Model save
Browse files- README.md +67 -0
- config.json +44 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/May01_18-31-07_13983870a714/events.out.tfevents.1714588278.13983870a714.1243.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21K
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: Main_Fashion
|
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 |
+
# Main_Fashion
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21K](https://huggingface.co/google/vit-base-patch16-224-in21K) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.7633
|
21 |
+
- Accuracy: 0.6961
|
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: 0.0002
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 7
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
53 |
+
| 0.934 | 0.9259 | 100 | 0.9492 | 0.7030 |
|
54 |
+
| 0.9191 | 1.8519 | 200 | 0.7838 | 0.7401 |
|
55 |
+
| 0.7774 | 2.7778 | 300 | 0.8152 | 0.7123 |
|
56 |
+
| 0.5743 | 3.7037 | 400 | 0.7249 | 0.7100 |
|
57 |
+
| 0.5145 | 4.6296 | 500 | 0.7721 | 0.7077 |
|
58 |
+
| 0.4713 | 5.5556 | 600 | 0.7182 | 0.7146 |
|
59 |
+
| 0.4397 | 6.4815 | 700 | 0.7633 | 0.6961 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.40.1
|
65 |
+
- Pytorch 2.2.1+cu121
|
66 |
+
- Datasets 2.19.0
|
67 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "dress",
|
13 |
+
"1": "sweater",
|
14 |
+
"2": "short",
|
15 |
+
"3": "shirt",
|
16 |
+
"4": "pants",
|
17 |
+
"5": "skirt",
|
18 |
+
"6": "jacket",
|
19 |
+
"7": "Tshirt"
|
20 |
+
},
|
21 |
+
"image_size": 224,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"Tshirt": 7,
|
26 |
+
"dress": 0,
|
27 |
+
"jacket": 6,
|
28 |
+
"pants": 4,
|
29 |
+
"shirt": 3,
|
30 |
+
"short": 2,
|
31 |
+
"skirt": 5,
|
32 |
+
"sweater": 1
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"model_type": "vit",
|
36 |
+
"num_attention_heads": 12,
|
37 |
+
"num_channels": 3,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"patch_size": 16,
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"qkv_bias": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.40.1"
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c103ebafe9fcd097cc4eaccce53b3f6c8d800a3dde1a810b9ddab8d501596f12
|
3 |
+
size 343242432
|
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 |
+
224,
|
34 |
+
224
|
35 |
+
]
|
36 |
+
}
|
runs/May01_18-31-07_13983870a714/events.out.tfevents.1714588278.13983870a714.1243.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d8df19a666d5c3e99c1aa1c5f9859d7c4b39992ecdc6bbc656739c3a8d8dc7d
|
3 |
+
size 23231
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c75b9c9fdfaa3ab47e34330f972b3914b1cc07eae4057d7d748e05024b604a5
|
3 |
+
size 4984
|