Comments (5)
Now you can use the detection and classification and segmentation methods.
from torchcv.
Run 'make' in the PyTorchCV directory to build Cython scripts. But I am not sure OpenPose could be trained successfully, because I have refactored the code many times. And I will update it as soon as possible! Please keep your continuous attention!
from torchcv.
Thanks for your help!
After 'make' in the root path, there is still an issue about pycocotools. It shows
ModuleNotFoundError: No module named 'pycocotools'
But after I 'make' under the PythonAPI directory as the readme says, it is still there. Do you have any idea?
And if you could help with all the file holders needing 'make', it would help a lot.
solved:
under PythonAPI directory,
python3 setup.py install
New issue:
using
python main.py --hypes hypes/pose/coco/op_vgg19_coco_pose.json --base_lr 0.001 --phase train --gpu 0
Then it shows
'OpenPose' object has no attribute 'module'
Any idea?
from torchcv.
I will update OpenPose this week.
from torchcv.
Ok.
from torchcv.
Related Issues (20)
- 关于SFNet中Flow Field作用于Low Resolution Feature的细节问题 HOT 1
- Where can I find FAM? HOT 1
- about sfnet HOT 2
- Error compiling objects for extension
- Pytorch >1.3.0
- Where can download the pretrained model 3x3resnet18-imagenet.pth of sfnet HOT 2
- Question about the inference speed of SFNet HOT 7
- Question about the implementation of the AlignModule in SFNet HOT 1
- What is the mAP of your openpose model on coco val2017 dataset ?
- Weird memory allocation, leading to OOM easily. HOT 1
- SFNet pretrained model HOT 1
- When to write an reid project :>
- mIoU of SFNet is much lower than 78.9% HOT 19
- 将sfnet训练出来的pth模型转换成onnx模型应该怎么做 HOT 1
- train error HOT 2
- SFNET: what's difference between x,fpn_dsn? HOT 1
- 大佬能否更新一下repo啊 一看就是代码好久没更新了,训练各种bug, 代码尤其是cls_model对不齐,改了半天才跑起来
- AttributeError: 'RandomSampler' object has no attribute 'num_samples'
- 您好,《Spherical Criteria for Fast and Accurate 360◦Object Detection》论文的代码可以提供一下吗?
- RuntimeError: Given groups=1, weight of size [512, 1024, 3, 3], expected input[1, 256, 64, 64] to have 1024 channels, but got 256 channels instead
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.
from torchcv.