---
tags:
- biology
- pytorch
metrics:
- accuracy
pipeline_tag: image-classification
datasets:
- huggan/inat_butterflies_top10k
language:
- en
---
Butterfly image classification model that use pre-trained cnn model resnet18 and fine-tuned the last fully connected layer to classify 75 categories of butterfly species.

The model used the best checkpoint with 90% test accuracy. 

The model constructed on Pytorch environment.

# Training and testing result:

Epoch: 28 Train Loss: 0.17 Train Accuracy: 0.96 Test Accuracy: 0.90

# To use this model you have to:

1. download this model
2. load pretrained model resnet18
3. model_for_predict = models.resnet18(pretrained=True)
4. load checkpoint from your local
5. checkpoint = torch.load('pytorch_model.bin')
7. model_for_predict.load_state_dict(checkpoint)
8. predict the images
9. model_for_predict.eval())


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65bdde53259bc6caeb094e85/b__Bo6f-R0el__5yqusRc.jpeg)