ivalab / affkpnet Goto Github PK
View Code? Open in Web Editor NEWThe implementation and supplementary material for our RA-L work "An Affordance Keypoint Detection Network for Robot Manipulation".
The implementation and supplementary material for our RA-L work "An Affordance Keypoint Detection Network for Robot Manipulation".
First of all, I tried python==3.6 and follow the step of configuring the environment of maskrcnn-benchmark
as mentioned, when I succeded with the environment of maskrcnn-benchmark
, I returned to this project and tried to install
cd AffKpNet
python setup.py install
however, it told me that python version must>=3.8
so then,
I used python==3.8, torch==1.6.0, torchvision==0.7.0, cudatoolkit=10.1
and followed the steps of maskrcnn-benchmark
as well. It compiles successful, However, when it comes to execute the code, there is always some errors
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
how should I do? I have no idea.
The viewer won't be able to make to make any sense of the images with affordance labels like 0.0, 1.0, etc.
Especially for the out-of-distribution content. I have no idea what is going on, nor what is being shown. Truly, the page could be tossed out and nothing would change.
Please make an effort to add in information that a first time reader might not be fully aware of. For sure the numeric labeling of the affordance is meaningless to most people. The more someon has to think, the less likely they are to actually understand what you wish to convey. All results should be clear and obvious. Otherwise, you are not effectively communicating anything to the reader.
Leave this open until I am/we are happy with the messaging of the different supplementary content files.
Hello!
Thanks for sharing your dataset! I wanted to ask whether you had any information on the camera intrinsics/extrinsics for images? In your paper you mentioned that you used a Intel Realsense and Kinect, could you share specifically which models of those cameras you used?
Thanks!
An error occurs when the dataset is about to finish downloading
Could you please tell me how to solve "subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1."
When I try to run the evaluate code with command
CUDA_VISIBLE_DEVICES=0 python eval_aff_mask.py --dataset umd_self_kp --model danet_kp --resume-dir /danet_kp/umd_gt/model --base-size 480 --crop-size 480 --workers 1 --backbone resnet101 --multi-grid --multi-dilation 4 8 16 --eval
I got the error as below
Traceback (most recent call last):
File "eval_aff_mask.py", line 19, in <module>
import encoding.utils as utils
File "/root/anaconda3/lib/python3.8/site-packages/torch_encoding-1.2.2b20220804-py3.8.egg/encoding/__init__.py", line 13, in <module>
from . import nn, functions, dilated, parallel, utils, models, datasets
File "/root/anaconda3/lib/python3.8/site-packages/torch_encoding-1.2.2b20220804-py3.8.egg/encoding/nn/__init__.py", line 12, in <module>
from .encoding import *
File "/root/anaconda3/lib/python3.8/site-packages/torch_encoding-1.2.2b20220804-py3.8.egg/encoding/nn/encoding.py", line 19, in <module>
from ..functions import scaledL2, aggregate, pairwise_cosine
File "/root/anaconda3/lib/python3.8/site-packages/torch_encoding-1.2.2b20220804-py3.8.egg/encoding/functions/__init__.py", line 2, in <module>
from .encoding import *
File "/root/anaconda3/lib/python3.8/site-packages/torch_encoding-1.2.2b20220804-py3.8.egg/encoding/functions/encoding.py", line 14, in <module>
from .. import lib
File "/root/anaconda3/lib/python3.8/site-packages/torch_encoding-1.2.2b20220804-py3.8.egg/encoding/lib/__init__.py", line 9, in <module>
cpu = load('enclib_cpu', [
File "/root/anaconda3/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1202, in load
return _jit_compile(
File "/root/anaconda3/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1425, in _jit_compile
_write_ninja_file_and_build_library(
File "/root/anaconda3/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1506, in _write_ninja_file_and_build_library
verify_ninja_availability()
File "/root/anaconda3/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1562, in verify_ninja_availability
raise RuntimeError("Ninja is required to load C++ extensions")
RuntimeError: Ninja is required to load C++ extensions
Could you help me find out where is the problem?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.