End of training
Browse files- README.md +95 -0
- config.json +88 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: Boya1_SGD_1-e3_20Epoch_09Momentum_Beit-base-patch16_fold5
|
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: test
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.4277190127474912
|
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 |
+
# Boya1_SGD_1-e3_20Epoch_09Momentum_Beit-base-patch16_fold5
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.7637
|
36 |
+
- Accuracy: 0.4277
|
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: 0.001
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 16
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
62 |
+
- num_epochs: 20
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
+
| 2.3338 | 1.0 | 924 | 2.4489 | 0.2086 |
|
69 |
+
| 2.3427 | 2.0 | 1848 | 2.3125 | 0.2517 |
|
70 |
+
| 2.1284 | 3.0 | 2772 | 2.2064 | 0.2853 |
|
71 |
+
| 2.0324 | 4.0 | 3696 | 2.1236 | 0.3106 |
|
72 |
+
| 1.929 | 5.0 | 4620 | 2.0514 | 0.3369 |
|
73 |
+
| 1.9691 | 6.0 | 5544 | 1.9984 | 0.3537 |
|
74 |
+
| 2.0646 | 7.0 | 6468 | 1.9525 | 0.3653 |
|
75 |
+
| 1.8686 | 8.0 | 7392 | 1.9172 | 0.3813 |
|
76 |
+
| 1.972 | 9.0 | 8316 | 1.8843 | 0.3916 |
|
77 |
+
| 2.0678 | 10.0 | 9240 | 1.8632 | 0.3973 |
|
78 |
+
| 1.8342 | 11.0 | 10164 | 1.8414 | 0.3976 |
|
79 |
+
| 1.9641 | 12.0 | 11088 | 1.8250 | 0.4057 |
|
80 |
+
| 1.6663 | 13.0 | 12012 | 1.8107 | 0.4093 |
|
81 |
+
| 1.7839 | 14.0 | 12936 | 1.7966 | 0.4193 |
|
82 |
+
| 1.7724 | 15.0 | 13860 | 1.7857 | 0.4258 |
|
83 |
+
| 1.7746 | 16.0 | 14784 | 1.7787 | 0.4245 |
|
84 |
+
| 1.9266 | 17.0 | 15708 | 1.7714 | 0.4261 |
|
85 |
+
| 1.8612 | 18.0 | 16632 | 1.7673 | 0.4280 |
|
86 |
+
| 1.7224 | 19.0 | 17556 | 1.7664 | 0.4291 |
|
87 |
+
| 1.7078 | 20.0 | 18480 | 1.7637 | 0.4277 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.35.0
|
93 |
+
- Pytorch 2.1.0
|
94 |
+
- Datasets 2.14.6
|
95 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
|
3 |
+
"architectures": [
|
4 |
+
"BeitForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"auxiliary_channels": 256,
|
8 |
+
"auxiliary_concat_input": false,
|
9 |
+
"auxiliary_loss_weight": 0.4,
|
10 |
+
"auxiliary_num_convs": 1,
|
11 |
+
"drop_path_rate": 0.1,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.0,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "AmorfHead",
|
17 |
+
"1": "AsymmetricNeck",
|
18 |
+
"10": "RoundHead",
|
19 |
+
"11": "ShortTail",
|
20 |
+
"12": "TaperedHead",
|
21 |
+
"13": "ThickNeck",
|
22 |
+
"14": "ThinNeck",
|
23 |
+
"15": "TwistedNeck",
|
24 |
+
"16": "TwistedTail",
|
25 |
+
"17": "VacuolatedHead",
|
26 |
+
"2": "CurlyTail",
|
27 |
+
"3": "DoubleHead",
|
28 |
+
"4": "DoubleTail",
|
29 |
+
"5": "LongTail",
|
30 |
+
"6": "NarrowAcrosome",
|
31 |
+
"7": "Normal",
|
32 |
+
"8": "PinHead",
|
33 |
+
"9": "PyriformHead"
|
34 |
+
},
|
35 |
+
"image_size": 224,
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"label2id": {
|
39 |
+
"AmorfHead": "0",
|
40 |
+
"AsymmetricNeck": "1",
|
41 |
+
"CurlyTail": "2",
|
42 |
+
"DoubleHead": "3",
|
43 |
+
"DoubleTail": "4",
|
44 |
+
"LongTail": "5",
|
45 |
+
"NarrowAcrosome": "6",
|
46 |
+
"Normal": "7",
|
47 |
+
"PinHead": "8",
|
48 |
+
"PyriformHead": "9",
|
49 |
+
"RoundHead": "10",
|
50 |
+
"ShortTail": "11",
|
51 |
+
"TaperedHead": "12",
|
52 |
+
"ThickNeck": "13",
|
53 |
+
"ThinNeck": "14",
|
54 |
+
"TwistedNeck": "15",
|
55 |
+
"TwistedTail": "16",
|
56 |
+
"VacuolatedHead": "17"
|
57 |
+
},
|
58 |
+
"layer_norm_eps": 1e-12,
|
59 |
+
"layer_scale_init_value": 0.1,
|
60 |
+
"model_type": "beit",
|
61 |
+
"num_attention_heads": 12,
|
62 |
+
"num_channels": 3,
|
63 |
+
"num_hidden_layers": 12,
|
64 |
+
"out_indices": [
|
65 |
+
3,
|
66 |
+
5,
|
67 |
+
7,
|
68 |
+
11
|
69 |
+
],
|
70 |
+
"patch_size": 16,
|
71 |
+
"pool_scales": [
|
72 |
+
1,
|
73 |
+
2,
|
74 |
+
3,
|
75 |
+
6
|
76 |
+
],
|
77 |
+
"problem_type": "single_label_classification",
|
78 |
+
"semantic_loss_ignore_index": 255,
|
79 |
+
"torch_dtype": "float32",
|
80 |
+
"transformers_version": "4.35.0",
|
81 |
+
"use_absolute_position_embeddings": false,
|
82 |
+
"use_auxiliary_head": true,
|
83 |
+
"use_mask_token": false,
|
84 |
+
"use_mean_pooling": true,
|
85 |
+
"use_relative_position_bias": true,
|
86 |
+
"use_shared_relative_position_bias": false,
|
87 |
+
"vocab_size": 8192
|
88 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9a4d1a71588e1c5e2b26eecd9b938bc4af0ab694670b5a27fd5df953e1edf3
|
3 |
+
size 343129544
|
preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": false,
|
7 |
+
"do_normalize": true,
|
8 |
+
"do_reduce_labels": false,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"image_processor_type": "BeitImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.5,
|
19 |
+
0.5,
|
20 |
+
0.5
|
21 |
+
],
|
22 |
+
"resample": 2,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"height": 224,
|
26 |
+
"width": 224
|
27 |
+
}
|
28 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5c8e8840787b89fba000f01c6ce75a00ac891a9d0cc1c2ff8ea36658c598021
|
3 |
+
size 4704
|