Hfrxdjt

I am trying to run a Transfer Learning Code from Github Section 9. Transfer learning for large image classification. I have gotten the original code to work with the flower dataset and inception v3. I want to try a different dataset being the MNIST Dataset. However I am running into an error of having too many indices for array. The error comes from this line of code in 9.4

from random import sample

def prepare_batch(flower_paths_and_classes, batch_size):
 batch_paths_and_classes = sample(flower_paths_and_classes, batch_size)
 >>> images = [mpimg.imread(path)[:, :, :channels] for path, labels in batch_paths_and_classes]
 prepared_images = [prepare_image(image) for image in images]
 X_batch = 2 * np.stack(prepared_images) - 1 # Inception expects colors ranging from -1 to 1
 y_batch = np.array([labels for path, labels in batch_paths_and_classes], dtype=np.int32)
 return X_batch, y_batch

I am still very new at tensorflow and python in general and am having a hard time understanding the line of code images = [mpimg.imread(path)[:, :, :channels] for path, labels in batch_paths_and_classes] When messing around with the [:, :, :channels] I notice when deleting the :classes this part of the code runs, however it does not match the required (?, 299, 299, 3) input for Inception v3. I understand that MNIST data is (?, 28,28). How would I be able to add the 3 channels to the dataset to work in the pre trained model? Would I need to use a .reshape method or cv2? I am unsure how to tackle this situation. Any advice would be great!