franzzepol
commited on
Commit
•
2656f85
1
Parent(s):
e9f7f5c
Training in progress, epoch 1
Browse files- README.md +65 -0
- all_results.json +13 -0
- config.json +65 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Jul02_14-56-56_Precision5860/events.out.tfevents.1719950217.Precision5860.25088.0 +3 -0
- runs/Jul02_14-56-56_Precision5860/events.out.tfevents.1720008603.Precision5860.25088.1 +3 -0
- runs/Jul12_12-22-38_Precision5860/events.out.tfevents.1720804964.Precision5860.19552.0 +3 -0
- runs/Jun20_11-10-33_Precision5860/events.out.tfevents.1718899898.Precision5860.21684.0 +3 -0
- runs/Jun20_12-07-11_Precision5860/events.out.tfevents.1718903243.Precision5860.6684.0 +3 -0
- runs/Jun21_16-37-45_Precision5860/events.out.tfevents.1719005866.Precision5860.26544.0 +3 -0
- runs/Jun21_16-37-45_Precision5860/events.out.tfevents.1719068746.Precision5860.26544.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +81 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/swin-base-patch4-window7-224-in22k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: swin-base-patch4-window7-224-in22k-finetuned-CT-V2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# swin-base-patch4-window7-224-in22k-finetuned-CT-V2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0038
|
21 |
+
- Accuracy: 0.9989
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
47 |
+
- num_epochs: 5
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| No log | 1.0 | 1147 | 0.0393 | 0.9877 |
|
54 |
+
| No log | 2.0 | 2294 | 0.0201 | 0.9921 |
|
55 |
+
| No log | 3.0 | 3441 | 0.0089 | 0.9964 |
|
56 |
+
| No log | 4.0 | 4588 | 0.0071 | 0.9971 |
|
57 |
+
| 0.1453 | 5.0 | 5735 | 0.0038 | 0.9989 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.37.2
|
63 |
+
- Pytorch 2.3.1+cpu
|
64 |
+
- Datasets 2.20.0
|
65 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9989094874591058,
|
4 |
+
"eval_loss": 0.00382046215236187,
|
5 |
+
"eval_runtime": 721.3858,
|
6 |
+
"eval_samples_per_second": 12.712,
|
7 |
+
"eval_steps_per_second": 0.398,
|
8 |
+
"total_flos": 1.4373615310681375e+19,
|
9 |
+
"train_loss": 0.1452722072185593,
|
10 |
+
"train_runtime": 57646.0553,
|
11 |
+
"train_samples_per_second": 3.183,
|
12 |
+
"train_steps_per_second": 0.099
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swin-base-patch4-window7-224-in22k",
|
3 |
+
"architectures": [
|
4 |
+
"SwinForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
18,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 128,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 1024,
|
19 |
+
"id2label": {
|
20 |
+
"0": "meningioma_tumor",
|
21 |
+
"1": "glioma_tumor",
|
22 |
+
"2": "no_tumor",
|
23 |
+
"3": "pituitary_tumor"
|
24 |
+
},
|
25 |
+
"image_size": 224,
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"label2id": {
|
28 |
+
"glioma_tumor": 1,
|
29 |
+
"meningioma_tumor": 0,
|
30 |
+
"no_tumor": 2,
|
31 |
+
"pituitary_tumor": 3
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-05,
|
34 |
+
"mlp_ratio": 4.0,
|
35 |
+
"model_type": "swin",
|
36 |
+
"num_channels": 3,
|
37 |
+
"num_heads": [
|
38 |
+
4,
|
39 |
+
8,
|
40 |
+
16,
|
41 |
+
32
|
42 |
+
],
|
43 |
+
"num_layers": 4,
|
44 |
+
"out_features": [
|
45 |
+
"stage4"
|
46 |
+
],
|
47 |
+
"out_indices": [
|
48 |
+
4
|
49 |
+
],
|
50 |
+
"patch_size": 4,
|
51 |
+
"path_norm": true,
|
52 |
+
"problem_type": "single_label_classification",
|
53 |
+
"qkv_bias": true,
|
54 |
+
"stage_names": [
|
55 |
+
"stem",
|
56 |
+
"stage1",
|
57 |
+
"stage2",
|
58 |
+
"stage3",
|
59 |
+
"stage4"
|
60 |
+
],
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.41.2",
|
63 |
+
"use_absolute_embeddings": false,
|
64 |
+
"window_size": 7
|
65 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9989094874591058,
|
4 |
+
"eval_loss": 0.00382046215236187,
|
5 |
+
"eval_runtime": 721.3858,
|
6 |
+
"eval_samples_per_second": 12.712,
|
7 |
+
"eval_steps_per_second": 0.398
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ec3d30c0b299fb557718243fcff2a32a7b5f175da664b746a6cfa81138ccce0
|
3 |
+
size 347507016
|
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 |
+
0.485,
|
21 |
+
0.456,
|
22 |
+
0.406
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTImageProcessor",
|
25 |
+
"image_std": [
|
26 |
+
0.229,
|
27 |
+
0.224,
|
