both new and old weights don't load

[jcpeterson]

Using keras 2.2.0. I tried both the new and old weights in the main 28-8 script, and neither load correctly.

ValueError: Layer #0 (named "conv2d_1" in the current model) was found to correspond to layer convolution2d_29 in the save file. However the new layer conv2d_1 expects 1 weights, but the saved weights have 2 elements.

The keras contrib version of this code does load the new weights, but the accuracy on the test set is around 30%. Am I missing something?

[FrancescoCrecchi]

Indeed! Knowing the exact Keras version you used in your experiments would help a lot! Any chance for this?

[titu1994]

I don't precisely remember, but it's most definitely Keras 1.x later releases.

[persistz]

Keras 2.1.3 has the same problem, both on 28-8 and 16-8 model.