SVHNClassifier-PyTorch
SVHNClassifier-PyTorch copied to clipboard
potterhsu
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)
when i traning by using the Learning Rate 0.16,the loss will increase to nan.
Hi, I am using this classifier to recognize square images containing numbers. In most cases this classifier performs very well but when there are no numbers in the image, it...
Is the maximum number of digits recognized by this model 5?
Hi, I have no powerful machine to train SVHNClassifier. Can I have a trained SVHNClassifier (model-100.tar)?
After reviewing the mentioned paper in section 5.1: > The fully connected layers contain 3,072 units each And your other version of this repository written in tensorflow: https://github.com/potterhsu/SVHNClassifier/blob/475fb68fde1fa1c057cc301ef0af049d9b9c4afb/model.py#L72 Is it...
Thank you for your efforts in making this available. On issuing: python train.py --data_dir ./data --logdir ./logs I get the error: AssertionError: Torch not compiled with CUDA enabled I then...
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...
Hi! Did you compare the speed of default torchvision dataset https://pypi.python.org/pypi/torchvision/0.1.8#svhn and your LMDB version?
