Alexey

@jamessmith90 Yes, you can. The more frames - the better.

@edwardxliu Hi, Thanks for PR! Why is it better than: https://github.com/AlexeyAB/darknet#how-to-use-on-the-command-line JSON and MJPEG server that allows multiple connections from your soft or Web-browser ip-address:8070 and 8090: `./darknet detector demo...

You can use 2-4x GPUs to train 2x-4x faster, so after each iteration GPUs will be synchronized. No, you cant use lower subdivisions. Because GPUGPU PCI-express interconnect (~16 GB/sec) is...

Do you want to increase mini_batch size 2x and decrease performance 100x?

@andreasmarxer Compile Darknet with GPU=1 CUDNN=1 in the Makefile

1. Compile darknet by using ``` cmake . make ``` 2. install OpenCV

@cenit Hi, do you know what is the reason?

Try to set `random=0` at the end of your cfg-file. ---- Also you can try to base your cfg-file on Densenet instead of Resnet: https://pjreddie.com/darknet/imagenet/

@skyuuka Old version of darknet had some issues with resize of some layers when random=1. Current version of Darknet should work successfully with random=1.

@skyuuka Because resnet18.weights is already trained the number of iterations >= max_batch-param(from your cfg-file) * Or add `-clear` flag at the end of command * Or do partial. Extract required...