Hi i’ve done training and export my object detector model to onnx format, but after run prediciton i got an error:
Traceback (most recent call last):
File "run_ssd_live_caffe2.py", line 85, in <module>
confidences, boxes = predictor.run({'0': image})
RuntimeError: [enforce fail at ..\caffe2\predictor\predictor.cc:12] blob. Blob does not exist: 0
this is my code inside opencv loop
image = cv2.cvtColor(orig_image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, (300, 300))
image = image.astype(np.float32)
image = (image - 127) / 128
image = np.transpose(image, [2, 0, 1])
image = np.expand_dims(image, axis=0)
timer.start()
confidences, boxes = predictor.run({'0': image})