ppogg/YOLOv5-Lite

Issues

• YOLOv5-Lite (onnx)(v1.5版本 5月22日) 类似报错：1.ValueError: operands could not be broadcast together with shapes (3,2,80,85) (19200,2) 2. IndexError: index 4 is out of bounds for axis 0 with size 3

  #263 opened 6 months ago by inbigtoiletboy
  12

• c++ ort make的时候报错undefined reference to `OrtGetApiBase'

  #265 opened 5 months ago by defzhangaa
  1

• 树莓派4B使用C++部署时，向前推理createSession()返回Segmentation fault

  #275 opened a month ago by codingSellena
  0

• 使用best.pt和使用由best.pt转成的best.onnx推理准确度相差很大，为什么

  #274 opened a month ago by sana-u
  0

• 关于导出v5lite-e-mnnd_fp16.mnn模型

  #273 opened 2 months ago by moyans
  0

• yolov5lite用ncnn部署，内存占用很高，是正常的吗

  #272 opened 3 months ago by qiu-pinggaizi
  0

• Pinto Model Zoo link seems to be down

  #271 opened 3 months ago by abblancodos
  0

• 编译错误，error: use of undeclared identifier 'unsig_pro'

  #270 opened 3 months ago by qiu-pinggaizi
  1

• 使用main进行heatmap热力图可视化报错

  #269 opened 3 months ago by Leezzzzz
  0

• 为什么YOLOv5-Lite的推理会比YOLOv5n的推理速度要慢？

  #249 opened a year ago by pcycccccc
  2

• 用rk3399测试mnn模型，用gpu比单独用cpu跑慢好多

  #268 opened 4 months ago by lfb-blueSky
  0

• Use NCNN model

  #267 opened 5 months ago by PrashantDixit0
  0

• cpp_demo中mnn框架部署yolov5-lite导致系统内存一直被占用问题的说明及解决办法

  #257 opened 8 months ago by hz1012hz
  4

• Error in prediction result of onnxruntime in c++

  #229 opened 2 years ago by EudicL
  2

• AttributeError: 'Namespace' object has no attribute 'cache_images'

  #264 opened 6 months ago by sceddd
  0

• find_blob_index_by_name Reshape_output_0 failed

  #253 opened a year ago by ranjith502
  3

• v5lite-g.pt 部署至rk3588 預測結果錯誤

  #259 opened 8 months ago by TomHsu-MIddle
  2

• AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor' when export to onnx

  #243 opened a year ago by Houangnt
  3

• None of the models support dynamic batch size

  #262 opened 7 months ago by tungngreen
  0

• 树莓派5B MNN 部署yolov5lite运行过程中出现异常，报错double free or corruption (out)

  #261 opened 7 months ago by yangbinguet
  0

• heatmap功能报错

  #260 opened 8 months ago by koushita
  2

• onnx export with NMS does not work.

  #258 opened 8 months ago by omair18
  0

• Will int8 support provided in existing export.py for converting model into int8.tflite?

  #256 opened 8 months ago by rickspark4
  0

• could not find the site of v5lite-s.pt.can you help me

  #231 opened 2 years ago by c1l2d3
  2

• pt > ncnn 的文档帮更新下呗

  #255 opened 9 months ago by finekewei
  0

• 请教大佬个问题，推理文件夹时，崩溃。engine->getNbBindings()的值等于4了，如何解决？

  #254 opened 10 months ago by retioa11
  0

• train的时候调用test发生ValueError: not enough values to unpack (expected 3, got 2)报错

  #251 opened a year ago by z0v0z
  3

• How to Transfer Learning with yolov5 lite

  #252 opened a year ago by ranjith502
  1

• 训练新的模型

  #250 opened a year ago by z0v0z
  1

• 请问一下这些模型都是在多少epochs情况下训练得到的？

  #238 opened a year ago by Anoue
  2

• shufflenetv2预训练的模型的问题

  #246 opened a year ago by baibsB
  1

• onnxruntime cpp demo 输出的box坐标为负的

  #240 opened a year ago by 2019switch
  2

• lite-e我训练时发现GFLOPS是2.7

  #245 opened a year ago by vcbeaut
  1

• Exception: train: Error loading data from data//VOC/images/train/: train: data/VOC/images/train does not exist See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data

  #248 opened a year ago by liuyiming199721
  0

• v5lite android中如何将显示在OpenCV的推理结果输出到java中

  #247 opened a year ago by justdoit-aaron
  0

• yolov5_7.0版本经过rep_convert.py脚本转换后，推理报错。

  #242 opened a year ago by Miku0999
  2

• ./v5lite_trt ./config.yaml ./samples/ terminate called after throwing an instance of 'YAML::TypedBadConversion<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >' what(): bad conversion

  #244 opened a year ago by ShiweiCheng0303
  0

• 为什么我用lite5e 测出来计算量是2.5Gflops而不是0.7

  #239 opened a year ago by xibici
  2

• 使用推理时，遇到了问题

  #241 opened a year ago by Shengshenlan
  1

• wrong parameters in train.py

  #237 opened a year ago by xibici
  0

• 训练结果为nan

  #236 opened 2 years ago by Yitianw
  0

• Deploy TensorRT C++ in Jetson_Xaviver NX

  #234 opened 2 years ago by RMsu233
  0

• 文字显示方向

  #233 opened 2 years ago by C4712
  0

• lite-g版本输出跟其他版本不一样

  #232 opened 2 years ago by liuxufenfeiya
  1

• Python_demo ONNXruntime 错误

  #230 opened 2 years ago by TJJ120635
  0

• v5lite yaml里的anchor大小为啥和cpp demo里的不一样？

  #228 opened 2 years ago by xingxinghanzi
  2

• shuffle_block中的dw卷积可以替换吗

  #227 opened 2 years ago by tigger2018
  1

• 训练不进行

  #226 opened 2 years ago by hq0709
  3

• v5lite-s在pytorch上预测的效果好，导出onnx格式，用onnxruntime推理效果差距较大。

  #225 opened 2 years ago by liuxiao789
  1

• 请问有轻量级2d姿态的开源吗？感谢

  #224 opened 2 years ago by henbucuoshanghai
  0