search

potterhsu / SVHNClassifier-PyTorch

A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)
MIT License
198 stars 45 forks source link

Issue evaluating #4

Open jake-shomer opened 6 years ago

jake-shomer commented 6 years ago

The model's evaluation accuracy maintains 0.00% throughout the entire training process. The model's loss decreases significantly but when evaluating on the validation set it returns 0% accuracy. No code was modified to perform training. Any idea of what the issue may be?

muety commented 5 years ago

I got the same problem. Any solutions?

potterhsu commented 5 years ago

If you’re using Python 2, try to replace with float(len(self._loader.dataset)) at evaluator.py #47, or you could check the value of num_corrects