Model save
Browse files- README.md +92 -0
- config.json +153 -0
- model.safetensors +3 -0
- preprocessor_config.json +44 -0
- runs/Jun05_01-56-31_236c2c095f0f/events.out.tfevents.1717552593.236c2c095f0f.21358.0 +3 -0
- runs/Jun05_01-58-00_236c2c095f0f/events.out.tfevents.1717552682.236c2c095f0f.21922.0 +3 -0
- runs/Jun05_01-59-29_236c2c095f0f/events.out.tfevents.1717552771.236c2c095f0f.22502.0 +3 -0
- runs/Jun05_02-01-19_236c2c095f0f/events.out.tfevents.1717552882.236c2c095f0f.23177.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/dinov2-giant
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: dino_finetuned_giant_10_layers_thawed
|
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: 0.7361218408564176
|
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 |
+
# dino_finetuned_giant_10_layers_thawed
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/dinov2-giant](https://huggingface.co/facebook/dinov2-giant) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0387
|
36 |
+
- Accuracy: 0.7361
|
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: 5e-05
|
56 |
+
- train_batch_size: 54
|
57 |
+
- eval_batch_size: 54
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 216
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 5
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
70 |
+
| 3.3778 | 0.3145 | 25 | 2.5161 | 0.3373 |
|
71 |
+
| 2.0106 | 0.6289 | 50 | 1.8874 | 0.4838 |
|
72 |
+
| 1.9 | 0.9434 | 75 | 1.6407 | 0.5441 |
|
73 |
+
| 1.2966 | 1.2579 | 100 | 1.4907 | 0.5930 |
|
74 |
+
| 1.3413 | 1.5723 | 125 | 1.3532 | 0.6358 |
|
75 |
+
| 1.2871 | 1.8868 | 150 | 1.2731 | 0.6547 |
|
76 |
+
| 0.7792 | 2.2013 | 175 | 1.1967 | 0.6875 |
|
77 |
+
| 0.7153 | 2.5157 | 200 | 1.1761 | 0.6966 |
|
78 |
+
| 0.7544 | 2.8302 | 225 | 1.1136 | 0.7096 |
|
79 |
+
| 0.465 | 3.1447 | 250 | 1.0962 | 0.7187 |
|
80 |
+
| 0.414 | 3.4591 | 275 | 1.0997 | 0.7274 |
|
81 |
+
| 0.4749 | 3.7736 | 300 | 1.0717 | 0.7291 |
|
82 |
+
| 0.4742 | 4.0881 | 325 | 1.0425 | 0.7323 |
|
83 |
+
| 0.3448 | 4.4025 | 350 | 1.0402 | 0.7392 |
|
84 |
+
| 0.3341 | 4.7170 | 375 | 1.0387 | 0.7361 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.41.2
|
90 |
+
- Pytorch 2.3.0+cu121
|
91 |
+
- Datasets 2.19.2
|
92 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/dinov2-giant",
|
3 |
+
"apply_layernorm": true,
|
4 |
+
"architectures": [
|
5 |
+
"Dinov2ForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"drop_path_rate": 0.0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 1536,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Alternative",
|
14 |
+
"1": "Animecore",
|
15 |
+
"10": "Dark_Fantasy",
|
16 |
+
"11": "E-Girl",
|
17 |
+
"12": "Ethereal",
|
18 |
+
"13": "Fairycore",
|
19 |
+
"14": "Goblincore",
|
20 |
+
"15": "Goth",
|
21 |
+
"16": "Grunge",
|
22 |
+
"17": "Hypebeast",
|
23 |
+
"18": "Jersey_Shore",
|
24 |
+
"19": "Kawaii",
|
25 |
+
"2": "Art_Hoe",
|
26 |
+
"20": "Kidcore",
|
27 |
+
"21": "Lagenlook",
|
28 |
+
"22": "Lolita",
|
29 |
+
"23": "Mob_Wife",
|
30 |
+
"24": "Normcore",
|
31 |
+
"25": "Old_Money",
|
32 |
+
"26": "Pastel_Goth",
|
33 |
+
"27": "Preppy",
|
34 |
+
"28": "Punk",
|
35 |
+
"29": "Soft_Grunge",
|
36 |
+
"3": "Avant-garde",
|
37 |
+
"30": "Steampunk",
|
38 |
+
"31": "Tomato_Girl_Summer",
|
39 |
+
"32": "Twee",
|
40 |
+
"33": "VSCO",
|
41 |
+
"34": "Vaporwave",
|
42 |
+
"35": "Y2K",
|
43 |
+
"4": "Baddie",
|
44 |
+
"5": "Bohemian",
|
45 |
+
"6": "Cottagecore",
|
46 |
+
"7": "Country",
|
47 |
+
"8": "Cyberpunk",
|
48 |
+
"9": "Dark_Academia"
|
49 |
+
},
|
50 |
+
"image_size": 518,
|
51 |
+
"initializer_range": 0.02,
|
52 |
+
"label2id": {
|
53 |
+
"Alternative": "0",
|
54 |
+
"Animecore": "1",
|
55 |
+
"Art_Hoe": "2",
|
56 |
+
"Avant-garde": "3",
|
57 |
+
"Baddie": "4",
|
58 |
+
"Bohemian": "5",
|
59 |
+
"Cottagecore": "6",
|
60 |
+
"Country": "7",
|
61 |
+
"Cyberpunk": "8",
|
62 |
+
"Dark_Academia": "9",
|
63 |
+
"Dark_Fantasy": "10",
|
64 |
+
"E-Girl": "11",
|
65 |
+
