Noah_1992

Results 2 comments of Noah_1992

tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_1' (op: 'MaxPool') with input shapes: [?,1,112,128].

It works, but another error happened: Using Theano backend. (Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0) (Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0) (Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0) (Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0) (Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0) (Subtensor{int64}.0,...

tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_1' (op: 'MaxPool') with input shapes: [?,1,112,128].

i have read the keras's topology.py code, it say that only no parms use provided weight shape, but the model is download from offcial.what i miss?