kernel weights has count 2688 but 32640 was expected

[SunnyBoy-GitHub]

Env

About this repo

./yolov5_det -s bestss.wts bestss.engine s [W] [TRT] The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible. Loading weights: bestss.wts (Unnamed Layer* 201) [Convolution]:kernel weights has count 2688 but 32640 was expected [E] [TRT] 4: (Unnamed Layer* 201) [Convolution]: count of 2688 weights in kernel, but kernel dimensions (1,1) with 128 input channels, 255 output channels and 1 groups were specified. Expected Weights count is 128 * 11 * 255 / 1 = 32640 [E] [TRT] 4: [convolutionNode.cpp::computeOutputExtents::57] Error Code 4: Internal Error ((Unnamed Layer 201) [Convolution]: number of kernel weights does not match tensor dimensions) 大佬这种转模型为什么会出现最终输出参数不同呢，大佬有办法解决吗

[wang-xinyu]

修改这个了吗

Update kNumClass in src/config.h if your model is trained on custom dataset

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.