SoulPerforms/Butterfly_image_classification_resnet18

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