ppogg/YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
C++GPL-3.0
Pinned issues
Issues
- 12
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 by inbigtoiletboy - 1
- 0
- 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 by sana-u - 0
关于导出v5lite-e-mnnd_fp16.mnn模型
#273 opened by moyans - 0
yolov5lite用ncnn部署,内存占用很高,是正常的吗
#272 opened by qiu-pinggaizi - 0
Pinto Model Zoo link seems to be down
#271 opened by abblancodos - 1
- 0
使用main进行heatmap热力图可视化报错
#269 opened by Leezzzzz - 2
为什么YOLOv5-Lite的推理会比YOLOv5n的推理速度要慢?
#249 opened by pcycccccc - 0
用rk3399测试mnn模型,用gpu比单独用cpu跑慢好多
#268 opened by lfb-blueSky - 0
Use NCNN model
#267 opened by PrashantDixit0 - 4
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 by hz1012hz - 2
Error in prediction result of onnxruntime in c++
#229 opened by EudicL - 0
- 3
find_blob_index_by_name Reshape_output_0 failed
#253 opened by ranjith502 - 2
v5lite-g.pt 部署至rk3588 預測結果錯誤
#259 opened by TomHsu-MIddle - 3
AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor' when export to onnx
#243 opened by Houangnt - 0
None of the models support dynamic batch size
#262 opened by tungngreen - 0
- 2
heatmap功能报错
#260 opened by koushita - 0
onnx export with NMS does not work.
#258 opened by omair18 - 0
Will int8 support provided in existing export.py for converting model into int8.tflite?
#256 opened by rickspark4 - 2
could not find the site of v5lite-s.pt.can you help me
#231 opened by c1l2d3 - 0
pt > ncnn 的文档帮更新下呗
#255 opened by finekewei - 0
- 3
- 1
How to Transfer Learning with yolov5 lite
#252 opened by ranjith502 - 1
- 2
请问一下这些模型都是在多少epochs情况下训练得到的?
#238 opened by Anoue - 1
shufflenetv2预训练的模型的问题
#246 opened by baibsB - 2
onnxruntime cpp demo 输出的box坐标为负的
#240 opened by 2019switch - 1
lite-e我训练时发现GFLOPS是2.7
#245 opened by vcbeaut - 0
Exception: [34m[1mtrain: [0mError loading data from data//VOC/images/train/: [34m[1mtrain: [0mdata/VOC/images/train does not exist See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
#248 opened 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 by justdoit-aaron - 2
yolov5_7.0版本经过rep_convert.py脚本转换后,推理报错。
#242 opened by Miku0999 - 0
./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 by ShiweiCheng0303 - 2
为什么我用lite5e 测出来计算量是2.5Gflops而不是0.7
#239 opened by xibici - 1
使用推理时,遇到了问题
#241 opened by Shengshenlan - 0
wrong parameters in train.py
#237 opened by xibici - 0
- 0
Deploy TensorRT C++ in Jetson_Xaviver NX
#234 opened by RMsu233 - 0
- 1
lite-g版本输出跟其他版本不一样
#232 opened by liuxufenfeiya - 0
Python_demo ONNXruntime 错误
#230 opened by TJJ120635 - 2
v5lite yaml里的anchor大小为啥和cpp demo里的不一样?
#228 opened by xingxinghanzi - 1
shuffle_block中的dw卷积可以替换吗
#227 opened by tigger2018 - 3
- 1
- 0
请问有轻量级2d姿态的开源吗?感谢
#224 opened by henbucuoshanghai