yushanshan05

CUDA error: an illegal memory access was encountered

3

hi, thanks for you great works. I train my dataset, which has ten classes, fps =1, and I don't add --fp16 flag. max_iter=2 batch_size=2 But when I start training, there...

Why the GPU memory of rednet50 is larger than resnet50?

1

I used Tesla V100. When I train resnet50-retinanet, the gpu memory is 9.26G. But when I train rednet50-retinanet, the gpu memory is 10.98G. In your paper, the params and floats...

why the pull loss and push loss is 0.0 when training my own dataset?

9

When I train my own dataset, the pull loss and push loss is always 0.0. The log is: training loss at iteration 270: 0.08008845895528793 focal loss at iteration 270: 0.08008845895528793...

how to calculate mAP?

25

I found that the ./darknet detector recall function, but it only calculate the recall without fp,tp and mAP. how to calculate mAP? Thanks!

How should I varify the trained model by run_val.sh?

5

I have seen the code that the validated datavaridat is set by the parameter of ‘--data-val'. And the default value is '/tmp/val.rec‘. But I don't know what and where this...