princeton-vl/CornerNet-Lite

Issues

• [W Resize.cpp:19] Warning: An output with one or more elements was resized since it had shape [16263], which does not match the required output shape [14926].This behavior is deprecated, and in a future PyTorch release outputs will not be resized unless they have zero elements. You can explicitly reuse an out tensor t by resizing it, inplace, to zero elements with t.resize_(0). (function resize_output)

  #160 opened a year ago by xutao2020
  1

• About the software requirements

  #159 opened 2 years ago by pcuevas-ch
  1

• ModuleNotFoundError: No module named 'core'

  #143 opened 5 years ago by annyhou
  3

• A small running error

  #158 opened 3 years ago by simple-boy
  0

• some training issue

  #151 opened 4 years ago by ZeKunZhang1998
  1

• error while tarining on my new dataset which has same COCO format

  #157 opened 3 years ago by alaa-shubbak
  1

• ModuleNotFoundError: No module named 'top_pool'

  #119 opened 5 years ago by Hhy1024
  7

• When I train the model on my own dataset, I met IndexError in cornernet_saccade.py

  #156 opened 3 years ago by imzhangyd
  1

• ImportError undefined symbol: _ZNSt19basic_ostringstreamIcSt11char_traitsIcESaIcEEC1Ev

  #155 opened 3 years ago by zielona1
  1

• why?RuntimeError: Dimension out of range (expected to be in range of [-2, 1], but got 2)

  #118 opened 5 years ago by star744
  1

• 0%| | 0/90000 [00:00<?, ?it/s]段错误(吐核)

  #154 opened 4 years ago by Fuhan1994
  0

• when run the demo.py, the program is stuck

  #153 opened 4 years ago by Mikiloo
  0

• some questions about the structure of cornerNet-saccade

  #152 opened 4 years ago by liushuai839
  1

• Duplicated boxes during soft_nms

  #150 opened 4 years ago by 0phoff
  1

• Can not create the envs on the first step， list many config package when created from file conda_packagelist.txt Please help me!!

  #149 opened 4 years ago by qiaolegeke
  1

• About "add downsampling lyaer before the hourglass module and remove one in hourglass modue"

  #145 opened 5 years ago by Vankeee
  1

• AttributeError: 'builtin_function_or_method' object has no attribute 'view'

  #142 opened 5 years ago by hs7251912
  1

• The network architecture of CornerNet-Saccade

  #148 opened 4 years ago by duongphilong1989
  0

• When I testing my own data, occur No module named 'test.xxx'

  #147 opened 4 years ago by chordxu
  0

• train error

  #146 opened 4 years ago by bryant-xia
  0

• There is a problem during training

  #113 opened 5 years ago by float4189
  2

• What does the UserWarning mean? How to solve it? Does it effect the training result?

  #111 opened 5 years ago by pingqi
  5

• _cpools error

  #138 opened 5 years ago by Hello526
  3

• Has anyone use another backbone networks to test the performance?

  #144 opened 5 years ago by bupt-renpei
  0

• Using a data set with only one category, Loss dropped to 0.003, but when testing, ap = -1

  #141 opened 5 years ago by liangqiLQ
  1

• 为什么测试结果ap=-1

  #120 opened 5 years ago by star744
  10

• Problem when evaluating

  #140 opened 5 years ago by tienthegainz
  0

• Freezing model to train small dataset

  #139 opened 5 years ago by tienthegainz
  1

• How Can I Use a Pre_trained Model?

  #128 opened 5 years ago by DataXujing
  3

• The CornerNet-Saccade pridiction spend more 10s in CPU mode，is it really faster than YOLOV3？

  #137 opened 5 years ago by xhb7636553
  1

• Problems when i evaluate my own data

  #123 opened 5 years ago by qingzhoudong
  2

• The accuracy and speed of CornerNet-Squeeze

  #134 opened 5 years ago by jerrywgz
  3

• filenotfounderror

  #135 opened 5 years ago by hundunshu
  1

• real-time detection

  #136 opened 5 years ago by hundunshu
  0

• error in evaluate the model

  #133 opened 5 years ago by qrt159
  1

• Train Loss Problem

  #130 opened 5 years ago by DataXujing
  3

• How to change backbone

  #129 opened 5 years ago by gonghaotian
  3

• Why resnet backbones do not perform well on CornerNet?

  #131 opened 5 years ago by Epiphqny
  0

• suggested error handling

  #132 opened 5 years ago by blafasel42
  0

• There was a problem during training

  #124 opened 5 years ago by float4189
  3

• but i get another problem,even i set batch_size=1,it also raise RuntimeError: CUDA out of memory. Tried to allocate 6.75 MiB (GPU 0; 3.94 GiB total capacity; 1.50 GiB already allocated; 23.00 MiB free; 49.10 MiB cached),it is wired??

  #116 opened 5 years ago by cqray1990
  1

• Question about training CornerNet-squeeze on Tesla v-100

  #127 opened 5 years ago by calvindu95
  0

• Questions about the mask in _ae_loss

  #126 opened 5 years ago by i-yliu
  0

• train for voc dataset

  #125 opened 5 years ago by huangzicheng
  0

• Test COCO time

  #112 opened 5 years ago by Yang507
  2

• git clone git@github.com:cocodataset/cocoapi.git coco

  #117 opened 5 years ago by Youggie
  1

• Problems when i evulate my own data

  #122 opened 5 years ago by qingzhoudong
  0

• Problem when evaluate my own datasets

  #121 opened 5 years ago by qingzhoudong
  0

• What is the meaing of command ' --split <split>' for training

  #114 opened 5 years ago by lmomoy
  0

• dist = tag_mean.unsqueeze(1) - tag_mean.unsqueeze(2)

  #115 opened 5 years ago by cqray1990
  7