Axel13fr

hi @leadcain84 , this tensor contains the ground truth boxes. They are input into the model because the loss is computed in the tensor flow graph directly to do it...

Hi Rodrigo, No answers from me, just a side question: how did you get these metrics into tensorboard ? I've had difficulties getting them through the tensorboard callback. Any code...

Hi Rodrigo, thanks, I cherry picked your mAP Tensorboard callback. Regarding your questions, I believe you have used the .h5 backend files right ? Have you tried using the weights...

Interesting. Was it done with Full or Tiny Yolo ? Did you do a warmup before training ? Also, have you tried to freeze some of the layers, specially during...

@rodrigo2019 this repo implements Yolo V2, which is a bit different from the original version you mention in the paper. Specifically, it uses a conv layer at the end of...

Thanks for the link, I'll take a look :+1: I've managed to train Full Yolo properly on one class on the COCO dataset but I'm still trying to have tiny...

@rodrigo2019 I was training on a single class (boat) only on COCO, got 34 with Full Yolo, only 10 with Tiny, Yolo authors had 42 on 80 classes. It is...

MAP for tiny Yolo is on yolo darknet website. For tiny yolo I implemented loading the darknet weights from darknet website but the model they used was for voc dataset...

So you got the correct mAP for coco and voc by loading the darknet weights? As for the layer sizes, you can check and change them according to the cfg...

I implemented the complete reading of darknet weights for full yolo and a mAP evaluation on COCO (without training) dataset gave me 45.32, a bit higher than 42.1. I think...