|
--- |
|
license: apache-2.0 |
|
library_name: transformers |
|
pipeline_tag: image-classification |
|
--- |
|
# body_complexion |
|
|
|
This is a fine-tuned [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) model. Dataset with men of |
|
different bode complexion was used for fine-tuning. |
|
|
|
### Intended Use: |
|
The model is intended for image classification tasks specifically related to men's body types. It is designed to classify images into four categories based on body complexion: skinny, ordinary, overweight, and very muscular. The model can be utilized in applications such as: |
|
|
|
- Health and fitness platforms for body type analysis |
|
- Clothing recommendation systems tailored for different body types |
|
- Visual content moderation systems to filter images based on body type |
|
|
|
### Launch |
|
```python |
|
import torch |
|
from PIL import Image |
|
from transformers import ResNetForImageClassification, AutoImageProcessor |
|
|
|
processor = AutoImageProcessor.from_pretrained('glazzova/body_complexion') |
|
model = ResNetForImageClassification.from_pretrained('glazzova/body_complexion') |
|
image = Image.open('your_pic.jpeg') |
|
inputs = processor(image, return_tensors="pt") |
|
|
|
with torch.no_grad(): |
|
logits = model(**inputs).logits |
|
|
|
# model predicts one of the 4 classes |
|
predicted_label = logits.argmax(-1).item() |
|
print(model.config.id2label[predicted_label]) |
|
|