torch2trt

torch2trt copied to clipboard

CUDA out of memory

3

Hi, there. I see many people talked about this problem, so is there any solutions? many thanks! ``` Traceback (most recent call last): File "model2trt.py", line 134, in tokenizer, eod_id,...

Biaocsu

Traceback (most recent call last): File "convert.py", line 52, in info(opt) File "convert.py", line 18, in info result = text_recogn.predict(opt,img_path) File "/home/kc/Desktop/torch2trt/lib/helpers2.py", line 99, in predict model_trt = torch2trt(model, [img],...

YasinTURKMENOGLU

Update `torch2trt` to use dynamic batch sizes up to the size given during conversion

3

Creating an issue to track the TODOs for this task: We need to update `torch2trt` to support dynamic batch sizes, up to the size given during conversion. During first compilation...

chaoz-dev

python setup.py install --plugins compile error

7

Receiving a compile error when attempting ```python setup.py install --plugins``` Will track down and add further detail but wanted to add the issue here. ``` C:\Users\vroom\Documents\Bitbucket\torch2trt\torch2trt\plugins\interpolate.cpp(186): error C2440: 'initializing': cannot...

kvrooman

hello, now i build to generate torch2trt_plugins.dll and torch2trt_plugins.lib through CMakeLists.txt, but can i ask how i use torch2trt plugins in python? Thanks.

sunshinesjw1

the following test would be failed in some cases: ```python python3 -m torch2trt.test --name=group ``` ``` TypeError: add_plugin_v2(): incompatible function arguments. The following argument types are supported: 1. (self: tensorrt.tensorrt.INetworkDefinition,...

tp-nan

Seems like trt module will decrease input data`s dimension to 4D.

1

Fuzhiyuan

'NoneType' object has no attribute 'create_execution_context'

3

File "ai_py/test/test_pose_detect.py", line 67, in test(img_list, folder) File "ai_py/test/test_pose_detect.py", line 32, in test pos_detector = PoseDetector(PiP_IMAGE_DIM, PiP_MODEL_PATH, PiP_POSE_FILE) File "/home/zitong.wang1/pip/ai_py/worker/PoseDetector.py", line 40, in __init__ self.model_trt.load_state_dict(torch.load(self.optimized_model)) File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1468, in...

wang-TJ-20

How to handle multiple inputs？

1

I am now doing multi-sensor fusion, and the input has many different types of pictures. So how should I do it to make the code support multiple inputs? I look...

wangchangquan

from torch2trt.module_test import add_module_test ModuleNotFoundError: No module named 'torch2trt.module_test'

1

Dear experts: I'm trying to follow your Alexnet example. I get the following error: from torch2trt import torch2trt File "/usr/local/lib/python3.8/dist-packages/torch2trt/torch2trt/__init__.py", line 2, in from .converters import * File "/usr/local/lib/python3.8/dist-packages/torch2trt/torch2trt/converters/__init__.py", line...

KatBendtz