ValueError：尺寸必须相等，但对于具有输入形状的“mul_18”（操作：“Mul”）为 2 和 80：[?,?,?,5,2], [?,?,?,5,80]

Question

I am trying to detect objects in an using in Yolo in google collab. Here is the piece of code I am executing but getting value error. Looking for help, Stuck here for more than a week.

img = plt.imread('/content/drive/My Drive/Social_distance/img.jpg')
imshow(img)
image_shape = float(img.shape[0]), float(img.shape[1])
print(image_shape)
scores, boxes, classes = yolo_eval(yolo_outputs, image_shape=(720,1280))

definition of yolo_eval()

def yolo_eval(yolo_outputs, image_shape = (720., 1280.), max_boxes=10, score_threshold=.6, iou_threshold=.5):
   print(image_shape)
   box_confidence, box_xy, box_wh, box_class_probs = yolo_outputs
   boxes = yolo_boxes_to_corners(box_xy, box_wh)
   scores, boxes, classes = yolo_filter_boxes(box_confidence, boxes, box_class_probs, threshold = 
   score_threshold)
   boxes = scale_boxes(boxes, image_shape)
   scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold)

   return scores, boxes, classes

Here is the error:

   1606   try:
  -> 1607     c_op = c_api.TF_FinishOperation(op_desc)
   1608   except errors.InvalidArgumentError as e:

  InvalidArgumentError: Dimensions must be equal, but are 2 and 80 for 
  'mul_19' (op: 'Mul') with input shapes: [?,?,?,5,2], [?,?,?,5,80].

  During handling of the above exception, another exception occurred:

  ValueError                                Traceback (most recent call last)
  11 frames
  /tensorflow-1.15.2/python3.6/tensorflow_core/python/framework/ops.py in 
  _create_c_op(graph, node_def, inputs, control_inputs)
  1608   except errors.InvalidArgumentError as e:
  1609     # Convert to ValueError for backwards compatibility.
  -> 1610     raise ValueError(str(e))
   1611 
  1612   return c_op

  ValueError: Dimensions must be equal, but are 2 and 80 for 'mul_19' (op: 
  'Mul') with input shapes: [?,?,?,5,2], [?,?,?,5,80].

Answer 1

I suspect that the problem comes from the yolo_filter_boxes() . Try doing something like this:

final_yolo_outputs = (yolo_outputs[2], yolo_outputs[0], yolo_outputs[1], yolo_outputs[3])

And then,

scores, boxes, classes = yolo_eval(final_yolo_outputs , image_shape=(720,1280))

It would be good if you could provide the definition of the functions used as well, as suggested above.