Alexey

@sonalambwani Just wait about 1000 iterations, and `nan` will disappear: https://github.com/AlexeyAB/darknet/issues/504#issuecomment-377290060 1. You can re-calculate anchors, but it is not necessary. You can calculate anchors for Yolo v3 using this...

@ss199302 If there are only some `nan` then training goes well, but if there are all `nan` then training goes wrong.

> For me, I see nans even after 2500 iterations. * All lines have `nan` values or only some lines? * How many classes and images in your dataset? And...

@sonalambwani Looks like normal output of training.

@arun-kumark 1. You should download Classification weights: https://pjreddie.com/media/files/resnet152.weights 2. Then you should get the file `resnet152.200` - pre-trained weights: `./darknet partial cfg/resnet152.cfg resnet152.weights resnet152.200 200` 3. And then you should...

@arun-kumark Something goes wrong! * Check content of your cfg/resnet152.cfg - file, is this file resnet152? * Check that you are doing everything right * If you still get wrong...

You can use repo https://github.com/AlexeyAB/darknet that shows Loss & mAP chart during Training: 

@groszste It is Training loss and Validation mAP. For me it isn't necessary to see Validation loss, it is much better to see Validation mAP.

Anchors are initial sizes (width, height) some of which (the closest to the object size) will be resized to the object size - using some outputs from the neural network...

@abdulkalam1233 * `linear` is `Identity`-activation: `y = x` https://github.com/pjreddie/darknet/blob/f6d861736038da22c9eb0739dca84003c5a5e275/src/activations.h#L31 ---- * `leaky` is `Leaky ReLU`-activation: `if(x