ZaneHorrible
commited on
Commit
•
8a5baa2
1
Parent(s):
90e638b
Model save
Browse files- README.md +118 -0
- config.json +76 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/May23_15-05-50_94fe4971605c/events.out.tfevents.1716476775.94fe4971605c.34.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-large-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: Adam_ViTL-16_224-2e-4-batch_16_epoch_4_classes_24
|
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: 0.9683908045977011
|
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 |
+
# Adam_ViTL-16_224-2e-4-batch_16_epoch_4_classes_24
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1211
|
36 |
+
- Accuracy: 0.9684
|
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: 0.0002
|
56 |
+
- train_batch_size: 16
|
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: 3
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.6934 | 0.07 | 100 | 0.4138 | 0.8477 |
|
69 |
+
| 0.4815 | 0.14 | 200 | 0.7227 | 0.8103 |
|
70 |
+
| 0.3952 | 0.21 | 300 | 0.5867 | 0.8491 |
|
71 |
+
| 0.6095 | 0.28 | 400 | 0.5975 | 0.8448 |
|
72 |
+
| 0.3448 | 0.35 | 500 | 0.4000 | 0.8721 |
|
73 |
+
| 0.2604 | 0.42 | 600 | 0.3335 | 0.9080 |
|
74 |
+
| 0.3734 | 0.49 | 700 | 0.4264 | 0.875 |
|
75 |
+
| 0.3074 | 0.56 | 800 | 0.3634 | 0.8908 |
|
76 |
+
| 0.312 | 0.63 | 900 | 0.4347 | 0.875 |
|
77 |
+
| 0.1076 | 0.7 | 1000 | 0.3203 | 0.9052 |
|
78 |
+
| 0.2001 | 0.77 | 1100 | 0.2668 | 0.9224 |
|
79 |
+
| 0.0507 | 0.84 | 1200 | 0.2265 | 0.9353 |
|
80 |
+
| 0.0767 | 0.91 | 1300 | 0.2797 | 0.9239 |
|
81 |
+
| 0.3201 | 0.97 | 1400 | 0.2977 | 0.9109 |
|
82 |
+
| 0.0293 | 1.04 | 1500 | 0.2849 | 0.9239 |
|
83 |
+
| 0.0353 | 1.11 | 1600 | 0.2918 | 0.9339 |
|
84 |
+
| 0.0787 | 1.18 | 1700 | 0.3012 | 0.9253 |
|
85 |
+
| 0.0749 | 1.25 | 1800 | 0.2383 | 0.9454 |
|
86 |
+
| 0.0233 | 1.32 | 1900 | 0.3272 | 0.9152 |
|
87 |
+
| 0.1635 | 1.39 | 2000 | 0.2857 | 0.9124 |
|
88 |
+
| 0.0586 | 1.46 | 2100 | 0.3785 | 0.9109 |
|
89 |
+
| 0.0103 | 1.53 | 2200 | 0.2032 | 0.9468 |
|
90 |
+
| 0.0082 | 1.6 | 2300 | 0.2091 | 0.9397 |
|
91 |
+
| 0.0695 | 1.67 | 2400 | 0.1739 | 0.9526 |
|
92 |
+
| 0.0253 | 1.74 | 2500 | 0.2056 | 0.9511 |
|
93 |
+
| 0.0648 | 1.81 | 2600 | 0.1803 | 0.9526 |
|
94 |
+
| 0.0286 | 1.88 | 2700 | 0.2018 | 0.9440 |
|
95 |
+
| 0.0057 | 1.95 | 2800 | 0.2332 | 0.9483 |
|
96 |
+
| 0.0056 | 2.02 | 2900 | 0.3459 | 0.9267 |
|
97 |
+
| 0.0111 | 2.09 | 3000 | 0.1954 | 0.9540 |
|
98 |
+
| 0.0001 | 2.16 | 3100 | 0.1586 | 0.9626 |
|
99 |
+
| 0.0059 | 2.23 | 3200 | 0.1716 | 0.9526 |
|
100 |
+
| 0.0063 | 2.3 | 3300 | 0.1548 | 0.9612 |
|
101 |
+
| 0.0003 | 2.37 | 3400 | 0.1813 | 0.9569 |
|
102 |
+
| 0.0006 | 2.44 | 3500 | 0.1339 | 0.9626 |
|
103 |
+
| 0.0004 | 2.51 | 3600 | 0.1492 | 0.9583 |
|
104 |
+
| 0.0004 | 2.58 | 3700 | 0.1238 | 0.9698 |
|
105 |
+
| 0.0001 | 2.65 | 3800 | 0.1156 | 0.9713 |
|
106 |
+
| 0.0001 | 2.72 | 3900 | 0.1272 | 0.9684 |
|
107 |
+
| 0.0 | 2.79 | 4000 | 0.1303 | 0.9698 |
|
108 |
+
| 0.0001 | 2.86 | 4100 | 0.1269 | 0.9684 |
|
109 |
+
| 0.0001 | 2.92 | 4200 | 0.1209 | 0.9684 |
|
110 |
+
| 0.0 | 2.99 | 4300 | 0.1211 | 0.9684 |
|
111 |
+
|
112 |
+
|
113 |
+
### Framework versions
|
114 |
+
|
115 |
+
- Transformers 4.39.3
|
116 |
+
- Pytorch 2.1.2
|
117 |
+
- Datasets 2.18.0
|
118 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-large-patch16-224",
|
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": 1024,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)",
|
13 |
+
"1": "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)",
|
14 |
+
"10": "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)",
|
15 |
+
"11": "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)",
|
16 |
+
"12": "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)",
|
17 |
+
"13": "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)",
|
18 |
+
"14": "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)",
|
19 |
+
"15": "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)",
|
