mobilenet_v2_1.0_224-cxr-view
This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2278
- Accuracy: 0.9294
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7049 | 1.0 | 109 | 0.6746 | 0.7449 |
0.6565 | 2.0 | 219 | 0.6498 | 0.6743 |
0.5699 | 3.0 | 328 | 0.5730 | 0.7995 |
0.5702 | 4.0 | 438 | 0.5119 | 0.8087 |
0.4849 | 5.0 | 547 | 0.4356 | 0.8679 |
0.356 | 6.0 | 657 | 0.4641 | 0.8087 |
0.3713 | 7.0 | 766 | 0.3407 | 0.8679 |
0.4571 | 8.0 | 876 | 0.4896 | 0.7813 |
0.3896 | 9.0 | 985 | 0.3124 | 0.8884 |
0.3422 | 10.0 | 1095 | 0.2791 | 0.9271 |
0.3358 | 11.0 | 1204 | 0.3998 | 0.8246 |
0.3658 | 12.0 | 1314 | 0.2716 | 0.9066 |
0.4547 | 13.0 | 1423 | 0.5828 | 0.7973 |
0.2615 | 14.0 | 1533 | 0.3446 | 0.8542 |
0.377 | 15.0 | 1642 | 0.6322 | 0.7312 |
0.2846 | 16.0 | 1752 | 0.2621 | 0.9248 |
0.3433 | 17.0 | 1861 | 0.3709 | 0.8383 |
0.2851 | 18.0 | 1971 | 0.8134 | 0.7312 |
0.2298 | 19.0 | 2080 | 0.4324 | 0.8314 |
0.3916 | 20.0 | 2190 | 0.3631 | 0.8360 |
0.3049 | 21.0 | 2299 | 0.3405 | 0.8633 |
0.3068 | 22.0 | 2409 | 0.2585 | 0.9021 |
0.3091 | 23.0 | 2518 | 0.2278 | 0.9294 |
0.2749 | 24.0 | 2628 | 0.2963 | 0.9043 |
0.3543 | 25.0 | 2737 | 0.2637 | 0.8975 |
0.3024 | 26.0 | 2847 | 0.2966 | 0.8998 |
0.2593 | 27.0 | 2956 | 0.3842 | 0.8542 |
0.1979 | 28.0 | 3066 | 0.2711 | 0.8884 |
0.2549 | 29.0 | 3175 | 0.3145 | 0.8633 |
0.3216 | 29.86 | 3270 | 0.4565 | 0.8155 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 51
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.