00:47,165 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
689
+ 2024-05-16 22:00:47,171 - root - INFO - SpectrogramDataset initialized successfully
690
+ 2024-05-16 22:00:47,377 - root - ERROR - An error occurred: name 'nn' is not defined
691
+ 2024-05-16 22:01:22,777 - root - INFO - Initializing SpectrogramDataset...
692
+ 2024-05-16 22:01:23,295 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
693
+ 2024-05-16 22:01:23,300 - root - INFO - SpectrogramDataset initialized successfully
694
+ 2024-05-16 22:01:42,720 - root - INFO - Epoch 1:
695
+ Training Loss: 1.5260, Training Accuracy: 0.3385, Validation Loss: 1.6393, Validation Accuracy: 0.2624
696
+
697
+ 2024-05-16 22:01:42,722 - root - INFO - Current learning rate: 0.00014687223021475341
698
+ 2024-05-16 22:02:00,523 - root - INFO - Epoch 2:
699
+ Training Loss: 1.2230, Training Accuracy: 0.5228, Validation Loss: 1.5649, Validation Accuracy: 0.3120
700
+
701
+ 2024-05-16 22:02:00,524 - root - INFO - Current learning rate: 0.00014687223021475341
702
+ 2024-05-16 22:02:18,855 - root - INFO - Epoch 3:
703
+ Training Loss: 1.0560, Training Accuracy: 0.5853, Validation Loss: 1.5721, Validation Accuracy: 0.2886
704
+
705
+ 2024-05-16 22:02:18,856 - root - INFO - Current learning rate: 0.00014687223021475341
706
+ 2024-05-16 22:02:37,163 - root - INFO - Epoch 4:
707
+ Training Loss: 0.9178, Training Accuracy: 0.6221, Validation Loss: 1.5178, Validation Accuracy: 0.3644
708
+
709
+ 2024-05-16 22:02:37,165 - root - INFO - Current learning rate: 0.00014687223021475341
710
+ 2024-05-16 22:06:42,042 - root - INFO - Initializing SpectrogramDataset...
711
+ 2024-05-16 22:06:42,551 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
712
+ 2024-05-16 22:06:42,556 - root - INFO - SpectrogramDataset initialized successfully
713
+ 2024-05-16 22:06:42,755 - root - ERROR - An error occurred: name 'nn' is not defined
714
+ 2024-05-16 22:07:15,641 - root - INFO - Initializing SpectrogramDataset...
715
+ 2024-05-16 22:07:16,161 - root - INFO - Dataset object loaded from F:\DATASET\v1\Spectrograms\spectrogram_dataset.pkl
716
+ 2024-05-16 22:07:16,166 - root - INFO - SpectrogramDataset initialized successfully
717
+ 2024-05-16 22:07:16,465 - root - INFO - Loaded the best model from previous training.
718
+ 2024-05-16 22:07:34,862 - root - INFO - Epoch 1:
719
+ Training Loss: 0.5570, Training Accuracy: 0.7951, Validation Loss: 1.7239, Validation Accuracy: 0.5539
720
+
721
+ 2024-05-16 22:07:34,863 - root - INFO - Current learning rate: 0.00014687223021475341
722
+ 2024-05-16 22:07:51,864 - root - INFO - Epoch 2:
723
+ Training Loss: 0.5908, Training Accuracy: 0.7851, Validation Loss: 0.7348, Validation Accuracy: 0.7318
724
+
725
+ 2024-05-16 22:07:51,865 - root - INFO - Current learning rate: 0.00014687223021475341
726
+ 2024-05-16 22:08:09,242 - root - INFO - Epoch 3:
727
+ Training Loss: 0.5201, Training Accuracy: 0.8201, Validation Loss: 0.7574, Validation Accuracy: 0.7114
728
+
729
+ 2024-05-16 22:08:09,244 - root - INFO - Current learning rate: 0.00014687223021475341
730
+ 2024-05-16 22:08:25,962 - root - INFO - Epoch 4:
731
+ Training Loss: 0.4979, Training Accuracy: 0.8176, Validation Loss: 0.7149, Validation Accuracy: 0.7143
732
+
733
