pytorch-YOLOv4

pytorch-YOLOv4 copied to clipboard

RuntimeError: CUDA error: device-side assert triggered

5

/pytorch/aten/src/ATen/native/cuda/Loss.cu:102: operator(): block: [55,0,0], thread: [57,0,0] Assertion `input_val >= zero && input_val = zero && input_val = zero && input_val = zero && input_val = zero && input_val = zero...

huafeihuayu

while building nvdsinfer_custom_impl_Yolo though make command , i get below error . Kindly assist

1

root@39026ff1831b:/app/sriharsha/pytorch-YOLOv4/DeepStream/nvdsinfer_custom_impl_Yolo# make g++ -c -o nvdsinfer_yolo_engine.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream-6.1/sources/includes -I/usr/local/cuda-11.6/include nvdsinfer_yolo_engine.cpp In file included from nvdsinfer_yolo_engine.cpp:25: yoloPlugins.h: In member function 'virtual nvinfer1::IPluginV2* YoloLayerV3PluginCreator::deserializePlugin(const char*, const void*, size_t)':...

h9945394143

different loss functions for loss_xy and loss_wh

1

May I ask why you use F.binary_cross_entropy for loss_xy while you use F.mse_loss for loss_wh? And, (1) why did you divide by 2 for loss_wh? (you didn't divide by 2...

love2learn-7179

darknet2pytorch supported for Yolo versions below 4 ?

1

Tianxiamo, Amazing tool first of all. I tested your conversion method `darknet2pytorch` on both V4 and V1 and found out that V1 is not supported. Are there any plans to...

sendeniz

Guys, dont use this version of pytorch YOLOv4, its a total waste of time.

10

This repository is like a trap, like a hole without ending. Everything in this repository got bugs and no one is using them already. The bug continue and continues emerges...

MheadHero

Hi, I am currently running demo.py with the aim of converting my own trained yolov4-csp model from darknet to pytorch. I wanted to clarify if the parameters for the post...

lpkoh

why training so slow?

3

one hour each epoch, how to solve it please?

forwardwfg

error：OpenCV can't augment image: 608 x 608

3

ValueError: could not broadcast input array from shape (348,376,3) into shape (370,376,3) OpenCV can't augment image: 608 x 608

FYM1209

RuntimeError

3

@Tianxiaomo I use coco_annotation.py to create my train.txt .but when I train my dataset ,I met this problem, who can help me ? RuntimeError: Assertion `x >= 0. && x

yunxiaozimeng

Excuse me, compared to bakcbone, CBN is better than S, why is there no CBN in all experiments in the end, but there is S？ table is from yolov4 paper(i.e.,tabke4)...

futureisatyourhand