Model save
Browse files- README.md +105 -0
- config.json +83 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Apr22_19-46-52_25f23db457d4/events.out.tfevents.1713815212.25f23db457d4.34.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/swinv2-tiny-patch4-window16-256
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: Action_agent
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.7914285714285715
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# Action_agent
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window16-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6412
|
36 |
+
- Accuracy: 0.7914
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 10
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 2.039 | 0.32 | 100 | 1.7706 | 0.4848 |
|
68 |
+
| 1.3695 | 0.64 | 200 | 1.0886 | 0.6457 |
|
69 |
+
| 1.099 | 0.96 | 300 | 0.9092 | 0.68 |
|
70 |
+
| 1.0011 | 1.27 | 400 | 0.8183 | 0.7171 |
|
71 |
+
| 0.8437 | 1.59 | 500 | 0.7674 | 0.7190 |
|
72 |
+
| 0.8613 | 1.91 | 600 | 0.7168 | 0.7410 |
|
73 |
+
| 0.7427 | 2.23 | 700 | 0.7270 | 0.7352 |
|
74 |
+
| 0.693 | 2.55 | 800 | 0.6801 | 0.7676 |
|
75 |
+
| 0.7789 | 2.87 | 900 | 0.6832 | 0.7590 |
|
76 |
+
| 0.6863 | 3.18 | 1000 | 0.6655 | 0.7752 |
|
77 |
+
| 0.6437 | 3.5 | 1100 | 0.6382 | 0.7771 |
|
78 |
+
| 0.6741 | 3.82 | 1200 | 0.6446 | 0.7790 |
|
79 |
+
| 0.5871 | 4.14 | 1300 | 0.6551 | 0.7838 |
|
80 |
+
| 0.6051 | 4.46 | 1400 | 0.6970 | 0.7638 |
|
81 |
+
| 0.5175 | 4.78 | 1500 | 0.6553 | 0.7790 |
|
82 |
+
| 0.5795 | 5.1 | 1600 | 0.6667 | 0.7771 |
|
83 |
+
| 0.4919 | 5.41 | 1700 | 0.6317 | 0.7905 |
|
84 |
+
| 0.4986 | 5.73 | 1800 | 0.6486 | 0.7810 |
|
85 |
+
| 0.5104 | 6.05 | 1900 | 0.6700 | 0.7743 |
|
86 |
+
| 0.4919 | 6.37 | 2000 | 0.6528 | 0.7819 |
|
87 |
+
| 0.5144 | 6.69 | 2100 | 0.6355 | 0.7876 |
|
88 |
+
| 0.5554 | 7.01 | 2200 | 0.6552 | 0.7771 |
|
89 |
+
| 0.5389 | 7.32 | 2300 | 0.6361 | 0.7876 |
|
90 |
+
| 0.5751 | 7.64 | 2400 | 0.6377 | 0.7905 |
|
91 |
+
| 0.4743 | 7.96 | 2500 | 0.6417 | 0.7867 |
|
92 |
+
| 0.4519 | 8.28 | 2600 | 0.6309 | 0.7895 |
|
93 |
+
| 0.5058 | 8.6 | 2700 | 0.6453 | 0.7867 |
|
94 |
+
| 0.4754 | 8.92 | 2800 | 0.6414 | 0.7905 |
|
95 |
+
| 0.4637 | 9.24 | 2900 | 0.6330 | 0.7905 |
|
96 |
+
| 0.5028 | 9.55 | 3000 | 0.6418 | 0.7857 |
|
97 |
+
| 0.4227 | 9.87 | 3100 | 0.6412 | 0.7914 |
|
98 |
+
|
99 |
+
|
100 |
+
### Framework versions
|
101 |
+
|
102 |
+
- Transformers 4.39.3
|
103 |
+
- Pytorch 2.1.2
|
104 |
+
- Datasets 2.18.0
|
105 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swinv2-tiny-patch4-window16-256",
|
3 |
+
"architectures": [
|
4 |
+
"Swinv2ForImageClassification"
|
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": "\u0995\u09a5\u09be_\u09ac\u09b2\u09be",
|
21 |
+
"1": "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be",
|
22 |
+
"2": "\u0996\u09be\u0993\u09df\u09be",
|
23 |
+
"3": "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be",
|
24 |
+
"4": "\u0998\u09c1\u09ae\u09be\u09a8\u09cb",
|
25 |
+
"5": "\u09aa\u09be\u09a8_\u0995\u09b0\u09be",
|
26 |
+
"6": "\u09aa\u09dc\u09be",
|
27 |
+
"7": "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be",
|
28 |
+
"8": "\u09b2\u09c7\u0996\u09be",
|
29 |
+
"9": "\u09b9\u09be\u0981\u099f\u09be"
|
30 |
+
},
|
31 |
+
"image_size": 256,
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"label2id": {
|
34 |
+
"\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
|
35 |
+
"\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
|
36 |
+
"\u0996\u09be\u0993\u09df\u09be": "2",
|
37 |
+
"\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be": "3",
|
38 |
+
"\u0998\u09c1\u09ae\u09be\u09a8\u09cb": "4",
|
39 |
+
"\u09aa\u09be\u09a8_\u0995\u09b0\u09be": "5",
|
40 |
+
"\u09aa\u09dc\u09be": "6",
|
41 |
+
"\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be": "7",
|
42 |
+
"\u09b2\u09c7\u0996\u09be": "8",
|
43 |
+
"\u09b9\u09be\u0981\u099f\u09be": "9"
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
+
"mlp_ratio": 4.0,
|
47 |
+
"model_type": "swinv2",
|
48 |
+
"num_channels": 3,
|
49 |
+
"num_heads": [
|
50 |
+
3,
|
51 |
+
6,
|
52 |
+
12,
|
53 |
+
24
|
54 |
+
],
|
55 |
+
"num_layers": 4,
|
56 |
+
"out_features": [
|
57 |
+
"stage4"
|
58 |
+
],
|
59 |
+
"out_indices": [
|
60 |
+
4
|
61 |
+
],
|
62 |
+
"patch_size": 4,
|
63 |
+
"path_norm": true,
|
64 |
+
"pretrained_window_sizes": [
|
65 |
+
0,
|
66 |
+
0,
|
67 |
+
0,
|
68 |
+
0
|
69 |
+
],
|
70 |
+
"problem_type": "single_label_classification",
|
71 |
+
"qkv_bias": true,
|
72 |
+
"stage_names": [
|
73 |
+
"stem",
|
74 |
+
"stage1",
|
75 |
+
"stage2",
|
76 |
+
"stage3",
|
77 |
+
"stage4"
|
78 |
+
],
|
79 |
+
"torch_dtype": "float32",
|
80 |
+
"transformers_version": "4.39.3",
|
81 |
+
"use_absolute_embeddings": false,
|
82 |
+
"window_size": 16
|
83 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b5cf3b87b343cd43304129258627ec15995b5efe57f624c30058abd1a85104a
|
3 |
+
size 110374752
|
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": 256,
|
34 |
+
"width": 256
|
35 |
+
}
|
36 |
+
}
|
runs/Apr22_19-46-52_25f23db457d4/events.out.tfevents.1713815212.25f23db457d4.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb21aaacbc41e7069754d7bc02664dfdaaa197fd0871de78d0fd5beef4136819
|
3 |
+
size 60483
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e145019e5e9eb49ac1a9542b4cc2430a5e37f69fa201e50c7d9e96b4bb660be
|
3 |
+
size 4920
|