OpenGVLab/InternImage

Issues

• RuntimeError: mat1 and mat2 shapes cannot be multiplied (2112x1000 and 96x96)

  #315 opened a month ago by ENMA9527
  0

• [DCNv4 ERROR] cuda op error when use internimage-L and internimage-LX with DCNv4, however internimage-B works well with DCNv4

  #280 opened a year ago by dou3516
  5

• 训练和评估检测模型的时候报以下错误，请问是什么原因呢？

  #302 opened 6 months ago by CachCheng
  1

• InternImage block for input 3D

  #314 opened 3 months ago by faizan1234567
  0

• OpenImagesV6 based Object Detection Checkpoint

  #313 opened 3 months ago by TouqeerAhmad
  0

• detection 我是用自己数据训练 就是那个官方balloon数据，典型小样本，效果太差

  #282 opened a year ago by BoFan-tunning
  4

• 请问internimage-h与mask2former有在未经coco预训练情况下的ade20k语义分割性能吗？

  #309 opened 3 months ago by yan-hao-tian
  0

• 请问internimage-H和mask2former的组合，贵团队有试过未经coco预训练直接在ade20k上训练的效果如何吗？

  #310 opened 3 months ago by yan-hao-tian
  0

• name 'DCNv3Function' is not defined

  #312 opened 4 months ago by kll-df
  0

• how to detect image objects

  #307 opened 5 months ago by chengminglei77
  0

• Unsupported gpu architecture 'compute_86'

  #284 opened 9 months ago by Cominder
  1

• bad result from Image Demo Segmentation

  #306 opened 5 months ago by YicanGgg
  1

• Export Model to Onnx as Fp16 Not Working

  #305 opened 5 months ago by RhinoInani
  0

• Multimodality

  #304 opened 6 months ago by aliman80
  0

• cannot use Python API to infer after converting the segmentation model to tensorrt

  #303 opened 6 months ago by chenzhutian
  0

• 训练和评估分类模型的时候报以下错误，请问是什么原因呢？

  #301 opened 6 months ago by CachCheng
  2

• TypeError: unsupported operand type(s) for -: 'tuple' and 'int'

  #299 opened 6 months ago by zhouxuedaasd
  0

• [bug] how to train fine-tuning classification model (size mismatch for head.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([4]).)

  #297 opened 7 months ago by jeonga0303
  3

• Confused about the number of classes when segmenting with Mask2Former

  #298 opened 7 months ago by AndreiMihalea
  0

• About the stride in detection/ops_dcnv3

  #258 opened a year ago by GoblinCraftman
  2

• [Solved] RuntimeError: Not implemented on the CPU

  #296 opened 7 months ago by jeonga0303
  1

• It appears that the InternImage project does not publicly provide inference code specifically for classifying individual images.

  #295 opened 7 months ago by unclelee97
  0

• 使用DCNv3_pytorch 训练的分割模型，导出onnx后，还是存在不支持的onnx node

  #286 opened 8 months ago by ZJDATY
  3

• How to install InternImage/detection with A100

  #267 opened a year ago by Deokhwan-Kyeong
  1

• Typo in classification/meta_data/map22kto1k.txt?

  #278 opened 10 months ago by ZhiqiGao2001
  0

• InternImage is not in the models registry

  #293 opened 7 months ago by wooj0216
  0

• conda env specs for CVPR23 Occupancy Prediction Challenge

  #294 opened 7 months ago by kaimingkuang
  0

• Great work! Can you share the training details of RGB-D semantic segmentation on the nyu dataset?

  #292 opened 7 months ago by ascacdsaa
  0

• ImportError: DLL load failed while importing DCNv3

  #291 opened 8 months ago by 123dddwn
  0

• The outdoor window is missing?

  #289 opened 8 months ago by yangxuan821
  0

• 如何才能使分割建筑的结果区分外墙和窗户，或者有更多精细的标签体现出来呢？我想对一个建筑进行详细分割。How can the results of dividing buildings distinguish between exterior walls and windows, or have more detailed labels reflected? I want to perform a detailed segmentation of a building.

  #288 opened 8 months ago by yangxuan821
  1

• ImportError: /root/miniconda3/lib/python3.8/site-packages/DCNv3.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN3c1015SmallVectorBaseIjE8grow_podEPvmm

  #269 opened a year ago by fengwen-coder
  2

• DCNv3 编译问题

  #287 opened 8 months ago by 123dddwn
  0

• cmake error

  #285 opened 9 months ago by Shanyaodedanshen
  0

• [DCNv4 error] RuntimeError: falseINTERNAL ASSERT FAILED at src/cuda/dcnv4_col2im_cuda.cuh:470

  #281 opened a year ago by billbliss3
  1

• Tensorrt engine inference of C++ API

  #279 opened a year ago by GitHubYuxiao
  0

• build torchscript extension

  #275 opened a year ago by GitHubYuxiao
  0

• Weights for CrowdHuman dataset

  #274 opened a year ago by filonenkoa
  0

• Unable to train the algorithms with 2 GPU instances (multi-node), each with 4 A100s

  #272 opened a year ago by CheruscanArminius
  0

• 预训练模型无法下载

  #271 opened a year ago by shellxiao
  0

• Is there a way to extract the heatmap based on the feature map from image_demo.py?

  #270 opened a year ago by jeonga0303
  0

• python-pytorch版本DCNv3

  #268 opened a year ago by lp-094
  0

• What are the differences between DCNv3 and DCNv3 pytorch?

  #266 opened a year ago by xgddyrq
  0

• a bug when converting the dino detector to tensorrt

  #265 opened a year ago by goldentimecoolk
  1

• DCNv3_pytorch代码中可变形卷积的卷积过程

  #264 opened a year ago by lp-094
  0

• Release date for InternImage-H pretrained weights

  #263 opened a year ago by aravind3134
  0

• Inference GPU memory is more than training

  #262 opened a year ago by ker95qq
  0

• Latency too high with DCNv3_pytorch op on cpu

  #261 opened a year ago by xbkaishui
  0

• GPU memory requirements increases when using DCNv3_pytorch rather than DCNv3

  #260 opened a year ago by jonassoebro
  0

• Why whl_files can not download?

  #259 opened a year ago by moderate-leon
  0