Rajashekar Yadavalli

Using instructions for custom object detections using yolov3 instructions throws an error like this ./darknet detector train data/yolov3-spp-3cls.data cfg/csresnext50-panet-spp.cfg -gpus 0,1,2,3 0,1,2,3 csresnext50-panet-spp compute_capability = 750, cudnn_half = 1 net.optimized_memory...

> @Rajasekhar06 > > plz follow https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects > > according to ur `.data` file name "yolov3-spp-3cls.data", i assume there r 3 classes in ur dataset. > so the number of...

@WongKinYiu I have another small query How to set max batches in multi gpu training on single gpu we do that multiplying class with 2000 but the README.md is a...

@WongKinYiu I have completed training by setting old style of max batched like `max_batches=2000*No. of classes` which is suited for Single GPU training with yolov3-spp config after 6000 iterations then...

Along with the above said @keldrom I request you @monocongo to add the feature argument which can generate different annotations types like for YOLO,COCO,XML so that it will give more...

> compile DCNv2 and add this to demo.py > > ``` > import sys > sys.path.append("./lib/model/networks/DCNv2") > ``` This worked

I'm also facing the same issue while I was training with complete OpenImages V5 dataset how to solve this 

Actually I solved it by deleting the old .pkl files which are loading back again try deleting them and train it worked for me. and make sure data is proper

it might not work with this repo use https://github.com/ultralytics/yolov3 because Yolov4 use some special tricks like imlementing new type of layers which will work with above repo