Downloads · 30 days
7
10% of all-time downloads
msi-resnet-18
aaa12963337/msi-resnet-18
msi-resnet-18 is a image classification model from aaa12963337. Use it when you need a label for an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
71
Public
Parameters
11.2M
358 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors44.8 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- resnet
- Access
- Public
- Created
- Dec 16, 2023
- Updated
- Dec 16, 2023
- SHA
- da1e5aef
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
msi-resnet-18
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6854
- Accuracy: 0.6337
- F1: 0.5299
- Precision: 0.5977
- Recall: 0.4760
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: 1e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.499 | 1.0 | 2015 | 0.7028 | 0.6189 | 0.4730 | 0.5911 | 0.3942 |
| 0.4738 | 2.0 | 4031 | 0.7003 | 0.6268 | 0.4981 | 0.5979 | 0.4268 |
| 0.4788 | 3.0 | 6047 | 0.7195 | 0.6148 | 0.4517 | 0.5906 | 0.3657 |
| 0.4523 | 4.0 | 8060 | 0.6854 | 0.6337 | 0.5299 | 0.5977 | 0.4760 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- resnet
- Created
- Dec 16, 2023
- Updated
- Dec 16, 2023