methane6923
commited on
Commit
•
bd85d01
1
Parent(s):
e75e270
Model save
Browse files- README.md +108 -0
- config.json +38 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Jul11_06-59-42_c678d70e5ef6/events.out.tfevents.1720681198.c678d70e5ef6.578.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- precision
|
11 |
+
- recall
|
12 |
+
- f1
|
13 |
+
model-index:
|
14 |
+
- name: weather_classification_ViT
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Image Classification
|
18 |
+
type: image-classification
|
19 |
+
dataset:
|
20 |
+
name: imagefolder
|
21 |
+
type: imagefolder
|
22 |
+
config: default
|
23 |
+
split: train
|
24 |
+
args: default
|
25 |
+
metrics:
|
26 |
+
- name: Accuracy
|
27 |
+
type: accuracy
|
28 |
+
value: 0.9679266895761741
|
29 |
+
- name: Precision
|
30 |
+
type: precision
|
31 |
+
value: 0.9679235596755258
|
32 |
+
- name: Recall
|
33 |
+
type: recall
|
34 |
+
value: 0.9679266895761741
|
35 |
+
- name: F1
|
36 |
+
type: f1
|
37 |
+
value: 0.9678827379290899
|
38 |
+
---
|
39 |
+
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
+
|
43 |
+
# weather_classification_ViT
|
44 |
+
|
45 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.1268
|
48 |
+
- Accuracy: 0.9679
|
49 |
+
- Precision: 0.9679
|
50 |
+
- Recall: 0.9679
|
51 |
+
- F1: 0.9679
|
52 |
+
- Auc: 0.9974
|
53 |
+
|
54 |
+
## Model description
|
55 |
+
|
56 |
+
More information needed
|
57 |
+
|
58 |
+
## Intended uses & limitations
|
59 |
+
|
60 |
+
More information needed
|
61 |
+
|
62 |
+
## Training and evaluation data
|
63 |
+
|
64 |
+
More information needed
|
65 |
+
|
66 |
+
## Training procedure
|
67 |
+
|
68 |
+
### Training hyperparameters
|
69 |
+
|
70 |
+
The following hyperparameters were used during training:
|
71 |
+
- learning_rate: 0.0002
|
72 |
+
- train_batch_size: 16
|
73 |
+
- eval_batch_size: 8
|
74 |
+
- seed: 42
|
75 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
76 |
+
- lr_scheduler_type: linear
|
77 |
+
- num_epochs: 4
|
78 |
+
- mixed_precision_training: Native AMP
|
79 |
+
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
|
83 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
|
84 |
+
| 0.2811 | 0.2288 | 100 | 0.3139 | 0.8958 | 0.9147 | 0.8958 | 0.8970 | 0.9903 |
|
85 |
+
| 0.1396 | 0.4577 | 200 | 0.2454 | 0.9278 | 0.9307 | 0.9278 | 0.9282 | 0.9919 |
|
86 |
+
| 0.3761 | 0.6865 | 300 | 0.2952 | 0.9072 | 0.9117 | 0.9072 | 0.9071 | 0.9889 |
|
87 |
+
| 0.2365 | 0.9153 | 400 | 0.1797 | 0.9444 | 0.9447 | 0.9444 | 0.9445 | 0.9940 |
|
88 |
+
| 0.2528 | 1.1442 | 500 | 0.2470 | 0.9278 | 0.9307 | 0.9278 | 0.9278 | 0.9924 |
|
89 |
+
| 0.2364 | 1.3730 | 600 | 0.2448 | 0.9261 | 0.9306 | 0.9261 | 0.9264 | 0.9934 |
|
90 |
+
| 0.34 | 1.6018 | 700 | 0.1986 | 0.9404 | 0.9409 | 0.9404 | 0.9405 | 0.9929 |
|
91 |
+
| 0.2001 | 1.8307 | 800 | 0.1525 | 0.9542 | 0.9548 | 0.9542 | 0.9539 | 0.9960 |
|
92 |
+
| 0.0958 | 2.0595 | 900 | 0.1783 | 0.9507 | 0.9515 | 0.9507 | 0.9505 | 0.9952 |
|
93 |
+
| 0.1862 | 2.2883 | 1000 | 0.1654 | 0.9553 | 0.9558 | 0.9553 | 0.9551 | 0.9952 |
|
94 |
+
| 0.1021 | 2.5172 | 1100 | 0.1654 | 0.9462 | 0.9472 | 0.9462 | 0.9459 | 0.9958 |
|
95 |
+
| 0.1178 | 2.7460 | 1200 | 0.1591 | 0.9525 | 0.9536 | 0.9525 | 0.9523 | 0.9960 |
|
96 |
+
| 0.0474 | 2.9748 | 1300 | 0.1299 | 0.9633 | 0.9635 | 0.9633 | 0.9633 | 0.9975 |
|
97 |
+
| 0.046 | 3.2037 | 1400 | 0.1384 | 0.9628 | 0.9628 | 0.9628 | 0.9627 | 0.9972 |
|
98 |
+
| 0.0294 | 3.4325 | 1500 | 0.1388 | 0.9645 | 0.9644 | 0.9645 | 0.9644 | 0.9969 |
|
99 |
+
| 0.1833 | 3.6613 | 1600 | 0.1346 | 0.9633 | 0.9634 | 0.9633 | 0.9633 | 0.9971 |
|
100 |
+
| 0.0548 | 3.8902 | 1700 | 0.1268 | 0.9679 | 0.9679 | 0.9679 | 0.9679 | 0.9974 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.41.2
|
106 |
+
- Pytorch 2.3.0+cu121
|
107 |
+
- Datasets 2.20.0
|
108 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Clear",
|
13 |
+
"1": "Fog",
|
14 |
+
"2": "Rain",
|
15 |
+
"3": "Sand storm",
|
16 |
+
"4": "Snow"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"Clear": "0",
|
23 |
+
"Fog": "1",
|
24 |
+
"Rain": "2",
|
25 |
+
"Sand storm": "3",
|
26 |
+
"Snow": "4"
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"model_type": "vit",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_channels": 3,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"patch_size": 16,
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"qkv_bias": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.41.2"
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62940802636080b2ebe1a854a83d94e4b8afb2d6aeb296d2f054e2fa657d53a6
|
3 |
+
size 343233204
|
preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTFeatureExtractor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
runs/Jul11_06-59-42_c678d70e5ef6/events.out.tfevents.1720681198.c678d70e5ef6.578.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a6d40be2ea71ee51193d2ba25f8be1efa120c615e3753d0763887e6df10b303
|
3 |
+
size 50760
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d540a90add4206a76bf8a3fe4dba66de4ed3d9969197a8840ec9a52c10686648
|
3 |
+
size 5112
|