tuteming

miss /yoltv4/darknet/data/rareplanes_train.data (we can build this file) and names = /yoltv4/darknet/data/rareplanes.name (important) (we can not build this file)

請問你用fast-reid是否可在win10配置?

我用的是TensorRT 7

已解決 yolo.cpp comment line 1139-1144 /* if (m_NetworkType == "yolov4")//pan { outputTensor.gridSize = (m_InputH / 32) * pow(2, 2-_n_yolo_ind); outputTensor.grid_h = (m_InputH / 32) * pow(2, 2-_n_yolo_ind); outputTensor.grid_w = (m_InputW...

這是行不通的 抱歉

Dear JJLimmm: I have try very times, but I get a wrong 1.jpg.  and the final result is  yolov7-w6-pose.pt is changed? Thanks.

抱歉 我覺得問題也不在這 我再查查看 不過真是沒道理 trt7 ok trt8則失敗

sorry, 我應該確定是maxpool的問題,因在建enging時(以下我只列部分) (11) conv-bn-leaky 64 x 200 x 200 128 x 200 x 200 280160 (12) skip 128 x 200 x 200 128 x 200 x 200 - (13) maxpool...

I have a yolo-like cfg with leaky, it run in your trt7 version is good. but run in your trt8 version has wrong. error in chunk.cu line 74: NV_CUDA_CHECK(cudaMemcpyAsync((char*)outputs[0] +...

if in chunk.h set int _n_size_split=0 it can run, but no any detect results . you have any idea can help me? thanks