ValueError: The last dimension of the inputs to `Dense` should be defined. Found `None`.
zubairahmed-ai opened this issue · 2 comments
zubairahmed-ai commented
Summary
Receiving this error trying to Fine-tune a EfficientNetB0 using Tensorflow 2.0
Environment
- Python version: 3.6.4
- Keras version: 2.3.1
- Keras-applications version:1.0.8
- Keras backend with version:
Logs or source codes for reproduction
ValueError: The last dimension of the inputs to
Denseshould be defined. Found
None.
When fine-tuning a EfficientNetB0 with my own fully connected layer I get the above error
my import looks like this import efficientnet.tfkeras as efn
and
baseModel = efn.EfficientNetB0(weights="imagenet", include_top=False)
headModel = FCHeadNet.build(baseModel, len(classNames), 256)
But the error is shown in this line
headModel = Dense(D, activation="relu")(headModel)
zubairahmed-ai commented
Fixed
limapedro commented
How did you fixed it?