+ 2024-05-16 22:08:25,963 - root - INFO - Current learning rate: 0.00014687223021475341
734
+ 2024-05-16 22:08:43,336 - root - INFO - Epoch 5:
735
+ Training Loss: 0.4966, Training Accuracy: 0.8189, Validation Loss: 0.6777, Validation Accuracy: 0.7522
736
+
737
+ 2024-05-16 22:08:43,337 - root - INFO - Current learning rate: 0.00014687223021475341
738
+ 2024-05-16 22:09:00,375 - root - INFO - Epoch 6:
739
+ Training Loss: 0.4906, Training Accuracy: 0.8276, Validation Loss: 0.6189, Validation Accuracy: 0.7551
740
+
741
+ 2024-05-16 22:09:00,376 - root - INFO - Current learning rate: 0.00014687223021475341
742
+ 2024-05-16 22:09:17,365 - root - INFO - Epoch 7:
743
+ Training Loss: 0.4680, Training Accuracy: 0.8289, Validation Loss: 0.5583, Validation Accuracy: 0.7784
744
+
745
+ 2024-05-16 22:09:17,367 - root - INFO - Current learning rate: 0.00014687223021475341
746
+ 2024-05-16 22:09:34,205 - root - INFO - Epoch 8:
747
+ Training Loss: 0.4521, Training Accuracy: 0.8326, Validation Loss: 0.6058, Validation Accuracy: 0.7755
748
+
749
+ 2024-05-16 22:09:34,207 - root - INFO - Current learning rate: 0.00014687223021475341
750
+ 2024-05-16 22:09:51,165 - root - INFO - Epoch 9:
751
+ Training Loss: 0.4068, Training Accuracy: 0.8501, Validation Loss: 0.4922, Validation Accuracy: 0.8163
752
+
753
+ 2024-05-16 22:09:51,167 - root - INFO - Current learning rate: 0.00014687223021475341
754
+ 2024-05-16 22:10:08,186 - root - INFO - Epoch 10:
755
+ Training Loss: 0.4259, Training Accuracy: 0.8463, Validation Loss: 0.5306, Validation Accuracy: 0.8076
756
+
757
+ 2024-05-16 22:10:08,187 - root - INFO - Current learning rate: 0.00014687223021475341
758
+ 2024-05-16 22:10:08,260 - root - INFO - Model saved to checkpoint_epoch_10.pth
759
+ 2024-05-16 22:10:25,419 - root - INFO - Epoch 11:
760
+ Training Loss: 0.4122, Training Accuracy: 0.8451, Validation Loss: 0.5452, Validation Accuracy: 0.8105
761
+
762
+ 2024-05-16 22:10:25,421 - root - INFO - Current learning rate: 0.00014687223021475341
763
+ 2024-05-16 22:10:42,549 - root - INFO - Epoch 12:
764
+ Training Loss: 0.4157, Training Accuracy: 0.8432, Validation Loss: 0.6177, Validation Accuracy: 0.7930
765
+
766
+ 2024-05-16 22:10:42,550 - root - INFO - Current learning rate: 0.00014687223021475341
767
+ 2024-05-16 22:10:59,620 - root - INFO - Epoch 13:
768
+ Training Loss: 0.3727, Training Accuracy: 0.8595, Validation Loss: 0.7197, Validation Accuracy: 0.7405
769
+
770
+ 2024-05-16 22:10:59,621 - root - INFO - Current learning rate: 1.4687223021475341e-05
771
+ 2024-05-16 22:11:17,022 - root - INFO - Epoch 14:
772
+ Training Loss: 0.4019, Training Accuracy: 0.8638, Validation Loss: 0.5073, Validation Accuracy: 0.8076
773
+
774
+ 2024-05-16 22:11:17,023 - root - INFO - Current learning rate: 1.4687223021475341e-05
775
+ 2024-05-16 22:11:34,626 - root - INFO - Epoch 15:
776
+ Training Loss: 0.3273, Training Accuracy: 0.8832, Validation Loss: 0.4066, Validation Accuracy: 0.8601
777
+
778
+ 2024-05-16 22:11:34,628 - root - INFO - Current learning rate: 1.4687223021475341e-05
779
+ 2024-05-16 22:11:51,725 - root - INFO - Epoch 16:
780
+ Training Loss: 0.3409, Training Accuracy: 0.8713, Validation Loss: 0.4711, Validation Accuracy: 0.8280
781
+
782
