taohan10200/IIM

Issues

• IIM for video input

  #40 opened 2 months ago by HiperSoloZ
  0

• 主页给的HRNet权重链接hrnetv2_w48_imagenet_pretrained.pth和Crowd_locator中模型结构不太一样

  #34 opened 2 years ago by xiong224
  2

• input video

  #39 opened a year ago by dngusd
  1

• How to visualize other datasets test set pictures?

  #25 opened 3 years ago by wzzhai
  7

• FileNotFoundError: [Errno 2] No such file or directory: '../ProcessedData/JHU\\train.txt'

  #38 opened a year ago by theflygod
  0

• Memory allocation error

  #32 opened 2 years ago by akshu281
  1

• segfault with pytorch 1.17 and 2.0.0

  #37 opened a year ago by fatbringer
  1

• Confidence level?

  #33 opened 2 years ago by fatbringer
  8

• 怎样转化为onnx模型

  #26 opened 3 years ago by huaxiangwangman
  3

• 您好 我想问下每个数据集给出的mean_std是如何计算的，和我自己计算的结果不太相同。

  #36 opened a year ago by csz-006
  0

• 请问mask_50_60具体有什么作用？运行prepare_NWPU会出现jsons文件缺失错误（缺失的是测试图片的id，所以肯定是没有的）

  #35 opened 2 years ago by tony-dd
  1

• killed when self.validate()

  #13 opened 4 years ago by henbucuoshanghai
  1

• Could you please give me demo code, I mean real-time testing code?

  #31 opened 2 years ago by vasanth4224
  0

• Training on general dataset

  #30 opened 2 years ago by akshu281
  2

• how can i use it on video ?

  #8 opened 4 years ago by dengxuankun
  2

• UserWarning: Corrupt EXIF data. Expecting to read 4 bytes but only got 2. warnings.warn(str(msg))

  #4 opened 4 years ago by ZJU-lishuang
  12

• How to config to train on NVIDIA GeForce RTX 3090 Ti/PCIe/SSE2

  #29 opened 3 years ago by vtmjapandev
  6

• threshold appear to be nan during the training process

  #27 opened 3 years ago by knightyxp
  2

• RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

  #28 opened 3 years ago by vtmjapandev
  1

• Great work but Threshold Encoder module is useless.Details look at the picture

  #24 opened 3 years ago by lab-gpu
  3

• 模型保存为pt时报错RuntimeError: Could not export Python function call 'BinarizedF'

  #23 opened 4 years ago by wangle-wang
  1

• loss不是很懂

  #19 opened 4 years ago by henbucuoshanghai
  6

• 训练时有足够内存，依然得到out of memory问题

  #21 opened 4 years ago by montensorrt
  1

• 训练时有足够得内存，依然得到out of memory问题

  #22 opened 4 years ago by montensorrt
  0

• 我在training時遇到以下錯誤

  #20 opened 4 years ago by tonyfantony
  1

• 关于源码里面BinarizedF的反传部分的疑惑

  #18 opened 4 years ago by muyiyiyi
  2

• net.load_state_dict(new_state_dict,False)

  #17 opened 4 years ago by henbucuoshanghai
  1

• 运行vis4val.py时出错 Key Error 求解~

  #16 opened 4 years ago by lizxko2009
  1

• 下载

  #15 opened 4 years ago by lyyhd
  0

• 数据集

  #14 opened 4 years ago by lyyhd
  0

• Can you share the codes for generating GT IIMs?

  #2 opened 4 years ago by BJTUJia
  8

• NAN in training process

  #7 opened 4 years ago by Nikumata
  5

• OOM

  #12 opened 4 years ago by henbucuoshanghai
  0

• val_gt_loc.txt is used only in the test time.

  #11 opened 4 years ago by henbucuoshanghai
  0

• 模型在哪里？怎样测试一张图片，得到人数？

  #10 opened 4 years ago by henbucuoshanghai
  0

• 关于读取模型权重的问题

  #9 opened 4 years ago by Veefas
  4

• the weights of Threshold Encoder be NaN when training

  #6 opened 4 years ago by s1702319
  2

• Cannot load pretrained models

  #5 opened 4 years ago by bitwalt
  3

• ImportError: cannot import name 'read_pred_and_gt' from 'misc.utils'

  #3 opened 4 years ago by ZJU-lishuang
  1

• Have you compare the result with other semantic segmentation methods?

  #1 opened 4 years ago by streamer-AP
  2