Training in progress, epoch 1
Browse files- README.md +67 -0
- config.json +65 -0
- dino-vits8-musinsa/config.json +36 -0
- dino-vits8-musinsa/model.safetensors +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/dino-vits8
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: dino-vits8-musinsa
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# dino-vits8-musinsa
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [facebook/dino-vits8](https://huggingface.co/facebook/dino-vits8) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1692
|
24 |
+
- Precision: 0.9579
|
25 |
+
- Recall: 0.9576
|
26 |
+
- F1: 0.9575
|
27 |
+
- Accuracy: 0.9576
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 128
|
48 |
+
- eval_batch_size: 128
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 202 | 0.1408 | 0.9513 | 0.9494 | 0.9498 | 0.9494 |
|
59 |
+
| No log | 2.0 | 404 | 0.1328 | 0.9563 | 0.9558 | 0.9560 | 0.9558 |
|
60 |
+
| 0.1129 | 3.0 | 606 | 0.1692 | 0.9579 | 0.9576 | 0.9575 | 0.9576 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.41.2
|
66 |
+
- Pytorch 2.3.1+cu121
|
67 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
|
3 |
+
"architectures": [
|
4 |
+
"SwinForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
6,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 96,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"id2label": {
|
20 |
+
"0": "LABEL_0",
|
21 |
+
"1": "LABEL_1",
|
22 |
+
"2": "LABEL_2",
|
23 |
+
"3": "LABEL_3"
|
24 |
+
},
|
25 |
+
"image_size": 224,
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_2": 2,
|
31 |
+
"LABEL_3": 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 |
+
3,
|
39 |
+
6,
|
40 |
+
12,
|
41 |
+
24
|
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 |
+
}
|
dino-vits8-musinsa/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/dino-vits8",
|
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": 384,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3"
|
16 |
+
},
|
17 |
+
"image_size": 224,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 1536,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2,
|
24 |
+
"LABEL_3": 3
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"model_type": "vit",
|
28 |
+
"num_attention_heads": 6,
|
29 |
+
"num_channels": 3,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"patch_size": 8,
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"qkv_bias": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.41.2"
|
36 |
+
}
|
dino-vits8-musinsa/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d658cf2dd8d0a42da0890a649cc2e9f0fbd9544a2d2b62bfe2278eaa3e2e1c9a
|
3 |
+
size 86710136
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d3c03d5409af706e2d8a92d40c4349a46571c85260ea91e3e2d66ed69963278
|
3 |
+
size 110348984
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c1110fd941dde43474bb6a904382a94444c30961356b2e5a1a574f297f8a6b1
|
3 |
+
size 5176
|