An IPython notebook demonstrating the process of Transfer Learning using pre-trained Convolutional Neural Networks with Keras on the popular CIFAR-10 Image Classification dataset.
I came across your cifar-10 example. It is really good for understanding transfer learning concepts but I have a query, why haven't you normalized your image array. Would this not lead to any problems.
in the part of Visualizing the Inception V3 bottleneck features using T-SNE dimensionality reduction
i get the error :
ValueError: 'c' argument has 50000 elements, which is not acceptable for use with 'x' with size 10000, 'y' with size 10000.
HELP please!