Hugging Face's logo

Jiyog
/
resnet-kitchen-object

Image Classification
Transformers
Safetensors
resnet
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
Jiyog commited on
Commit
ab6cf1b
·
verified ·
1 Parent(s): 67bee74

Jiyog/resnet-kitchen-object

Browse files
Files changed (4) hide show
  1. README.md +19 -19
  2. config.json +8 -9
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -22,10 +22,10 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6101118133203695
26
  - name: F1
27
  type: f1
28
- value: 0.6021708939263245
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [](https://huggingface.co/) on the imagefolder dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 1.2989
39
- - Accuracy: 0.6101
40
- - F1: 0.6022
41
 
42
  ## Model description
43
 
@@ -70,20 +70,20 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
- | 2.3261 | 1.0 | 224 | 3.1962 | 0.2003 | 0.1597 |
74
- | 2.0485 | 2.0 | 448 | 2.0192 | 0.2897 | 0.2667 |
75
- | 1.8855 | 3.0 | 672 | 2.0079 | 0.3359 | 0.3114 |
76
- | 1.8135 | 4.0 | 896 | 2.4398 | 0.2985 | 0.2768 |
77
- | 1.7122 | 5.0 | 1120 | 1.7434 | 0.4127 | 0.3893 |
78
- | 1.5719 | 6.0 | 1344 | 1.7204 | 0.4011 | 0.3928 |
79
- | 1.4702 | 7.0 | 1568 | 1.5112 | 0.4886 | 0.4830 |
80
- | 1.3995 | 8.0 | 1792 | 1.4794 | 0.4861 | 0.4804 |
81
- | 1.2542 | 9.0 | 2016 | 1.6779 | 0.4677 | 0.4694 |
82
- | 1.1446 | 10.0 | 2240 | 1.3876 | 0.5445 | 0.5359 |
83
- | 1.0104 | 11.0 | 2464 | 1.3369 | 0.5863 | 0.5782 |
84
- | 0.8867 | 12.0 | 2688 | 1.2919 | 0.5848 | 0.5821 |
85
- | 0.738 | 13.0 | 2912 | 1.2914 | 0.6057 | 0.6026 |
86
- | 0.7641 | 14.0 | 3136 | 1.2989 | 0.6101 | 0.6022 |
87
 
88
 
89
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.650461837627613
26
  - name: F1
27
  type: f1
28
+ value: 0.6481801350383302
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [](https://huggingface.co/) on the imagefolder dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 1.1453
39
+ - Accuracy: 0.6505
40
+ - F1: 0.6482
41
 
42
  ## Model description
43
 
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
+ | 2.0106 | 1.0 | 224 | 2.3071 | 0.2022 | 0.1647 |
74
+ | 1.7945 | 2.0 | 448 | 1.8394 | 0.3369 | 0.3385 |
75
+ | 1.6123 | 3.0 | 672 | 1.8258 | 0.3709 | 0.3426 |
76
+ | 1.5264 | 4.0 | 896 | 1.7281 | 0.4088 | 0.4060 |
77
+ | 1.3383 | 5.0 | 1120 | 1.7189 | 0.4093 | 0.4109 |
78
+ | 1.254 | 6.0 | 1344 | 1.4396 | 0.5012 | 0.4885 |
79
+ | 1.1198 | 7.0 | 1568 | 1.4400 | 0.5090 | 0.5126 |
80
+ | 0.9935 | 8.0 | 1792 | 1.5129 | 0.5177 | 0.5282 |
81
+ | 0.8163 | 9.0 | 2016 | 1.2204 | 0.6067 | 0.6020 |
82
+ | 0.5996 | 10.0 | 2240 | 1.2234 | 0.6179 | 0.6069 |
83
+ | 0.4508 | 11.0 | 2464 | 1.1936 | 0.6354 | 0.6288 |
84
+ | 0.3668 | 12.0 | 2688 | 1.1787 | 0.6364 | 0.6313 |
85
+ | 0.2702 | 13.0 | 2912 | 1.1435 | 0.6441 | 0.6427 |
86
+ | 0.2471 | 14.0 | 3136 | 1.1453 | 0.6505 | 0.6482 |
87
 
88
 
89
  ### Framework versions
config.json CHANGED
@@ -3,10 +3,10 @@
3
  "ResNetForImageClassification"
4
  ],
5
  "depths": [
6
- 3,
7
- 4,
8
- 6,
9
- 3
10
  ],
11
  "downsample_in_bottleneck": false,
12
  "downsample_in_first_stage": false,
@@ -14,10 +14,10 @@
14
  "embedding_size": 64,
15
  "hidden_act": "relu",
16
  "hidden_sizes": [
 
 
17
  256,
18
- 512,
19
- 1024,
20
- 2048
21
  ],
22
  "id2label": {
23
  "0": "bowl",
@@ -31,7 +31,6 @@
31
  "8": "spoon",
32
  "9": "whisk"
33
  },
34
- "image_size": 224,
35
  "label2id": {
36
  "bowl": "0",
37
  "fork": "1",
@@ -44,7 +43,7 @@
44
  "spoon": "8",
45
  "whisk": "9"
46
  },
47
- "layer_type": "bottleneck",
48
  "model_type": "resnet",
49
  "num_channels": 3,
50
  "out_features": [
 
3
  "ResNetForImageClassification"
4
  ],
5
  "depths": [
6
+ 2,
7
+ 2,
8
+ 2,
9
+ 2
10
  ],
11
  "downsample_in_bottleneck": false,
12
  "downsample_in_first_stage": false,
 
14
  "embedding_size": 64,
15
  "hidden_act": "relu",
16
  "hidden_sizes": [
17
+ 64,
18
+ 128,
19
  256,
20
+ 512
 
 
21
  ],
22
  "id2label": {
23
  "0": "bowl",
 
31
  "8": "spoon",
32
  "9": "whisk"
33
  },
 
34
  "label2id": {
35
  "bowl": "0",
36
  "fork": "1",
 
43
  "spoon": "8",
44
  "whisk": "9"
45
  },
46
+ "layer_type": "basic",
47
  "model_type": "resnet",
48
  "num_channels": 3,
49
  "out_features": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:541c9395d1ab1615a8cf8ac583df088ccc8c81d3546d7624ecc756b32ac1bb1d
3
- size 94368544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4965d63b49ccc69db969ebf41b101bcbcd0a5c2afb5609f89206e6b7c3763cda
3
+ size 44780752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0bfb2962d99bde82dd0e64aa71db08233ac86ac55c6bba8ea82e5cd4448ede4
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bea7d41aeaefbb85b544f23aa9399ebcdc2f653c0d9caaa25b5a3211ba135b8
3
  size 5841