version conflict while using efficientnet code

[shubhaminnani]

version conflict while using efficientnet code

[hasibzunair]

Check the variable type that is going in preprocess_input. It should be a numpy array of rank 3 or 4. You can try this:

print(type(img))
print(img.dim)

[qubvel]

HI @shubhaminnani
Code have been tested with

1. tf 1.14 (cpu) + keras 2.2.4
2. tf.keras 1.14 (cpu)
3. tf 1.12 (gpu) + keras 2.2.4

What kind of error do you have? Could you provide a traceback?

[shubhaminnani]

Not in efficientnet but while training the code.

[shubhaminnani]

img = preprocess_input(img)

File "/home/gpu3/anaconda3/envs/shubham/lib/python3.6/site-packages/efficientnet/preprocessing.py", line 56, in preprocess_input
assert x.ndim in (3, 4)

AttributeError: 'Tensor' object has no attribute 'ndim'