Hi, I am trying to use train_and_test_unet.ipynb to replicate the training process but I got an error when I run
model.fit_generator(trainGen,
steps_per_epoch=500,
epochs=1,
callbacks=[model_checkpoint],
validation_data = validGen,
validation_steps = 5)
The error is below
Found 0 images belonging to 1 classes.
Found 0 images belonging to 1 classes.
Found 0 images belonging to 1 classes.
Found 0 images belonging to 1 classes.
Epoch 1/1
ValueError Traceback (most recent call last)
in ()
10 callbacks=[model_checkpoint],
11 validation_data = validGen,
---> 12 validation_steps = 5)
12 frames
<__array_function__ internals> in amax(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/numpy/core/fromnumeric.py in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs)
88 return reduction(axis=axis, out=out, **passkwargs)
89
---> 90 return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
91
92
ValueError: zero-size array to reduction operation maximum which has no identity
Is it because the dataGenerate is empty so that there is no image there?
Many thanks for your help!
zz636
commented
4 years ago
Hi, I am trying to use train_and_test_unet.ipynb to replicate the training process but I got an error when I run
model.fit_generator(trainGen, steps_per_epoch=500, epochs=1, callbacks=[model_checkpoint], validation_data = validGen, validation_steps = 5) The error is below Found 0 images belonging to 1 classes. Found 0 images belonging to 1 classes. Found 0 images belonging to 1 classes. Found 0 images belonging to 1 classes. Epoch 1/1
ValueError Traceback (most recent call last)