"Ethereal": "12",
|
66 |
+
"Fairycore": "13",
|
67 |
+
"Goblincore": "14",
|
68 |
+
"Goth": "15",
|
69 |
+
"Grunge": "16",
|
70 |
+
"Hypebeast": "17",
|
71 |
+
"Jersey_Shore": "18",
|
72 |
+
"Kawaii": "19",
|
73 |
+
"Kidcore": "20",
|
74 |
+
"Lagenlook": "21",
|
75 |
+
"Lolita": "22",
|
76 |
+
"Mob_Wife": "23",
|
77 |
+
"Normcore": "24",
|
78 |
+
"Old_Money": "25",
|
79 |
+
"Pastel_Goth": "26",
|
80 |
+
"Preppy": "27",
|
81 |
+
"Punk": "28",
|
82 |
+
"Soft_Grunge": "29",
|
83 |
+
"Steampunk": "30",
|
84 |
+
"Tomato_Girl_Summer": "31",
|
85 |
+
"Twee": "32",
|
86 |
+
"VSCO": "33",
|
87 |
+
"Vaporwave": "34",
|
88 |
+
"Y2K": "35"
|
89 |
+
},
|
90 |
+
"layer_norm_eps": 1e-06,
|
91 |
+
"layerscale_value": 1.0,
|
92 |
+
"mlp_ratio": 4,
|
93 |
+
"model_type": "dinov2",
|
94 |
+
"num_attention_heads": 24,
|
95 |
+
"num_channels": 3,
|
96 |
+
"num_hidden_layers": 40,
|
97 |
+
"out_features": [
|
98 |
+
"stage40"
|
99 |
+
],
|
100 |
+
"out_indices": [
|
101 |
+
40
|
102 |
+
],
|
103 |
+
"patch_size": 14,
|
104 |
+
"problem_type": "single_label_classification",
|
105 |
+
"qkv_bias": true,
|
106 |
+
"reshape_hidden_states": true,
|
107 |
+
"stage_names": [
|
108 |
+
"stem",
|
109 |
+
"stage1",
|
110 |
+
"stage2",
|
111 |
+
"stage3",
|
112 |
+
"stage4",
|
113 |
+
"stage5",
|
114 |
+
"stage6",
|
115 |
+
"stage7",
|
116 |
+
"stage8",
|
117 |
+
"stage9",
|
118 |
+
"stage10",
|
119 |
+
"stage11",
|
120 |
+
"stage12",
|
121 |
+
"stage13",
|
122 |
+
"stage14",
|
123 |
+
"stage15",
|
124 |
+
"stage16",
|
125 |
+
"stage17",
|
126 |
+
"stage18",
|
127 |
+
"stage19",
|
128 |
+
"stage20",
|
129 |
+
"stage21",
|
130 |
+
"stage22",
|
131 |
+
"stage23",
|
132 |
+
"stage24",
|
133 |
+
"stage25",
|
134 |
+
"stage26",
|
135 |
+
"stage27",
|
136 |
+
"stage28",
|
137 |
+
"stage29",
|
138 |
+
"stage30",
|
139 |
+
"stage31",
|
140 |
+
"stage32",
|
141 |
+
"stage33",
|
142 |
+
"stage34",
|
143 |
+
"stage35",
|
144 |
+
"stage36",
|
145 |
+
"stage37",
|
146 |
+
"stage38",
|
147 |
+
"stage39",
|
148 |
+
"stage40"
|
149 |
+
],
|
150 |
+
"torch_dtype": "float32",
|
151 |
+
"transformers_version": "4.41.2",
|
152 |
+
"use_swiglu_ffn": true
|
153 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:158d90c99c5241670f230730e02183b630a9eeb0f685ec991fcb01d461cee8a9
|
3 |
+
size 4546453200
|
preprocessor_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"crop_size": {
|
20 |
+
"height": 224,
|
21 |
+
"width": 224
|
22 |
+
},
|
23 |
+
"do_center_crop": true,
|
24 |
+
"do_convert_rgb": true,
|
25 |
+
"do_normalize": true,
|
26 |
+
"do_rescale": true,
|
27 |
+
"do_resize": true,
|
28 |
+
"image_mean": [
|
29 |
+
0.485,
|
30 |
+
0.456,
|
31 |
+
0.406
|
32 |
+
],
|
33 |
+
"image_processor_type": "BitImageProcessor",
|
34 |
+
"image_std": [
|
35 |
+
0.229,
|
36 |
+
0.224,
|
37 |
+
0.225
|
38 |
+
],
|
39 |
+
"resample": 3,
|
40 |
+
"rescale_factor": 0.00392156862745098,
|
41 |
+
"size": {
|
42 |
+
"shortest_edge": 256
|
43 |
+
}
|
44 |
+
}
|
runs/Jun05_01-56-31_236c2c095f0f/events.out.tfevents.1717552593.236c2c095f0f.21358.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd44d3b3a15995d470ba790cfe2f839fdadc9b498513103b8663d236c2396f00
|
3 |
+
size 7409
|
runs/Jun05_01-58-00_236c2c095f0f/events.out.tfevents.1717552682.236c2c095f0f.21922.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d3565f558a54e1912ecec651fc169cf889983879d666d9af6162f8552f07c64
|
3 |
+
size 4184
|
runs/Jun05_01-59-29_236c2c095f0f/events.out.tfevents.1717552771.236c2c095f0f.22502.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a47bb8a77519e74ed90d218ad713b27e7ad3760283b8b082f89235fbb6b1072
|
3 |
+
size 4184
|
runs/Jun05_02-01-19_236c2c095f0f/events.out.tfevents.1717552882.236c2c095f0f.23177.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:316e2359ed7650880582f363b9113b855d6556a61817f453429f85cfff054485
|
3 |
+
size 20552
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d02c8ec29fe0801112ea78863c6b401ecfb3e708061a588e09c846e8c2602104
|
3 |
+
size 5112
|