tensorrtcv's People
Forkers
wolfworld6 pgdtgq cqray1990 hahher 1045245078 liangxin123456 zuzi2015 xxxgp zhaoxiaolong2020 outbreak-hui brotherstrong2 yawei666 winterxx taxuezcy yunfeiooo hailuo0112 sinead-li renzhihan sixgodgg shining-love arelax-zhu dyf-ai jiazhangke matu-46177 lightsalt2011 float123 xiededa irvingzhang0512 shikangouyang yuzhoupeng inez-chung rachel-kk tecsai zlannnn gaozheng-tech carlsummer kerry678231 fwd3 dzz95 baofengzan liufqing rocketwill csldali python-eric laster-lee xinsuinizhuan 18106574249 qianxunzdl123 lwj1980s iloveai8086 rainxuan2019 yinjiayang cvbuff xiaomujiang chenjunxia2030 xuanjiawangtensorrtcv's Issues
公众号文档中没有json 中yolo layer的写法,能帮忙提供一下吗?
公众号文档中没有json 中yolo layer的写法
加强版本什么时候出呢?比如:可视化?多输出?前后处理?
二三个月?
执行getweight.py这个脚本处理yolov5s.pt的时候报错 No module named 'models'?
我执行getweight.py脚本的时候报错, 只保存为.pth
if __name__ == '__main__':
#!将yolo5s.pt文件保存为yolov5s.pth文件
model = torch.load(path + 'yolov5s.pt')['model'].float()
torch.save(model.state_dict(), path + 'yolov5s.pth') #只保存模型权重参数,不保存模型结构
报错如下
(py38torch190-smoke) zxl@R9000P:~/mywork/tensorrtCV$ python getWeights_new.py
Traceback (most recent call last):
File "getWeights_new.py", line 67, in <module>
model = torch.load(path + 'yolov5s.pt')['model'].float()
File "/home/zxl/miniconda3/envs/py38torch190-smoke/lib/python3.8/site-packages/torch/serialization.py", line 607, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/home/zxl/miniconda3/envs/py38torch190-smoke/lib/python3.8/site-packages/torch/serialization.py", line 882, in _load
result = unpickler.load()
File "/home/zxl/miniconda3/envs/py38torch190-smoke/lib/python3.8/site-packages/torch/serialization.py", line 875, in find_class
return super().find_class(mod_name, name)
ModuleNotFoundError: No module named 'models'
这是什么原因呢? 我把下载下来的yolov5s.pt放在了model文件夹下,脚本的路径也对应修改了。
@sky 请问int8加速后,trt加速能进一步压缩显存占用?
trt怎样让其占用显存最小, int8之后有什么技术呢?
in ubuntu18.04 ,after change the trt path in cmakelist, then make, it has error
home//tensorrtCV/calibrator.cpp:125:61: error: expected primary-expression before ‘char’
copy(istream_iterator(input),istream_iterator(),back_inserter(m_CalibrationCache));
^~~~
CMakeFiles/tensorrtF.dir/build.make:108: recipe for target 'CMakeFiles/tensorrtF.dir/calibrator.cpp.o' failed
make[2]: *** [CMakeFiles/tensorrtF.dir/calibrator.cpp.o] Error 1
CMakeFiles/Makefile2:95: recipe for target 'CMakeFiles/tensorrtF.dir/all' failed
make[1]: *** [CMakeFiles/tensorrtF.dir/all] Error 2
Makefile:103: recipe for target 'all' failed
make: *** [all] Error 2
tks
通过getWeights.py 解析出的yolov3-tiny权重没有wts\\{anchor_grid}.wgt 文件
通过getWeights.py 解析出的yolov3-tiny权重没有wts\{anchor_grid}.wgt 文件 需要自己手动添加上吗?
reduce模块意思不是很懂 求解释
多个输出怎么修改呢?
cudaMemcpyAsync(output,m_bindings.at(outputIndex),batchsize * param.outputSize * 4, cudaMemcpyDeviceToHost,m_cudaStream)
upsample plugin怎么添加fp16相关实现?
upsample plugin如果打算支持fp16的话,如何修改代码呢?
is it support transfomer?
like LN and attention in transformer block?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.