NSTiwari/YOLOv3-to-TensorFlow-Lite-Conversion

Issue while running test_tflite.py

Opened this issue · 0 comments

While running test_tflite.py, I am encountering this error:

2022-08-10 15:49:49.506528: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
[{'name': 'output_boxes', 'index': 407, 'shape': array([ 1, 10647, 85], dtype=int32), 'shape_signature': array([ 1, 10647, 85], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}]

/content/tensorflow-yolo-v3/test_tflite.py:17: RuntimeWarning: invalid value encountered in greater_equal
pos = np.where(box_class_scores >= confidence)
Traceback (most recent call last):
File "/content/tensorflow-yolo-v3/test_tflite.py", line 162, in
draw_boxes(boxes, classes, scores, img, class_names, (height, width), True)
File "/content/tensorflow-yolo-v3/test_tflite.py", line 107, in draw_boxes
for box, score, cls in zip((boxes), (scores), (classes)):
TypeError: zip argument #1 must support iteration

Kindly let me know how to fix it,