python - wrong results when saving and loading weights/model in Keras -
i can't post code using, try explain it. first have defined few functions preprocess raw data. then, using keras have following arquitecture:
model = sequential() model.add(dense(10, input_dim=230, init='uniform',activation='sigmoid')) model.add(dense(5, init='uniform', activation='sigmoid')) model.add(dense(2, init='uniform', activation='sigmoid')) model.compile(loss='mse', optimizer='rmsprop', metrics=['binary_accuracy']) model.fit(trainx, trainy, nb_epoch=1000, batch_size=1, callbacks=[history], verbose=2)
now problem. when run code >98% accuracy, when save weights/model (following keras doc) , load them, garbage results.
i have tried loading after , before compile line, saving/loading weights/model, nothing works (i keep getting wrong results after loading them in different python session)
Comments
Post a Comment