+ 2024-05-16 22:11:51,726 - root - INFO - Current learning rate: 1.4687223021475341e-05
783
+ 2024-05-16 22:12:09,010 - root - INFO - Epoch 17:
784
+ Training Loss: 0.3207, Training Accuracy: 0.8826, Validation Loss: 0.4586, Validation Accuracy: 0.8338
785
+
786
+ 2024-05-16 22:12:09,011 - root - INFO - Current learning rate: 1.4687223021475341e-05
787
+ 2024-05-16 22:12:25,474 - root - INFO - Epoch 18:
788
+ Training Loss: 0.3405, Training Accuracy: 0.8738, Validation Loss: 0.4560, Validation Accuracy: 0.8222
789
+
790
+ 2024-05-16 22:12:25,476 - root - INFO - Current learning rate: 1.4687223021475341e-05
791
+ 2024-05-16 22:12:42,848 - root - INFO - Epoch 19:
792
+ Training Loss: 0.3721, Training Accuracy: 0.8657, Validation Loss: 0.4278, Validation Accuracy: 0.8426
793
+
794
+ 2024-05-16 22:12:42,849 - root - INFO - Current learning rate: 1.4687223021475343e-06
795
+ 2024-05-16 22:13:00,038 - root - INFO - Epoch 20:
796
+ Training Loss: 0.3588, Training Accuracy: 0.8701, Validation Loss: 0.4247, Validation Accuracy: 0.8397
797
+
798
+ 2024-05-16 22:13:00,039 - root - INFO - Current learning rate: 1.4687223021475343e-06
799
+ 2024-05-16 22:13:00,114 - root - INFO - Model saved to checkpoint_epoch_20.pth
800
+ 2024-05-16 22:13:17,127 - root - INFO - Epoch 21:
801
+ Training Loss: 0.3153, Training Accuracy: 0.8745, Validation Loss: 0.4080, Validation Accuracy: 0.8571
802
+
803
+ 2024-05-16 22:13:17,129 - root - INFO - Current learning rate: 1.4687223021475343e-06
804
+ 2024-05-16 22:13:33,743 - root - INFO - Epoch 22:
805
+ Training Loss: 0.3187, Training Accuracy: 0.8876, Validation Loss: 0.4765, Validation Accuracy: 0.8251
806
+
807
+ 2024-05-16 22:13:33,744 - root - INFO - Current learning rate: 1.4687223021475343e-06
808
+ 2024-05-16 22:13:50,886 - root - INFO - Epoch 23:
809
+ Training Loss: 0.3215, Training Accuracy: 0.8795, Validation Loss: 0.4566, Validation Accuracy: 0.8251
810
+
811
+ 2024-05-16 22:13:50,888 - root - INFO - Current learning rate: 1.4687223021475343e-07
812
+ 2024-05-16 22:14:08,209 - root - INFO - Epoch 24:
813
+ Training Loss: 0.3030, Training Accuracy: 0.8938, Validation Loss: 0.4290, Validation Accuracy: 0.8222
814
+
815
+ 2024-05-16 22:14:08,211 - root - INFO - Current learning rate: 1.4687223021475343e-07
816
+ 2024-05-16 22:14:25,025 - root - INFO - Epoch 25:
817
+ Training Loss: 0.3203, Training Accuracy: 0.8869, Validation Loss: 0.4327, Validation Accuracy: 0.8484
818
+
819
+ 2024-05-16 22:14:25,027 - root - INFO - Current learning rate: 1.4687223021475343e-07
820
+ 2024-05-16 22:14:42,254 - root - INFO - Epoch 26:
821
+ Training Loss: 0.3120, Training Accuracy: 0.8938, Validation Loss: 0.4477, Validation Accuracy: 0.8280
822
+
823
+ 2024-05-16 22:14:42,255 - root - INFO - Current learning rate: 1.4687223021475343e-07
824
+ 2024-05-16 22:14:59,624 - root - INFO - Epoch 27:
825
+ Training Loss: 0.3136, Training Accuracy: 0.8913, Validation Loss: 0.4614, Validation Accuracy: 0.8309
826
+
827
+ 2024-05-16 22:14:59,626 - root - INFO - Current learning rate: 1.4687223021475344e-08
828
+ 2024-05-16 22:15:16,671 - root - INFO - Epoch 28:
829
+ Training Loss: 0.3044, Training Accuracy: 0.8938, Validation Loss: 0.4706, Validation Accuracy: 0.8251
830
+
831