28 |
+
0.225
|
29 |
+
],
|
30 |
+
"resample": 3,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
runs/Jul02_14-56-56_Precision5860/events.out.tfevents.1719950217.Precision5860.25088.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8db009c9ffa974f588242654c6a85467bea1ffdf9549e0011fd6b0f85a1ded42
|
3 |
+
size 7093
|
runs/Jul02_14-56-56_Precision5860/events.out.tfevents.1720008603.Precision5860.25088.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:342b64de9abdd0c663c7bd0362383feabe81b179c3852d9fc02e02945170ef46
|
3 |
+
size 411
|
runs/Jul12_12-22-38_Precision5860/events.out.tfevents.1720804964.Precision5860.19552.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1544b658007ac03d8bb84c89536ceaf98788ec14bf245eba6d49d481c3acf41a
|
3 |
+
size 5747
|
runs/Jun20_11-10-33_Precision5860/events.out.tfevents.1718899898.Precision5860.21684.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d664b8db2a0ca23aba251acfb02ee878e61e7a024e3adc74257709ef8a8346f
|
3 |
+
size 5424
|
runs/Jun20_12-07-11_Precision5860/events.out.tfevents.1718903243.Precision5860.6684.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93cbe2a567d6e259f3f04c4cf8fbe36317e1c3e9fb0e0ea68c02d4191cf5bb79
|
3 |
+
size 7604
|
runs/Jun21_16-37-45_Precision5860/events.out.tfevents.1719005866.Precision5860.26544.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:400d915a8f2526f579d5787d79e0e9ba5a4a9194305cb50da44ef6f5da1473a6
|
3 |
+
size 7093
|
runs/Jun21_16-37-45_Precision5860/events.out.tfevents.1719068746.Precision5860.26544.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d837b8e9f13d62ddb5a4d1353befcaf9fc65e396e161318825ab3ba8c094ee7
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 1.4373615310681375e+19,
|
4 |
+
"train_loss": 0.1452722072185593,
|
5 |
+
"train_runtime": 57646.0553,
|
6 |
+
"train_samples_per_second": 3.183,
|
7 |
+
"train_steps_per_second": 0.099
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9989094874591058,
|
3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-CT-V2\\checkpoint-5735",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 5735,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.9876772082878953,
|
14 |
+
"eval_loss": 0.03928782418370247,
|
15 |
+
"eval_runtime": 746.795,
|
16 |
+
"eval_samples_per_second": 12.279,
|
17 |
+
"eval_steps_per_second": 0.384,
|
18 |
+
"step": 1147
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.9921483097055616,
|
23 |
+
"eval_loss": 0.02005026862025261,
|
24 |
+
"eval_runtime": 756.0286,
|
25 |
+
"eval_samples_per_second": 12.129,
|
26 |
+
"eval_steps_per_second": 0.38,
|
27 |
+
"step": 2294
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.996401308615049,
|
32 |
+
"eval_loss": 0.008917241357266903,
|
33 |
+
"eval_runtime": 747.9437,
|
34 |
+
"eval_samples_per_second": 12.26,
|
35 |
+
"eval_steps_per_second": 0.384,
|
36 |
+
"step": 3441
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.9970556161395856,
|
41 |
+
"eval_loss": 0.007110947743058205,
|
42 |
+
"eval_runtime": 757.7501,
|
43 |
+
"eval_samples_per_second": 12.102,
|
44 |
+
"eval_steps_per_second": 0.379,
|
45 |
+
"step": 4588
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"learning_rate": 0.0,
|
50 |
+
"loss": 0.1453,
|
51 |
+
"step": 5735
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 5.0,
|
55 |
+
"eval_accuracy": 0.9989094874591058,
|
56 |
+
"eval_loss": 0.00382046215236187,
|
57 |
+
"eval_runtime": 750.1592,
|
58 |
+
"eval_samples_per_second": 12.224,
|
59 |
+
"eval_steps_per_second": 0.383,
|
60 |
+
"step": 5735
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 5.0,
|
64 |
+
"step": 5735,
|
65 |
+
"total_flos": 1.4373615310681375e+19,
|
66 |
+
"train_loss": 0.1452722072185593,
|
67 |
+
"train_runtime": 57646.0553,
|
68 |
+
"train_samples_per_second": 3.183,
|
69 |
+
"train_steps_per_second": 0.099
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": -5735,
|
73 |
+
"max_steps": 5735,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 5,
|
76 |
+
"save_steps": 500,
|
77 |
+
"total_flos": 1.4373615310681375e+19,
|
78 |
+
"train_batch_size": 32,
|
79 |
+
"trial_name": null,
|
80 |
+
"trial_params": null
|
81 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12e07f906c854c55d99bce068ff133ff72c5deef7ba2cf6b9a80e876b65a1a64
|
3 |
+
size 5176
|