Hugging Face's logo

omarhkh
/
resnet-50-finetuned-omar

Image Classification
Transformers
PyTorch
resnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
omarhkh commited on
Commit
82b6bc9
·
1 Parent(s): 5f3dd81

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -7
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.5768261964735516
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.8737
35
- - Accuracy: 0.5768
36
 
37
  ## Model description
38
 
@@ -60,15 +60,27 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 3
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.9977 | 1.0 | 111 | 0.9933 | 0.5214 |
70
- | 0.9814 | 2.0 | 223 | 0.9009 | 0.5340 |
71
- | 0.9463 | 2.99 | 333 | 0.8737 | 0.5768 |
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9143576826196473
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2645
35
+ - Accuracy: 0.9144
36
 
37
  ## Model description
38
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 15
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 1.0695 | 1.0 | 111 | 1.0576 | 0.5315 |
70
+ | 0.971 | 2.0 | 223 | 0.9366 | 0.5416 |
71
+ | 0.8121 | 3.0 | 334 | 0.7493 | 0.7103 |
72
+ | 0.6861 | 4.0 | 446 | 0.5625 | 0.8363 |
73
+ | 0.606 | 5.0 | 557 | 0.4239 | 0.8816 |
74
+ | 0.5001 | 6.0 | 669 | 0.3159 | 0.9219 |
75
+ | 0.4704 | 7.0 | 780 | 0.3254 | 0.9118 |
76
+ | 0.4332 | 8.0 | 892 | 0.2808 | 0.9194 |
77
+ | 0.4432 | 9.0 | 1003 | 0.2854 | 0.9219 |
78
+ | 0.4768 | 10.0 | 1115 | 0.2782 | 0.9219 |
79
+ | 0.4432 | 11.0 | 1226 | 0.2768 | 0.9320 |
80
+ | 0.4752 | 12.0 | 1338 | 0.2744 | 0.9219 |
81
+ | 0.489 | 13.0 | 1449 | 0.2693 | 0.9194 |
82
+ | 0.3743 | 14.0 | 1561 | 0.2715 | 0.9270 |
83
+ | 0.417 | 14.93 | 1665 | 0.2645 | 0.9144 |
84
 
85
 
86
  ### Framework versions