Closed MicheleCancilla closed 3 years ago
Here it is important to decide which layers are going to be the output of the network. If you remove the softmax but still pretend to build it with some loss and metrics associated... it has non sense
Let me work on this and i will provide a way of doing
Check 3_onnx_import_net_from_file.cpp in develop branch
Describe the bug Removing the last layer of Net causes vector subscript out of range debug assertion error in debug on Visual Studio. The error occurs on net_build.cpp: https://github.com/deephealthproject/eddl/blob/6759e7976f045e3cd10e43a3f23a9be8e4880562/src/net/net_build.cpp#L61
The last layer apparently has empty child vector, so
layers[j]->child[0]
causes out of range error.To Reproduce Steps to reproduce the behavior:
onnx_export
to create the "trained_model.onnx" file3_onnx_import_net_from_file.cpp
adding the removeLayer of last softmax:onnx_import