Closed duduRodrigues closed 6 years ago
What model file are you passing to correct_rotation.py
? From the error message, it looks like you are using the small model trained on the MNIST dataset (which takes input images of shape 28 x 28 x 1
) instead of the ResNet50 model trained on the Google Street View dataset (which takes input images of shape 224 x 224 x 3
).
It worked!! Thanks!!!!
Hi, I am trying to run your code but I keep getting these errors:
I am using Python 3.6.3, Cuda 8, Cudnn 6 and installed all the others dependencies using pip with exception of the MarkupSafe that was with some bugs so I compiled and installed it myself. Do you have any idea of how can I fix it? I am using the following image as input (resolution of 259 x 194) for your network: