HuangLian126

icon company Chongqing University of Technology icon location Chongqing icon location computer vision, few-shot learning, object detection

Results 5 comments of HuangLian126

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

@jfzhang95@lyd953621450 Hi, I have faced the same problem. Do you train your own datasets? I think the key is the label.

how to visualize the detection results?

> > _No description provided._ > > Did you successfully get the visual result? > > _No description provided._ > > Did you successfully get the visual result? Yes, I...

how to visualize the detection results?

@NHW2017 torch==0.4, torchvision==0.21

Issue training base model

@christegho Hi, I try to train the base with torch 1.2.0 , torchvision 0.4.0 and CUDA 10.1. However, I get this error: File "/home/hl/hl/Fewshot_Detection-master/region_loss.py", line 330, in forward pred_boxes[0] =...

What is the meaning for "Exp Name FULL" ?

@Patrickctyyx Thanks for your reply. I'm training, hhh.