PiseyYou

@Adamdad test with the video, but seems the speed is very low, the video show pic per frame per second. Something need to check?

@violet17, have you deal with such issue? I meet the same error, after excu sparsity_train, to excu test_prune.py, the error happen as below: > assert sample_metrics != [] > ValueError:...

> result = self.forward(*input, **kwargs) File "/ext_data/anaconda3_before/envs/yolo/yolov3-network-slimming/yolomodel.py", line 130, in forward loss_cls = (1 / nB) * self.ce_loss(pred_cls[mask], torch.argmax(tcls[mask], 1)) RuntimeError: cannot perform reduction function max on tensor with no...

@leJson Thanks a lot, I solve the issue, the key point is put folder "images" and "label" at the same folder. The folder path as below: This make clear how...

I was doing the task for test coco, not VOC right now, after check this, I will these test later. As I get the information, the key point to deal...

@leJson it is rigth, follow this suggestion, it work. But there is another problem, in parse_config.py file, as the default, try to set options['gpus'] = '0, 1' let two GPU...

same problem, have you already solved?

> > I meet a similar problem that I cannot load my trained data, always show this problem. I choose different version about some pkg, but it is doesn't work....

> > Have you add the upsample layer into caffe? > > After you add the upsample layer into caffe, you need to add upsample_param into caffe.proto . > >...

> @chirs123456 > yes, I commented the "USE_CUDNN := 1" like "# USE_CUDNN := 1" in "Makefile.config", and it worked, my gpu is 750, maybe it can't work with cudnn...