+ 2024-05-16 22:15:16,673 - root - INFO - Current learning rate: 1.4687223021475344e-08
832
+ 2024-05-16 22:15:33,835 - root - INFO - Epoch 29:
833
+ Training Loss: 0.3022, Training Accuracy: 0.8938, Validation Loss: 0.4032, Validation Accuracy: 0.8455
834
+
835
+ 2024-05-16 22:15:33,836 - root - INFO - Current learning rate: 1.4687223021475344e-08
836
+ 2024-05-16 22:15:51,218 - root - INFO - Epoch 30:
837
+ Training Loss: 0.2987, Training Accuracy: 0.8982, Validation Loss: 0.4105, Validation Accuracy: 0.8426
838
+
839
+ 2024-05-16 22:15:51,219 - root - INFO - Current learning rate: 1.4687223021475344e-08
840
+ 2024-05-16 22:15:51,293 - root - INFO - Model saved to checkpoint_epoch_30.pth
841
+ 2024-05-16 22:16:07,971 - root - INFO - Epoch 31:
842
+ Training Loss: 0.3077, Training Accuracy: 0.8869, Validation Loss: 0.4213, Validation Accuracy: 0.8251
843
+
844
+ 2024-05-16 22:16:07,973 - root - INFO - Current learning rate: 1.4687223021475344e-08
845
+ 2024-05-16 22:16:24,561 - root - INFO - Epoch 32:
846
+ Training Loss: 0.3193, Training Accuracy: 0.8838, Validation Loss: 0.4009, Validation Accuracy: 0.8455
847
+
848
+ 2024-05-16 22:16:24,563 - root - INFO - Current learning rate: 1.4687223021475344e-08
849
+ 2024-05-16 22:16:42,053 - root - INFO - Epoch 33:
850
+ Training Loss: 0.3314, Training Accuracy: 0.8869, Validation Loss: 0.4344, Validation Accuracy: 0.8397
851
+
852
+ 2024-05-16 22:16:42,055 - root - INFO - Current learning rate: 1.4687223021475344e-08
853
+ 2024-05-16 22:16:59,057 - root - INFO - Epoch 34:
854
+ Training Loss: 0.2837, Training Accuracy: 0.9001, Validation Loss: 0.4218, Validation Accuracy: 0.8280
855
+
856
+ 2024-05-16 22:16:59,059 - root - INFO - Current learning rate: 1.4687223021475344e-08
857
+ 2024-05-16 22:17:16,041 - root - INFO - Epoch 35:
858
+ Training Loss: 0.3607, Training Accuracy: 0.8701, Validation Loss: 0.4585, Validation Accuracy: 0.8134
859
+
860
+ 2024-05-16 22:17:16,042 - root - INFO - Current learning rate: 1.4687223021475344e-08
861
+ 2024-05-16 22:17:33,182 - root - INFO - Epoch 36:
862
+ Training Loss: 0.2987, Training Accuracy: 0.8919, Validation Loss: 0.4383, Validation Accuracy: 0.8251
863
+
864
+ 2024-05-16 22:17:33,184 - root - INFO - Current learning rate: 1.4687223021475344e-09
865
+ 2024-05-16 22:17:50,259 - root - INFO - Epoch 37:
866
+ Training Loss: 0.3294, Training Accuracy: 0.8682, Validation Loss: 0.4253, Validation Accuracy: 0.8309
867
+
868
+ 2024-05-16 22:17:50,260 - root - INFO - Current learning rate: 1.4687223021475344e-09
869
+ 2024-05-16 22:18:06,981 - root - INFO - Epoch 38:
870
+ Training Loss: 0.2821, Training Accuracy: 0.9019, Validation Loss: 0.4611, Validation Accuracy: 0.8251
871
+
872
+ 2024-05-16 22:18:06,982 - root - INFO - Current learning rate: 1.4687223021475344e-09
873
+ 2024-05-16 22:18:23,998 - root - INFO - Epoch 39:
874
+ Training Loss: 0.3158, Training Accuracy: 0.8869, Validation Loss: 0.4367, Validation Accuracy: 0.8280
875
+
876
+ 2024-05-16 22:18:24,000 - root - INFO - Current learning rate: 1.4687223021475344e-09
877
+ 2024-05-16 22:18:41,011 - root - INFO - Epoch 40:
878
+ Training Loss: 0.3254, Training Accuracy: 0.8888, Validation Loss: 0.3913, Validation Accuracy: 0.8513
879
+
880
