When attempting to perform Object Detection using a pre-trained YoloV3 model, I am getting a ModuleNotFoundError. I'm attempting to detect a single class ("boat") from the 80 pre-trained classes available. My code is below (taken from the ImageAI documentation):
3 frames
/usr/local/lib/python3.8/dist-packages/torch/serialization.py in find_class(self, mod_name, name)
1122 pass
1123 mod_name = load_module_mapping.get(mod_name, mod_name)
-> 1124 return super().find_class(mod_name, name)
1125
1126 # Load the data (which may in turn use persistent_load to load tensors)
ModuleNotFoundError: No module named 'models'
All other imports were successful and I'm scratching my head as to what might be wrong. I'm working in a Colab notebook. Thanks for any help you can provide!
Good evening,
When attempting to perform Object Detection using a pre-trained YoloV3 model, I am getting a ModuleNotFoundError. I'm attempting to detect a single class ("boat") from the 80 pre-trained classes available. My code is below (taken from the ImageAI documentation):
`from imageai.Detection import ObjectDetection
detector = ObjectDetection() detector.setModelTypeAsYOLOv3() detector.setModelPath("/content/gdrive/MyDrive/shipspotting_revision/yolov3.pt") detector.loadModel() custom = detector.CustomObjects(boat=True) detections = detector.detectCustomObjectsFromImage(custom_objects=custom, input_image="/content/gdrive/MyDrive/shipspotting_revision/rostock/output/livetest/test[1463].jpg", output_image_path="/content/gdrive/MyDrive/shipspotting_revision/rostock/output/live_test/test_new.jpg")
for eachObject in detections: print(eachObject["name"] , " : ", eachObject["percentage_probability"], " : ", eachObject["box_points"] ) `
The traceback for the error I'm getting is below:
ModuleNotFoundError Traceback (most recent call last) in
4 detector.setModelTypeAsYOLOv3()
5 detector.setModelPath("/content/gdrive/MyDrive/shipspotting_revision/yolov3.pt")
----> 6 detector.loadModel()
7 custom = detector.CustomObjects(boat=True)
8 detections = detector.detectCustomObjectsFromImage(custom_objects=custom, input_image="/content/gdrive/MyDrive/shipspotting_revision/rostock/output/livetest/test[1463].jpg", output_image_path="/content/gdrive/MyDrive/shipspotting_revision/rostock/output/live_test/test_new.jpg")
3 frames /usr/local/lib/python3.8/dist-packages/torch/serialization.py in find_class(self, mod_name, name) 1122 pass 1123 mod_name = load_module_mapping.get(mod_name, mod_name) -> 1124 return super().find_class(mod_name, name) 1125 1126 # Load the data (which may in turn use
persistent_load
to load tensors)ModuleNotFoundError: No module named 'models'
All other imports were successful and I'm scratching my head as to what might be wrong. I'm working in a Colab notebook. Thanks for any help you can provide!