Hugging Face's logo

paolinox
/
mobilevit-finetuned-food101

Image Classification
Transformers
TensorBoard
Safetensors
mobilevitv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
paolinox commited on
Commit
b7f582f
·
1 Parent(s): 8d3feb5

paolinox/mobilevit-FT-food101

Browse files
Files changed (7) hide show
  1. README.md +107 -0
  2. config.json +61 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +17 -0
  5. runs/Nov28_11-52-58_f71d5d222dbc/events.out.tfevents.1701172379.f71d5d222dbc.15295.1 +3 -0
  6. runs/Nov28_11-54-32_f71d5d222dbc/events.out.tfevents.1701172483.f71d5d222dbc.16548.0 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: apple/mobilevitv2-1.0-imagenet1k-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - food101
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: mobilevit-finetuned-food101
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: food101
18
+ type: food101
19
+ config: default
20
+ split: train[:5000]
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.874
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
+ # mobilevit-finetuned-food101
32
+
33
+ This model is a fine-tuned version of [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) on the food101 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.4191
36
+ - Accuracy: 0.874
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: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
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: 30
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.9487 | 0.98 | 23 | 1.9476 | 0.151 |
71
+ | 1.9273 | 2.0 | 47 | 1.9070 | 0.24 |
72
+ | 1.8561 | 2.98 | 70 | 1.8401 | 0.448 |
73
+ | 1.7788 | 4.0 | 94 | 1.7301 | 0.612 |
74
+ | 1.6586 | 4.98 | 117 | 1.5863 | 0.676 |
75
+ | 1.4603 | 6.0 | 141 | 1.4199 | 0.72 |
76
+ | 1.3027 | 6.98 | 164 | 1.2215 | 0.734 |
77
+ | 1.1717 | 8.0 | 188 | 1.0581 | 0.759 |
78
+ | 0.9601 | 8.98 | 211 | 0.9013 | 0.769 |
79
+ | 0.8482 | 10.0 | 235 | 0.7866 | 0.791 |
80
+ | 0.7276 | 10.98 | 258 | 0.7112 | 0.803 |
81
+ | 0.6449 | 12.0 | 282 | 0.6132 | 0.835 |
82
+ | 0.6279 | 12.98 | 305 | 0.6069 | 0.83 |
83
+ | 0.5982 | 14.0 | 329 | 0.5637 | 0.832 |
84
+ | 0.5766 | 14.98 | 352 | 0.5149 | 0.857 |
85
+ | 0.5345 | 16.0 | 376 | 0.5392 | 0.837 |
86
+ | 0.494 | 16.98 | 399 | 0.5017 | 0.848 |
87
+ | 0.4953 | 18.0 | 423 | 0.5002 | 0.846 |
88
+ | 0.5118 | 18.98 | 446 | 0.4782 | 0.856 |
89
+ | 0.4708 | 20.0 | 470 | 0.4898 | 0.858 |
90
+ | 0.4774 | 20.98 | 493 | 0.4769 | 0.851 |
91
+ | 0.4848 | 22.0 | 517 | 0.4665 | 0.841 |
92
+ | 0.4533 | 22.98 | 540 | 0.4890 | 0.837 |
93
+ | 0.4449 | 24.0 | 564 | 0.4558 | 0.857 |
94
+ | 0.4205 | 24.98 | 587 | 0.4767 | 0.857 |
95
+ | 0.4417 | 26.0 | 611 | 0.4476 | 0.853 |
96
+ | 0.4333 | 26.98 | 634 | 0.4853 | 0.834 |
97
+ | 0.4545 | 28.0 | 658 | 0.4573 | 0.847 |
98
+ | 0.4489 | 28.98 | 681 | 0.4659 | 0.845 |
99
+ | 0.4172 | 29.36 | 690 | 0.4191 | 0.874 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.35.2
105
+ - Pytorch 2.1.0+cu118
106
+ - Datasets 2.15.0
107
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "apple/mobilevitv2-1.0-imagenet1k-256",
3
+ "architectures": [
4
+ "MobileViTV2ForImageClassification"
5
+ ],
6
+ "aspp_dropout_prob": 0.1,
7
+ "aspp_out_channels": 512,
8
+ "atrous_rates": [
9
+ 6,
10
+ 12,
11
+ 18
12
+ ],
13
+ "attn_dropout": 0.0,
14
+ "base_attn_unit_dims": [
15
+ 128,
16
+ 192,
17
+ 256
18
+ ],
19
+ "classifier_dropout_prob": 0.1,
20
+ "conv_kernel_size": 3,
21
+ "expand_ratio": 2.0,
22
+ "ffn_dropout": 0.0,
23
+ "ffn_multiplier": 2,
24
+ "hidden_act": "swish",
25
+ "id2label": {
26
+ "0": "beignets",
27
+ "1": "bruschetta",
28
+ "2": "chicken_wings",
29
+ "3": "hamburger",
30
+ "4": "pork_chop",
31
+ "5": "prime_rib",
32
+ "6": "ramen"
33
+ },
34
+ "image_size": 256,
35
+ "initializer_range": 0.02,
36
+ "label2id": {
37
+ "beignets": 0,
38
+ "bruschetta": 1,
39
+ "chicken_wings": 2,
40
+ "hamburger": 3,
41
+ "pork_chop": 4,
42
+ "prime_rib": 5,
43
+ "ramen": 6
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "mlp_ratio": 2.0,
47
+ "model_type": "mobilevitv2",
48
+ "n_attn_blocks": [
49
+ 2,
50
+ 4,
51
+ 3
52
+ ],
53
+ "num_channels": 3,
54
+ "output_stride": 32,
55
+ "patch_size": 2,
56
+ "problem_type": "single_label_classification",
57
+ "semantic_loss_ignore_index": 255,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.35.2",
60
+ "width_multiplier": 1.0
61
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250016110cd75ef795dada56345d97dcc5bacffb2777a16883391b5647bdc64a
3
+ size 17669344
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 256,
4
+ "width": 256
5
+ },
6
+ "do_center_crop": true,
7
+ "do_flip_channel_order": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_processor_type": "MobileViTImageProcessor",
11
+ "resample": 2,
12
+ "rescale_factor": 0.00392156862745098,
13
+ "size": {
14
+ "shortest_edge": 288
15
+ },
16
+ "use_square_size": false
17
+ }
runs/Nov28_11-52-58_f71d5d222dbc/events.out.tfevents.1701172379.f71d5d222dbc.15295.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046766e71836da40311411a26bee2fbabb18169dab91ed48ae53e5dc298c8a53
3
+ size 88
runs/Nov28_11-54-32_f71d5d222dbc/events.out.tfevents.1701172483.f71d5d222dbc.16548.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286caa6dbd5dc6d7fc331b6df8653ba9b5677adaa4c9f7731b9c4c44c73d1ab2
3
+ size 25601
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dc3836ce49174d52c62e09cce157e36d8ec85d6f9b9d126bd00187ed165ad09
3
+ size 4600