How To Fix Datatype Mismatch To Predict Images Using My Trained Model?

I trained a CNN, but I'm unable to use it to make predictions. All of my images are in a folder

model = tf.keras.models.load_model("C:\Sid\CNNs\MoonRocks.h5")
import os
filepath = "C:\Sid\Projects\LunarMoonRocks\DataSet\Test Images"

for img in os.listdir(filepath):
    img_path = os.path.join(filepath, img)
    img_array=cv2.imread(img_path, cv2.IMREAD_GRAYSCALE)
    new_array=cv2.resize(img_array, (480, 480)) 
    img_tbp = new_array.reshape(-1, 480, 480, 1)
    prediction = model.predict([img_tbp])

This code shows the error

TypeError: Value passed to parameter 'input' has DataType uint8 not in list of allowed values: float16, bfloat16, float32, float64

I tried to change the image type to float32 using

image = tf.image.decode_jpeg(img_tbp)
image = tf.cast(image, tf.float32)

But that showed the error

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int).

How do I get my model to predict the images in the folder?



decode_jpeg is used to decode the contents of image file which is read in binary format. You have already read your image file using OpenCV and OpenCV reads the file in NumPy format. Had you made use of read_file, then you should have used decode_jpeg.

Now coming to your problem, you could have converted your uint8 image to floating type either by just using tf.cast operation as you had done it, but you have most likely forgotten to normalize your image from the range of [0, 255] in uint8 to [0, 1] in float. So you could have directly converted your image to float and bring the number's value in range of [0, 1] using:

image = image / 255.0