Downloads · 30 days
9
1% of all-time downloads
swinv2-base-512
gagan3012/swinv2-base-512
swinv2-base-512 is a image classification model from gagan3012. 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
901
Public
Repo size
695 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin348 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- swinv2
- Access
- Public
- Created
- Jan 24, 2023
- Updated
- Jan 24, 2023
- SHA
- c3241ca8
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. -->
swinv2-base-512
This model was trained from scratch on the /lustre07/scratch/gagan30/arocr/Shamila dataset. It achieves the following results on the evaluation set:
- Loss: 1.0139
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-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 1337
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9887 | 1.0 | 139819 | 1.0138 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1
- Datasets 2.7.1
- Tokenizers 0.11.6
- Task
- Image Classification
- Library
- transformers
- Type
- swinv2
- Created
- Jan 24, 2023
- Updated
- Jan 24, 2023