Open andresdigiovanni opened 4 years ago
mee too bro, need help!
I tried implementing your fixes @tackoo for my data of 1600 rows 103 columns. I've tried training the data earlier with Conv1D in a sequential model with input (103,1) but when I try to use this inpus shape for this ResNet model I get this error:
ValueError: Input 0 of layer conv1 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: (None, 103, 1)
When load a model
`
save model
`
I get this error:
_Shape must be rank 3 but is rank 4 for 'padding_conv12/Pad'