Symbadian
commented
3 years ago Hey Li,
I solved it pal, change the following in your code it is causing some issues on the 3dcnn.py file in the model section! I am running spyder 5.0.0 whilst researching I found the solution here at the very bottom: https://stackoverflow.com/questions/49079115/valueerror-negative-dimension-size-caused-by-subtracting-2-from-1-for-max-pool
Change the max pooling to this and edit all of the section in the model with the padding to padding='same': """ model.add(MaxPooling3D(pool_size=(3, 3, 3), padding='same'))''''
apparently, the images are gradually getting smaller making it challenging for the convolution processing to occur! let me know when you made the amendments I will select the start ratings!
paolo626
Hi Liupeng,
I tried reaching out to you via your email but no luck in catching your attention!!
I have been receiving these errors for which I cannot seem to evade as this is challenging my understanding!
I really would like to solve this as your code is very interesting! Can you help me solve this, please?
I googled and saw this response but when I tried implementing this, it is still futile! https://stackoverflow.com/questions/45645276/negative-dimension-size-caused-by-subtracting-3-from-1-for-conv2d-2-convolution
WHAT I TRIED: ''' expects the input to be in the format (samples, rows, cols, channels), which is "channels-last". Your data seems to be in the format (samples, channels, rows, cols). You should be able to fix this using the optional keyword data_format = 'channels_first' when declaring the Convolution2D layer
model.add(Convolution2D(32, (3, 3), activation='relu', input_shape=(1,28,28), data_format='channels_first'))
They also mention removing some of the convolution layers but I think in my limited knowledge that this will have an adverse effect on the accuracy and metrics!???!?! I could be wrong here! Please assist? Something seems off with the Max Pooling Layer '''
My ERRORS: ValueError: Negative dimension size caused by subtracting 3 from 1 for '{{node conv3d_2/Conv3D}} = Conv3D[T=DT_FLOAT, data_format="NDHWC", dilations=[1, 1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1, 1]](Placeholder, conv3d_2/Conv3D/ReadVariableOp)' with input shapes: [?,9,9,1,32], [3,3,3,32,64].