Tensorflow 如何为模型预测输入正确重塑图像数组

Question

I have trained model and I am trying to test it

import tensorflow as tf
import os
import cv2
import matplotlib.pyplot as plt
import numpy as np


# Some paths

paths = {
    "cats": "data\\images\\cats",
    "dogs": "data\\images\\dogs",
    "img": "data\\images"
}

label_to_index = {
    "cat": 0,
    "dog": 1
}

index_to_label = {
    0: "cat",
    1: "dog"
}

animals = {
    "cats_labels": [label_to_index["cat"] for _ in range(len(paths["cats"]))],
    "dogs_labels": [label_to_index["dog"] for _ in range(len(paths["dogs"]))],
    "cats": [os.path.join(paths["cats"], img) for img in os.listdir(paths["cats"])],
    "dogs": [os.path.join(paths["dogs"], img) for img in os.listdir(paths["dogs"])],
}

# Load model
model = tf.keras.models.load_model('models/cats_dogs_model_1.h5')

# Load one image for test
img = cv2.imread(animals['cats'][0])

# Predictions input needs to be an array
test_img = [img]

# (1) mobilenetv2_1.00_192_input expected to have 4 dimensions, image now has 3 dims ->
# -> add new dim
test_img = [np.expand_dims(img, axis=0) for img in test_img]
print("Shape is ", test_img[0].shape)               # New Shape is  (1, 375, 500, 3) , was (375, 500, 3) 
print("Number if dimentions is ", test_img[0].ndim) # New Number if dimentions is  4 , was 3

# (2) ValueError: Error when checking input: expected mobilenetv2_1.00_192_input
# to have shape (192, 192, 3) but got array with shape (375, 500, 3)
# in the next line I am trying to reshape image for necessary sizes:
# test_img = [np.reshape(img, (192, 192)) for img in test_img]
# but if I uncomment it new error will be raised:
# ValueError: cannot reshape array of size 562500 into shape (192,192)

predictions = model.predict(test_img) # !!! error raises here
plt.imshow(test_img[0])
label = np.argmax(predictions)
plt.title(label)
plt.show()

But I encounter errors all the time I am trying to make image shape and dims valid for model.predict input, so I am stuck at this moment without understanding how to reshape my image properly. I hope anybody could explain me what is wrong with my image transormation, because this part is a black box for me now.

Errors I encounter:

1. (1) Error about dimentions - I added fourth dim, and everything is ok for now, then
2. (2) Error about invalid input image shape

Answer 1

Reshape is not you are looking for, reshape only rearranges the dimensions and changes values across dimensions, but never generates new values to fit a required size. What you want to resize the images. TensorFlow has a convenient function to resize a batch of images:

import tensorflow as tf

# ... 

model = tf.keras.models.load_model('models/cats_dogs_model_1.h5')

img = cv2.imread(animals['cats'][0])

test_img = [img]
test_img = [np.expand_dims(img, axis=0) for img in test_img]

# It is better to have a single tensor instead of a list of tensors, therefore,
# before resizing the images concatenate all them in a tensor
test_img = tf.concat(test_img, axis=0)
test_img = tf.image.resize(test_img, [192, 192])

Answer 2

np.reshape cannot resize an image. It's used to, you guessed it, reshape an array to another shape without changing the number of elements it contains. For instance, you can reshape a (20, 50) array into a (20, 5, 10) array because 20x50=20x5x10, but you can't reshape a (375, 500, 3) image into a (192, 192, 3) image.

Instead, you should use the resize method from PIL.Image ( https://www.google.com/amp/s/www.geeksforgeeks.org/python-pil-image-resize-method/amp/ )