_get_batches_of_transformed_samples(self, index_array)

[SumanthMeenan]

ValueError: could not broadcast input array from shape (1048576,7) into shape (1024,1024,3) I'm getting error at batch_x[i] = x broadcasting. My images and masks both are going into _get_batches_of_transformed_samples(self, index_array).

batch_x = np.zeros((len(index_array),) + self.image_shape, dtype=self.dtype) batch_x is empty zeros based on image size, My mask size array is (1024*1024,7) batch_X is (1024,1024,3)

I used train_data_generator in model.fit_generator()

train_data_generator() is zip(train_image_generator, train_mask_generator I used different image datagenerators for mask and images

[Dref360]

Hi, We could work on this better if you could provide a standalone reproducible example. Some advices:

• Don't use custom data or custom paths.
• Use random arrays or even np.ones, np.zeros.
• The example should run with Keras (and deps) alone.
• Should be Python3 compatible.
• Should not be OS specific.
• The file should reproduce the bug with *high fidelity.
• Link to a gist would be appreciated.

Thanks! Dref360