在使用YOLOv5(6.0版本)时,运行export.py,尝试将pytorch训练pt模型转换成Tensorflow支持tflite模型,然而遇到报错: TensorFlow saved_model: export failure: can’t convert cuda:0 device type tensor to numpy. 对于此类问题,作者在issue中的统一回答是:新版本已解决了该问题,请使用新版本。
Sign in Sign up pytorch / pytorch Public Notifications Fork 23.2k Star 86.2k Code Issues 5k+ Pull requests 1.1k Actions Projects 12 Wiki Security 1 Insights Assign User on Comment DISABLED test_pre_dispatch_export_scan_simple_cuda_float32 (__main__.TestHOPCUDA) #139553 Sign i...
Test name: test_pre_dispatch_export_scan_simple_cuda_float32 (__main__.TestHOPCUDA) Platforms for which to skip the test: linux, slow Disabled by pytorch-bot[bot] Within ~15 minutes, test_pre_dispatch_export_scan_simple_cuda_float32 (__main__.TestHOPCUDA) will be disabled in PyTorch...
python3 onnx_export.py --model-dir=models/model01/ --labels=models/model01/labels.txt Traceback (most recent call last): File “onnx_export.py”, line 9, in from vision.ssd.vgg_ssd import create_vgg_ssd File “/home/anupriya/jetson-inference/python/training/detection/ssd/vision/ssd/v...
CUDA Version: 10.2 CUDNN Version: 7.6.5 Operating System + Version: ubuntu 18 Python Version (if applicable): 3.6 TensorFlow Version (if applicable): no PyTorch Version (if applicable): 1.6 (1.2 tested too) Baremetal or Container (if container which image + tag): no ...
edited by pytorch-botbot 🐛 Describe the bug The exported model failed to do inference on cuda. importtorchep=torch.export.load('retina.pt2')gm=ep.module()gm(torch.rand(1,3,800,1216))# successgm=ep.module().cuda()gm(torch.rand(1,3,800,1216).cuda())# failed ...
Click on the Test step of the job so that it is expanded. Otherwise, the grepping will not work. Grep fortest_serialize_export_cond_simple_cuda_float32 There should be several instances run (as flaky tests are rerun in CI) from which you can study the logs. ...
Pytorch :1.3.0 Detectron2 :0.1.1 CUDA :10.0 Python :3.6.9 JetPack version :4.3 cuDNN version :7.6.3 cmake version :3.10.2 onnxruntime-gpu-tensorrt :1.0.0 AastaLLL2020 年5 月 18 日 03:503 Hi, Do you have any dependencies on JetPack4.3?
Tensors and Dynamic neural networks in Python with strong GPU acceleration - DISABLED test_retrace_export_while_loop_simple_cuda_float32 (__main__.TestHOPCUDA) · pytorch/pytorch@bad6904
Tensors and Dynamic neural networks in Python with strong GPU acceleration - DISABLED test_retrace_export_cond_simple_cuda_float32 (__main__.TestHOPCUDA) · pytorch/pytorch@4db199f