zpge
zpge
Hello, it's a very nice work. I happend to need a program to generate hexaspere. I am not good at mathmatics. Can you help to point me the reationamong edge...
I want to train on my own data. Can anyone give a short explaination on how to prepare and put the files?
Many thanks!!!
发现一个问题,train的时候可以用很大的batchsize和image size,但是每次test的时候就要用很小的image size和batch size,不知道这是什么原因造成的呢? test是指训练完N次后的validation。
在mobilev2-yolov3-lite voc上根据已有的pruned model,训完完成后,再做merge bn,发现做检测的时候,程序一直停在self._forward(start_ind, end_ind),没有报错也没有进展。所以问一下如果想剪枝和merge bn都用的话,这个流程是怎样的?
In this repo https://github.com/eric612/MobileNet-YOLO/tree/master/models/mobilenetv2_voc/yolo_lite, I noticed in the file train.prototxt, there is a line #10,14, 23,27, 37,58, 81,82, 135,169, 344,319. What does it mean? It seems to stand for the...
I have downloaded both the sim10k and cityscapes datasets and tries to repeat the training process. But when I use the following commond python3 -m torch.distributed.launch --nproc_per_node=4 --master_port=$((RANDOM + 10000))...
Am I blind?