Replies: 1 comment
-
This is not the right repo for this question, we do not use ONNX. Try asking in https://github.com/nvidia/tensorrt |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I have got below memory error , how to solve that
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:10: DeprecationWarning: Use get_tensor_name instead.
print(engine.get_binding_index("input"))
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:11: DeprecationWarning: Use get_tensor_name instead.
context.set_binding_shape(engine.get_binding_index("input"), (1, 3, image_height, image_width))
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:11: DeprecationWarning: Use set_input_shape instead.
context.set_binding_shape(engine.get_binding_index("input"), (1, 3, image_height, image_width))
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:16: DeprecationWarning: Use get_tensor_name instead.
binding_idx = engine.get_binding_index(binding)
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:17: DeprecationWarning: Use get_tensor_shape instead.
print("binding size",context.get_binding_shape(binding_idx))
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:18: DeprecationWarning: Use get_tensor_shape instead.
size = trt.volume(context.get_binding_shape(binding_idx))
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:19: DeprecationWarning: Use get_tensor_dtype instead.
dtype = trt.nptype(engine.get_binding_dtype(binding))
C:\Users\gj\AppData\Local\Temp\ipykernel_11580\158248581.py:21: DeprecationWarning: Use get_tensor_mode instead.
if engine.binding_is_input(binding):
LogicError Traceback (most recent call last)
Cell In[6], line 3
1 print("Running TensorRT inference for FCN-ResNet101")
2 with load_engine(engine_file) as engine:
----> 3 infer(engine, input_file, output_file)
Cell In[4], line 46, in infer(engine, input_file, output_file)
44 print(output_memory)
45 # Synchronize the stream
---> 46 stream.synchronize()
49 img =postprocess(np.reshape(output_buffer, (image_height, image_width)))
51 print("Writing output image to file {}".format(output_file))
LogicError: cuStreamSynchronize failed: an illegal memory access was encountered
what would bethe problem
Beta Was this translation helpful? Give feedback.
All reactions