rs(interpreter.get_tensor(output_details[2]['index']))]
#output_data = interpreter.get_tensor(output_details[0]['index'])
print('output_data shape is ', output_data.shape)
print('output data is ', output_data)
#results = np.squeeze(output_data)
#top_k = results.argsort()[-5:][::-1]
#print('top_k = ', top_k)
labels = load_labels(args.label_file)
print(labels)
yolo = YOLO(0.6, 0.5)
boxes, classes, scores = yolo.predict(input_data, image.size, outs = output_data)
#print(boxes)
if boxes is not None:
draw(image, boxes, scores, classes, labels)
image = image.save('detected.jpg')
'''
for i in top_k:
if floating_model:
print('i=', i)
print('reslut[i] = ', results[i])
print('labels[i] = ', labels[i])
#print('{:08.6f}: {}'.format(float(results[i]), labels[i]))
dictionary = {
"front": 0,
"front-side": 1,
"rear": 2,
"rear-side": 3,
"side": 4
}
x_train = []
y_train = []
for folder in folders:
images = os.listdir(path + "\\" + folder)
for image in images:
im_path = path + "\\" + folder + "\\" + image
image = cv2.imread(im_path)
pimage = process_image(image)
boxes, classes, scores = yolo.predict(pimage, image.shape)
#det_image = detect_image(image, yolo, all_classes)
# cv2.imshow("detected", det_image)
if classes is None:
print(im_path)
continue
S = 0
maxBox = []
if boxes is None:
print(im_path)
continue
for box in boxes:
x, y, w, h = box
if w * h > S: