Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Instructions to use andakm/swin-tiny-patch4-window7-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use andakm/swin-tiny-patch4-window7-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="andakm/swin-tiny-patch4-window7-224") 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("andakm/swin-tiny-patch4-window7-224") model = AutoModelForImageClassification.from_pretrained("andakm/swin-tiny-patch4-window7-224", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from andakm/swin-tiny-patch4-window7-224: direct link, hf CLI and curl.
- Browser
- Download file 2.29 kB
-
https://huggingface.co/andakm/swin-tiny-patch4-window7-224/resolve/main/README.md
- Command line
-
hf download hf://andakm/swin-tiny-patch4-window7-224/README.md
-
curl -L -o README.md https://huggingface.co/andakm/swin-tiny-patch4-window7-224/resolve/main/README.md
2.29 kB
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5294117647058824
swin-tiny-patch4-window7-224
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3635
- Accuracy: 0.5294
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.8 | 3 | 1.7560 | 0.3137 |
| No log | 1.87 | 7 | 1.6225 | 0.3725 |
| 1.7919 | 2.93 | 11 | 1.5661 | 0.4510 |
| 1.7919 | 4.0 | 15 | 1.5332 | 0.4510 |
| 1.7919 | 4.8 | 18 | 1.4522 | 0.5294 |
| 1.5187 | 5.87 | 22 | 1.3873 | 0.4902 |
| 1.5187 | 6.93 | 26 | 1.3741 | 0.4902 |
| 1.2773 | 8.0 | 30 | 1.3635 | 0.5294 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0