The comments on the SqueezeNet models indicate that the .caffemodel files include the training data. The deploy.caffemodel files' weights and biases are 0.0. Is this intentional? It wasn't evident from the comments. I see the squeezenet_v1.1.caffemodel does have non-zero weights and biases.
The comments on the SqueezeNet models indicate that the .caffemodel files include the training data. The deploy.caffemodel files' weights and biases are 0.0. Is this intentional? It wasn't evident from the comments. I see the squeezenet_v1.1.caffemodel does have non-zero weights and biases.
Look at any of the parameter data