Ошибка шины при использовании tenorflow в Raspberry Pi 3 - PullRequest
Новая
       19

Ошибка шины при использовании tenorflow в Raspberry Pi 3

0 голосов
/ 15 октября 2019

Я хочу сделать распознавание жестов с помощью TensorFlow в Raspberry pi 3.

Я пробовал таким образом. 

import tensorflow as tf
import numpy as np
import io, time
import cv2

cap = cv2.VideoCapture(-1)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 720)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)

img_num = 0

while(True):
    ret, frame = cap.read()

    cv2.imshow('frame', frame)

    if(cv2.waitKey(1) & 0xFF == ord('x')):
        print("X\n")
        break
    elif(cv2.waitKey(1) & 0xFF == ord('c')):
        cv2.imwrite(str(img_num) + ".jpg", frame)


        # Import the TF graph
        graph_def = tf.GraphDef()
        with tf.gfile.FastGFile("model.pb", 'rb') as f:
            graph_def.ParseFromString(f.read())
            tf.import_graph_def(graph_def, name='')

        # Create a list of labels.
        labels = []
        with open("labels.txt", 'rt') as lf:
            for l in lf:
                labels.append(l.strip())

        def oprate(image):

            def crop_center(img,cropx,cropy):
                h, w = img.shape[:2]
                startx = w//2-(cropx//2)
                starty = h//2-(cropy//2)
                return img[starty:starty+cropy, startx:startx+cropx]

            def resize_down_to_1600_max_dim(image):
                h, w = image.shape[:2]
                if (h < 1600 and w < 1600):
                    return image

                new_size = (1600 * w // h, 1600) if (h > w) else (1600, 1600 * h // w)
                return cv2.resize(image, new_size, interpolation = cv2.INTER_LINEAR)

            def resize_to_256_square(image):
                h, w = image.shape[:2]
                return cv2.resize(image, (227, 227), interpolation = cv2.INTER_LINEAR)


            # If the image has either w or h greater than 1600 we resize it down respecting
            # aspect ratio such that the largest dimension is 1600
            image = resize_down_to_1600_max_dim(image)


            # We next get the largest center square
            h, w = image.shape[:2]
            min_dim = min(w,h)
            max_square_image = crop_center(image, min_dim, min_dim)


            # Resize that square down to 256x256
            augmented_image = resize_to_256_square(max_square_image)


            # The compact models have a network size of 227x227, the model requires this size.
            # Crop the center for the specified network_input_Size
            augmented_image = crop_center(augmented_image, 227, 227)
            augmented_image = resize_to_256_square(max_square_image)



            # These names are part of the model and cannot be changed.
            output_layer = 'loss:0'
            input_node = 'Placeholder:0'

            with tf.Session() as sess:
                prob_tensor = sess.graph.get_tensor_by_name(output_layer)
                predictions, = sess.run(prob_tensor, {input_node: [augmented_image] })


                ###View the results
                # Print the highest probability label

                # Or you can print out all of the results mapping labels to probabilities.
                label_index = 0
                list_img = ""
                for p in predictions:
                    truncated_probablity = np.float64(round(p,8))
                    #list_img += labels[label_index] + ":%4f"%truncated_probablity+","
                    print (labels[label_index],":%4f "%truncated_probablity,end=" | ")
                    label_index += 1
                #list_img = (list_img.split(','))
                #print(list_img[0],list_img[4],list_img[9],list_img[15])
                highest_probability_index = np.argmax(predictions)
                print('Classified as:' + labels[highest_probability_index])
                return labels[highest_probability_index]

        ### MAIN ###
        if __name__ == '__main__':
            list_img2 = ""
            image = cv2.imread("%d.jpg"%img_num)
            list_img2 = (oprate(image)).split('_',1)
            print(list_img2[0]+"\n")

        img_num += 1

cap.release()
cv2.destroyAllWindows()

Это приводит к ошибке:

ValueError: Невозможно передать значение формы (1, 227, 227, 3) для тензора 'Заполнитель: 0', который имеет форму '(?, 224, 224, 3)'

ИтакЯ изменил (227, 227) на (224, 224) в

return cv2.resize(image, (227, 227), interpolation = cv2.INTER_LINEAR)

Но при этом я получаю ошибку.

...