yolov8s-seg.wts to yolov8s-seg.engine transform error about tensorrtx HOT 5 OPEN

Have you tried the official model?

from tensorrtx.

Have you tried the official model?

Yes, I used the yolov8 official weight pt(yolov8s-seg.pt) to convert

from tensorrtx.

@Rex-LK Please take a look.

from tensorrtx.

我用官方模型（640 X 640）和自己做的模型（640 X 640）不会报这个错误，用自己做的模型（960 X 960）也报这个错误：
[11/20/2023-15:58:28] [E] [TRT] 4: [shapeContext.cpp::nvinfer1::builder::reshapeCanFaultHelper::<lambda_87ad3b929fe52b49c0129bfe558f8fdd>::operator ()::3546] Error Code 4: Shape Error (reshape changes volume. Reshaping [32,120,120] to [32,6400].)
[11/20/2023-15:58:28] [E] [TRT] 4: [network.cpp::nvinfer1::Network::validate::2977] Error Code 4: Internal Error (Could not compute dimensions for (Unnamed Layer* 317) [Shuffle]_output, because the network is not valid.)

请问是需要修改哪边适配别的模型输入尺寸吗？

from tensorrtx.

我用官方模型（640 X 640）和自己做的模型（640 X 640）不会报这个错误，用自己做的模型（960 X 960）也报这个错误： [11/20/2023-15:58:28] [E] [TRT] 4: [shapeContext.cpp::nvinfer1::builder::reshapeCanFaultHelper::<lambda_87ad3b929fe52b49c0129bfe558f8fdd>::operator ()::3546] Error Code 4: Shape Error (reshape changes volume. Reshaping [32,120,120] to [32,6400].) [11/20/2023-15:58:28] [E] [TRT] 4: [network.cpp::nvinfer1::Network::validate::2977] Error Code 4: Internal Error (Could not compute dimensions for (Unnamed Layer* 317) [Shuffle]_output, because the network is not valid.)

请问是需要修改哪边适配别的模型输入尺寸吗？

maybe you can try to modify the config.h file in src directory

from tensorrtx.