Instructions to use mruby/swin-tiny-patch4-window7-224-attempt-m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mruby/swin-tiny-patch4-window7-224-attempt-m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="mruby/swin-tiny-patch4-window7-224-attempt-m") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("mruby/swin-tiny-patch4-window7-224-attempt-m") model = AutoModelForImageClassification.from_pretrained("mruby/swin-tiny-patch4-window7-224-attempt-m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from mruby/swin-tiny-patch4-window7-224-attempt-m: direct link, hf CLI and curl.
- Browser
- Download file 1.63 kB
-
https://huggingface.co/mruby/swin-tiny-patch4-window7-224-attempt-m/resolve/main/README.md
- Command line
-
hf download hf://mruby/swin-tiny-patch4-window7-224-attempt-m/README.md
-
curl -L -o README.md https://huggingface.co/mruby/swin-tiny-patch4-window7-224-attempt-m/resolve/main/README.md
1.63 kB
metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-attempt-m
results: []
swin-tiny-patch4-window7-224-attempt-m
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0513
- Accuracy: 0.9831
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1638 | 0.99 | 33 | 0.1839 | 0.9302 |
| 0.1017 | 1.98 | 66 | 0.1089 | 0.9556 |
| 0.0637 | 2.98 | 99 | 0.0513 | 0.9831 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3