lencm

This problem can occur with the engine file provided by the author, and can be solved using your own engine file.

> I have uploaded this 'libmyplugins.so' file, please test again. 我也遇到了这个问题，libmyplugins.so已经下载了，路径也没问题，不知道是不是环境哪里有问题呢？

> I have uploaded this 'libmyplugins.so' file, please test again. 环境为Ubuntu18.04 with CUDA 10.2 and cuDNN 8.0.0 TensorRT jetpack自带 PyTorch 1.8.0 and TorchVision 0.9.0 OpenCV-Python 4.5 pycuda 2019.1

> 嗯嗯，使用自己生成的文件后跑通了。目前只能用CPU跑，速度在0.5fps，用CUDA的话会报错，单独测试cuda没问题，重装了pytorch还是不行。不知道哪里有问题 Traceback (most recent call last): File "demo_trt.py", line 60, in detect(video_path, engine_file_path) File "demo_trt.py", line 31, in detect bboxes = detector.detect(img) File "/home/nvidia/yolov5_deepsort_tensorrt/detector_trt.py", line 120, in detect results_trt=...

> > > I have uploaded this 'libmyplugins.so' file, please test again. > > > > > > 环境为Ubuntu18.04 with CUDA 10.2 and cuDNN 8.0.0 TensorRT jetpack自带 PyTorch 1.8.0 and...

> > > > I have uploaded this 'libmyplugins.so' file, please test again. > > > > > > > > > 环境为Ubuntu18.04 with CUDA 10.2 and cuDNN 8.0.0 TensorRT...

你有自己尝试基于自己的数据集训练minigpt4吗，我制作了一些数据集只进行了stage2，感觉没有效果