20 |
+
"16": "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)",
|
21 |
+
"17": "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)",
|
22 |
+
"18": "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)",
|
23 |
+
"19": "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)",
|
24 |
+
"2": "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)",
|
25 |
+
"20": "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)",
|
26 |
+
"21": "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)",
|
27 |
+
"22": "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)",
|
28 |
+
"23": "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)",
|
29 |
+
"3": "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)",
|
30 |
+
"4": "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)",
|
31 |
+
"5": "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)",
|
32 |
+
"6": "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)",
|
33 |
+
"7": "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)",
|
34 |
+
"8": "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)",
|
35 |
+
"9": "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)"
|
36 |
+
},
|
37 |
+
"image_size": 224,
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 4096,
|
40 |
+
"label2id": {
|
41 |
+
"Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)": "0",
|
42 |
+
"Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)": "1",
|
43 |
+
"Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)": "2",
|
44 |
+
"Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)": "3",
|
45 |
+
"Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)": "4",
|
46 |
+
"Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)": "5",
|
47 |
+
"Fuchka(\u09ab\u09c1\u099a\u0995\u09be)": "6",
|
48 |
+
"Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)": "7",
|
49 |
+
"Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)": "8",
|
50 |
+
"Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)": "9",
|
51 |
+
"Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)": "10",
|
52 |
+
"Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)": "11",
|
53 |
+
"Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)": "12",
|
54 |
+
"Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)": "13",
|
55 |
+
"Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)": "14",
|
56 |
+
"Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)": "15",
|
57 |
+
"Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)": "16",
|
58 |
+
"Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)": "17",
|
59 |
+
"Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)": "18",
|
60 |
+
"Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)": "19",
|
61 |
+
"Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)": "20",
|
62 |
+
"Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)": "21",
|
63 |
+
"Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)": "22",
|
64 |
+
"Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)": "23"
|
65 |
+
},
|
66 |
+
"layer_norm_eps": 1e-12,
|
67 |
+
"model_type": "vit",
|
68 |
+
"num_attention_heads": 16,
|
69 |
+
"num_channels": 3,
|
70 |
+
"num_hidden_layers": 24,
|
71 |
+
"patch_size": 16,
|
72 |
+
"problem_type": "single_label_classification",
|
73 |
+
"qkv_bias": true,
|
74 |
+
"torch_dtype": "float32",
|
75 |
+
"transformers_version": "4.39.3"
|
76 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eecbd8080d13ff503aae99009494f1b8625bb87de75904184a47f0256228461
|
3 |
+
size 1213351480
|
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 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
runs/May23_15-05-50_94fe4971605c/events.out.tfevents.1716476775.94fe4971605c.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3394c3db075d2315744df6b0d410611fddeaff1a20c095efcf1e5b705d7b54d7
|
3 |
+
size 113190
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350f64a85edbab01dea26a00b544b2d028ceaf8fded4727b93e814bb605b56ed
|
3 |
+
size 4984
|