open-mmlab/mmyolo

Issues

• mmyolo训练的yolov5权重模型能使用yolov5官网的代码加载权重模型吗

  #917 opened 6 months ago by cainiaozp
  2

• Results do not correspond to current coco set

  #969 opened 3 months ago by EudicL
  3

• The fps of yolov6_v3_n is very low

  #982 opened a month ago by wsy-yjys
  5

• testing with the trained model

  #985 opened a month ago by Naziyashaik09
  0

• top_down_layer_inputs = torch.cat([upsample_feat, feat_low], 1) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 16 but got size 15 for tensor number 1 in the list.

  #928 opened 5 months ago by 99HU
  6

• KeyError: 'YOLOv5CocoDataset is not in the mmengine::dataset registry

  #984 opened a month ago by Priyanshu88
  0

• Cannot install with CUDA 12.1

  #983 opened a month ago by a-d-wicklund
  0

• About FPS

  #981 opened a month ago by wsy-yjys
  0

• RTMDet annotations incorrectly loaded in test pipeline

  #978 opened a month ago by mattias-pp
  0

• Can't build after following instructions, "#error C++17 or later compatible compiler is required to use ATen."

  #975 opened a month ago by mikeytrw
  3

• When will the YOLOv9 algorithm go live in the MMYOLO project?

  #973 opened 2 months ago by createhappily
  3

• Integrate with CVAT and Fiftyone for Semi-automatic and Automatic Annotation

  #976 opened a month ago by jenhaoyang
  0

• The testing results of the whole dataset is empty AND both loss_bbox and loss_dfl are 0

  #961 opened 3 months ago by lkh2022
  9

• Issue with PPYOLOE+ model output on custom YOLO5CocoDataset with custom classes

  #974 opened 2 months ago by sanjeevnara7
  0

• support mmcv2.1.0+

  #972 opened 2 months ago by zlccccc
  0

• save_param_scheduler is True but self.param_schedulers is None

  #971 opened 2 months ago by yuan-kai-design
  0

• TRT_FP16_Latency for RTMDet-R-s

  #929 opened 5 months ago by 54wb
  1

• Doc 404 - page not found

  #967 opened 3 months ago by levylll
  1

• Slower Training Than Ultralytics

  #964 opened 3 months ago by davidhuangal
  1

• 图片推理出的类别id如何改成类别名

  #963 opened 3 months ago by todesti2
  2

• converting to ONNX using docker image - KeyError: 'YOLODetector is not in the mmengine::model registry.

  #966 opened 3 months ago by tomyot
  0

• Reload model error from load_from

  #965 opened 3 months ago by lpz7
  0

• 如何推理一张图片

  #958 opened 3 months ago by todesti2
  15

• How to use the CBAM in yolo, could you give me an example?

  #960 opened 3 months ago by lijoe123
  0

• 多卡训练出现RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by passing the keyword argument `find_unused_parameters=True` to `torch.nn.parallel.DistributedDataParallel`, and by making sure all `forward` function outputs participate in calculating loss.如何解决

  #953 opened 4 months ago by iamecong
  1

• 使用tools/test.py画图yolox无法显示gt的bbox

  #957 opened 3 months ago by LeoRainly
  0

• How to solve TypeError: "tasks" must be a tuple object or a sequence object, but got <class 'mmcv.video.io.VideoReader'>

  #916 opened 6 months ago by Paihuai-D
  4

• when i use the test.py after train, it didn't work,the problem is "AssertionError"

  #955 opened 3 months ago by 1-etudiant
  2

• Update is messed up when mmyolo adds new learnable parameters for training.

  #954 opened 4 months ago by lpz7
  1

• same YOLOX config in mmdetection v2.25(using mmcv) and mmyolo(using mmengine), but mAP differs a lot

  #952 opened 4 months ago by clw5180
  0

• Colab install as per custom_installation.md not functioning

  #924 opened 5 months ago by thomasf1
  4

• IndexError: index 2 is out of bounds for axis 2 with size 1

  #951 opened 4 months ago by helloansuman
  0

• where is easydeploy?

  #948 opened 4 months ago by aooxin
  1

• 怎么把推理结果保存为txt文本

  #933 opened 5 months ago by Mahonehan
  0

• Exception: Cannot find valid image after 1000! Please check your image path and pipeline

  #940 opened 4 months ago by VincentCoulombe
  3

• Any plan for 'yolov8 instance segmentation'?

  #947 opened 4 months ago by chenxinfeng4
  2

• The network structure of the C2f module in YOLOv8 has a minor issue

  #941 opened 4 months ago by Latitude9527
  4

• Is the replication of yolov6 3.0 lacking some structure?

  #944 opened 4 months ago by 885225250
  0

• How do I use my computer's camera？

  #939 opened 5 months ago by fc-whu
  0

• Why are all AP at -1 during training

  #927 opened 5 months ago by peng-peng0913
  1

• How to draw the YOLOv8-P5 model structure

  #936 opened 5 months ago by xqc-qc
  0

• rtmdet 使用trt int8效果不好

  #932 opened 5 months ago by luuuyi
  0

• NMS works too slow!

  #931 opened 5 months ago by TolgaOzdmir
  0

• demo/boxam_vis_demo.py not work for yolo-x

  #925 opened 5 months ago by chenslcool
  1

• 改变mmyolov5的配置时出错

  #923 opened 5 months ago by zhen735
  0

• MMCV 2.1.0 support

  #922 opened 6 months ago by thiagoribeirodamotta
  0

• How should I set the loss weight of the config file?

  #921 opened 6 months ago by josh3255
  0

• box解码过程

  #919 opened 6 months ago by nanhui69
  1

• docker build docker/GPU/ -t mmdeploy:gpu --build-arg USE_SRC_INSIDE=true，报错Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProtocolError('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))': /conda-forge/noarch/current_repodata.json failed CondaHTTPError: HTTP 000 CONNECTION FAILED for url <https://conda.anaconda.org/conda-forge/noarch/current_repodata.json> Elapsed: - An HTTP error occurred when trying to retrieve this URL. HTTP errors are often intermittent, and a simple retry will get you on your way. 'https//conda.anaconda.org/conda-forge/noarch'

  #920 opened 6 months ago by cainiaozp
  0

• How to convert mmyolo model to tensorRT and call by C# like in the mmdeploy

  #912 opened 6 months ago by kelvinwang139
  0