kaishijeng

Sanghoon, Is pva-lite model available yet? Thanks,

Sanghoon OK, I will wait for new lite version. Thanks, On Wed, Dec 28, 2016 at 9:28 PM, Sanghoon Hong wrote: > Hi @kaishijeng > I may be able to...

I use the following script to train, bu got an error below: export CACHE_NAME=cache_voc MODEL_NAME=model_voc MODEL=model.mobilenet.MobileNet python3 train.py -b 32 -lr 1e-3 -e 160 -m cache/name=$CACHE_NAME model/name=$MODEL_NAME model/dnn=$MODEL train/optimizer='lambda params,...

I use the latest code and still got the same error. This error also happens yolo2.Tiny model. Can you share your command and config.ini file? Thanks,

After further debugging, _center_offset expects [32,144, 52, 2], but _positive has shape [32,144, 52, 1] and this causes an error in loss['center'] = F.mse_loss(pred['center_offset'][_positive], _center_offset[_positive], size_average=False) Do you know why...

Thanks,

I will download both pretrained models and try them out. Thanks,

i use PFE_sphere64_msarcface_am and got the following lfw accuracy: Euclidean (cosine) accuracy: 0.99717 threshold: 1.50062 MLS accuracy: 0.99833 threshold: -2435.03760 Not sure why MLS accuracy threshold is huge negative number....

It works now. On speed performance, I found SqueezeDet is slower than tiny-yolo model of Darkflow on afirefly-3399 platform: SqueezeDet: 0.9138s/image vs Tiny-Yolo: 0.6s/image. This is a surprise to me...

This measurement is from demo.py. The time is measured below: t_start = time.time() det_boxes, det_probs, det_class = sess.run( [model.det_boxes, model.det_probs, model.det_class], feed_dict={model.image_input:[input_image]}) t_end = time.time() times['detect'] = t_end - t_start...