newforrestgump001
newforrestgump001
in ubuntu18.04 it is built and works.
the shell to reproduce the issue: 1、python tools/infer.py --config configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml -o weights=mask_rcnn_r50_1x_coco.pdparams --infer_img=demo/000000014439_640x640.jpg 2 、python deploy/python/infer.py --config configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml -o weights=output_inference3/mask_rcnn_r50_1x_coco/model --infer_img=demo/000000014439_640x640.jpg 3、./vision_detection_paddledetection_infer_mask_rcnn output_inference3/mask_rcnn_r50_1x_coco demo/000000014439_640x640.jpg 1 step 1 and 2 get...
gpu 挺快的，有问题可以一起讨论。
链接: https://pan.baidu.com/s/1pfnonWjCKXmCsMfbUl88Ww 密码: g8aj --来自百度网盘超级会员V8的分享
请问这样直接分享可以吗 我还在Linux上，随后我再加群，多谢您！
推理报错，报错的地方在[02/23/2023-19:18:43] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.1.0 [02/23/2023-19:18:43] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.1.0...
还没有测试。同样的训练代码和同样的推理代码，类别数都为2，一个关键点个数为4，一个关键带你个数为2，前者可以，后者报错，我现在测试一下onnxruntime.
四个关键点的模型参数为：[info][simple_yolo.cu:2281]:Input shape is 1 x 3 x 1024 x 1024 [info][simple_yolo.cu:2283]:Set max workspace size = 1024.00 MB [info][simple_yolo.cu:2286]:Network has 1 inputs: [info][simple_yolo.cu:2292]: 0.[images] shape is 1 x 3 x 1024...
两类关键点的模型参数为[info][simple_yolo.cu:2281]:Input shape is 1 x 3 x 1024 x 1024 [info][simple_yolo.cu:2283]:Set max workspace size = 1024.00 MB [info][simple_yolo.cu:2286]:Network has 1 inputs: [info][simple_yolo.cu:2292]: 0.[images] shape is 1 x 3 x 1024...