aarohisingla / image-classification-using-efficientnets Goto Github PK

I am trying the custom code on my own image data, while fitting the model i am getting error :-
TypeError: Failed to convert elements of SparseTensor(indices=Tensor("DeserializeSparse:0", shape=(None, 2), dtype=int64), values=Tensor("DeserializeSparse:1", shape=(None,), dtype=float32), dense_shape=Tensor("stack:0", shape=(2,), dtype=int64)) to Tensor. Consider casting elements to a supported type. See https://www.tensorflow.org/api_docs/python/tf/dtypes for supported TF dtypes.

On Cusom dataset training notebook this line:

images = np.array(images)

images = images.astype('float32') / 255.0

converts images into black If input images are grayscaled.