hi guys,
i train my model for image classifier of flower dataset on colab -because it will take long time on my local machine- using pretrained model vgg19 and after train i want to save my model weights on my local machine how can i do that ?
i found this but i can’t reuse for pytorch
you can reuse the same solution for pytorch. there’s nothing about the solution that makes it specific to another framework. (you are just saving a file in a particular folder)
how can i edit this part to be proper for .pth
model_json = model.to_json()
with open("drive/app/model.json", "w") as json_file:
json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("drive/app/model_weights.h5")
print("Saved model to drive")
replace that entire snippet with:
torch.save(model.state_dict(), 'drive/app/model.pth')
3 Likes
thanks very much it works