Vivek Aswal

You need to comment/remove all the cv2.windows commands as colab doesn't allow these optional window graphics. These following lines of code were changed for running yoloface on images: def _main():...

@Classsic , I am no expert but I think, I found something useful on this. https://stackoverflow.com/questions/21697645/how-to-extract-metadata-from-a-image-using-python Here, the meta data of an image is converted in a dictionary format. Hope...

Hi Hshuqin, I am also doing some experiments with different config files. I would like to know what was the maximum mAP @tiny50 that you were able to achieve?

Sorry, maybe I wasn't precise enough. I meant the following mAP: **Average Precision (AP) @[ IoU=0.50 | area= tiny | maxDets=1000 ]**

Okay cool! Thanks @Hshuqin Also, @yinglang till now, I can only replicate the results for Faster RCNN-FPN (exp 2.1) but not for other configurations. As given in the detector results,...

@yinglang just to make sure if I want to run exp4.0 then I can directly do the 2nd step i.e., train on TinyPerson with the Pretrain COCO under directory FPN_SM_tinyperson_b4...

Yes, the FPN_SM_tinyperson_b4 is from the old TinyBenchmark version. It would be really helpful if you would provide the new pre-trained weights for exp4.0 and exp5.1. I would like to...

Thanks a lot for the info @yinglang! The new weight for **faster_rcnn_r50_fpn_1x_coco_sm_tinyperson_lr0.01_8b2g_latest.pth** worked like a charm! However, I had tried running exp 5.1 with old weights and it seemed to...