+ 2024-05-16 22:18:41,012 - root - INFO - Current learning rate: 1.4687223021475344e-09
881
+ 2024-05-16 22:18:41,155 - root - INFO - Model saved to checkpoint_epoch_40.pth
882
+ 2024-05-16 22:18:58,103 - root - INFO - Epoch 41:
883
+ Training Loss: 0.3082, Training Accuracy: 0.8857, Validation Loss: 0.3953, Validation Accuracy: 0.8542
884
+
885
+ 2024-05-16 22:18:58,105 - root - INFO - Current learning rate: 1.4687223021475344e-09
886
+ 2024-05-16 22:19:14,938 - root - INFO - Epoch 42:
887
+ Training Loss: 0.2816, Training Accuracy: 0.9007, Validation Loss: 0.4112, Validation Accuracy: 0.8484
888
+
889
+ 2024-05-16 22:19:14,939 - root - INFO - Current learning rate: 1.4687223021475344e-09
890
+ 2024-05-16 22:19:32,077 - root - INFO - Epoch 43:
891
+ Training Loss: 0.3457, Training Accuracy: 0.8788, Validation Loss: 0.4241, Validation Accuracy: 0.8455
892
+
893
+ 2024-05-16 22:19:32,078 - root - INFO - Current learning rate: 1.4687223021475344e-09
894
+ 2024-05-16 22:19:49,354 - root - INFO - Epoch 44:
895
+ Training Loss: 0.3149, Training Accuracy: 0.8826, Validation Loss: 0.4160, Validation Accuracy: 0.8542
896
+
897
+ 2024-05-16 22:19:49,356 - root - INFO - Current learning rate: 1.4687223021475344e-09
898
+ 2024-05-16 22:20:06,691 - root - INFO - Epoch 45:
899
+ Training Loss: 0.3011, Training Accuracy: 0.8894, Validation Loss: 0.4293, Validation Accuracy: 0.8484
900
+
901
+ 2024-05-16 22:20:06,692 - root - INFO - Current learning rate: 1.4687223021475344e-09
902
+ 2024-05-16 22:20:23,367 - root - INFO - Epoch 46:
903
+ Training Loss: 0.3327, Training Accuracy: 0.8795, Validation Loss: 0.3971, Validation Accuracy: 0.8630
904
+
905
+ 2024-05-16 22:20:23,369 - root - INFO - Current learning rate: 1.4687223021475344e-09
906
+ 2024-05-16 22:20:40,496 - root - INFO - Epoch 47:
907
+ Training Loss: 0.3180, Training Accuracy: 0.8894, Validation Loss: 0.4143, Validation Accuracy: 0.8513
908
+
909
+ 2024-05-16 22:20:40,497 - root - INFO - Current learning rate: 1.4687223021475344e-09
910
+ 2024-05-16 22:20:58,098 - root - INFO - Epoch 48:
911
+ Training Loss: 0.2915, Training Accuracy: 0.8969, Validation Loss: 0.4355, Validation Accuracy: 0.8455
912
+
913
+ 2024-05-16 22:20:58,100 - root - INFO - Current learning rate: 1.4687223021475344e-09
914
+ 2024-05-16 22:21:15,492 - root - INFO - Epoch 49:
915
+ Training Loss: 0.3160, Training Accuracy: 0.8882, Validation Loss: 0.4601, Validation Accuracy: 0.8163
916
+
917
+ 2024-05-16 22:21:15,494 - root - INFO - Current learning rate: 1.4687223021475344e-09
918
+ 2024-05-16 22:21:32,535 - root - INFO - Epoch 50:
919
+ Training Loss: 0.3085, Training Accuracy: 0.8832, Validation Loss: 0.4587, Validation Accuracy: 0.8105
920
+
921
+ 2024-05-16 22:21:32,537 - root - INFO - Current learning rate: 1.4687223021475344e-09
922
+ 2024-05-16 22:21:32,613 - root - INFO - Model saved to checkpoint_epoch_50.pth
923
+ 2024-05-16 22:21:33,771 - root - INFO - precision recall f1-score support
924
+
925
+ 808 0.88 0.88 0.88 43
926
+ Clap 0.62 0.78 0.69 27
927
+ Closed Hat 0.89 0.86 0.87 63
928
+ Kick 0.94 0.93 0.94 120
929
+ Open Hat 0.76 0.87 0.81 15
930
+ Snare 0.84 0.78 0.81 76
931
+
932
+ accuracy 0.86 344
933
+ macro avg 0.82 0.85 0.83 344
934
+ weighted avg 0.87 0.86 0.86 344
935
+