Network Architecture is wrong

[kevinchristensen1]

I was able to solve this issue by changing the Reshape args for last layers of the model.
Instead of the current model definition in unet.py (notice the input_shape arg for the Keras Reshape):



reshape = Reshape((self.img_rows * self.img_cols, 12), input_shape=(self.img_rows, self.img_cols, 12))(conv9)

print("reshape shape:", reshape.shape)



# permute = Permute((2, 1))(reshape)

# print("permute shape:", permute.shape)



activation = Activation('softmax')(reshape)


After 10 epochs I got this result:

Originally posted by @shabtayor in #1 (comment)

[shangmou]

I was able to solve this issue by changing the Reshape args for last layers of the model.
Instead of the current model definition in unet.py (notice the input_shape arg for the Keras Reshape):


reshape = Reshape((self.img_rows * self.img_cols, 12), input_shape=(self.img_rows, self.img_cols, 12))(conv9)

print("reshape shape:", reshape.shape)



permute = Permute((2, 1))(reshape)


print("permute shape:", permute.shape)



activation = Activation('softmax')(reshape)


After 10 epochs I got this result:

Originally posted by @shabtayor in #1 (comment)

Hello, may I ask if this set of code can be provided ?