ObjectDetection exception: int() argument must be a string, a bytes-like object or a number, not 'NoneType' about imageai HOT 5 CLOSED

Hello, did you ensure you downloaded the correct model file, set the correct model type and set the correct model path to the model file you downloaded? Ensure all of this is done before running your python code.

from imageai.

This is python code, resnet50_coco_best_v2.0.1.h5 model file in models folder

from imageai.Detection import ObjectDetection
import os

execution_path = os.getcwd()

detector = ObjectDetection()
detector.setModelTypeAsRetinaNet()
model_path = os.path.join(execution_path, "models\resnet50_coco_best_v2.0.1.h5")
print("model path : {}".format(model_path))

detector.setModelPath(model_path)

img_path = os.path.join(execution_path, "image\5.jpg")
print("img path : {}".format(img_path))

detector.loadModel()

detections = detector.detectObjectsFromImage(input_image=img_path,
output_image_path=os.path.join(execution_path, "image2new.jpg"))

for eachObject in detections:
print(eachObject["name"] + " : " + eachObject["percentage_probability"])
print("--------------------------------")``

from imageai.

Please see discussion here #30

from imageai.

ok,thanks

from imageai.

i got this type of error anyone knows how to solve please tell me i searching about it's solution lasst 3 days , i applied all things but it didn't solved

TypeError Traceback (most recent call last)
in ()
83 (boxes, scores, classes, num) = sess.run(
84 [detection_boxes, detection_scores, detection_classes, num_detections],
---> 85 feed_dict={image_tensor: frame_expanded})
86
87 # Draw the results of the detection (aka 'visulaize the results')

2 frames
/usr/local/lib/python3.6/dist-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
83
84 """
---> 85 return array(a, dtype, copy=False, order=order)
86
87

TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'

from imageai.