princetonlips / vitruvion Goto Github PK
View Code? Open in Web Editor NEWCode and data for Vitruvion: A Generative Model of Parametric CAD Sketches (ICLR 2022)
Code and data for Vitruvion: A Generative Model of Parametric CAD Sketches (ICLR 2022)
Thank you for opening your code.
How do I enter a sketch picture I draw by hand into your network and get visual network predictions?
Thanks for your contribution, this is an inspiring work! But when I try to run training and evaluation in my own conda environment, I run into some problems that I want you to help me.
As we konw, sketchgraphs.data is mentioned in many programs, for example in the /vitruvion/img2cad/constraint_data.py there are import _sketchgraphs.data as datalib
and from sketchgraphs.data import flat_array
, but here is no folder named data in the vitruvion/sketchgraphs/directory in this github project.
This seems to be resolved by downloading the file in SketchGraphs, and it is true for some parts of the code, but there seems to be no ConstructionSequence, and I would like to know how to find or retrieve this file, thank you for your focus!
/vitruvion/img2cad/constraint_data.py
import sketchgraphs.data as datalib
def tokenize_constraints(seq: datalib.ConstructionSequence, gather_idxs: Sequence[int], max_length: Optional[int]=None):
When I run python -m img2cad.evaluation.evaluate_constraints checkpoint_path=models/constraints.ckpt sequence_path=data/sg_filtered_unique.npy
, I will get
File "****/code/vitruvion/img2cad/constraint_data.py", line 67, in <module>
def tokenize_constraints(seq: datalib.ConstructionSequence, gather_idxs: Sequence[int], max_length: Optional[int]=None):
AttributeError: module 'sketchgraphs.data' has no attribute 'ConstructionSequence'
Hi,
I am trying to reimplement the sketch autocomplete results in Table 2. It seems we can only do the process_single_sketch
one sample each iteration, which caused the autocompletion super slow. Is there any way we can do that paralleled?
Best
Hi, thanks for your interesting and impressive work!
I'm curious about what can be the possible reasons that I'm getting a low-score for re-training image-to-primitive model. All the hyperparameters were the same with the original model and I adapted your slurm script to run the model on a similar setup (4 v100 gpus). Final accuracy for the image to primitive model was around 0.47.
I used the following slurm script to retrain the model.
#!/bin/bash -l
#SBATCH -p gpu
#SBATCH -N 1
#SBATCH --gpus=4
#SBATCH --constraint=volta32
#SBATCH --job-name train_image_to_primitive
#SBATCH --time=24:00:00
source activate vitruvion
python -m img2cad.train_image_to_primitive +cluster=akaradeniz +compute=4xv100 batch_size=2048
These are the graphs from the training logs:
Thank you in advance!
Hi, thank you for this really interesting project! I was hoping for some assistance..
I have downloaded all the required files into the project but have been unable to inference with the models.
Could you please providea step by step tutorial to help transform an input sketch (hand drawn image) to the network for obtaining either a vector or a CAD file?
For the mentioned error, here is the terminal log -
(vitruvion) sid@e2e-62-76:~/vitruvion/vitruvion$ ./start_singularity.sh python -m img2cad.evaluation.evaluate_image_to_primitive checkpoint_path=models/image_to_primitive.ckpt sequence_path=data/sg_filtered_unique.npy
=============
== PyTorch ==
=============
NVIDIA Release 21.03 (build 21060478)
PyTorch Version 1.9.0a0+df837d0
Container image Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
Copyright (c) 2014-2021 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006 Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015 Google Inc.
Copyright (c) 2015 Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.
NVIDIA Deep Learning Profiler (dlprof) Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
Various files include modifications (c) NVIDIA CORPORATION. All rights reserved.
This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
NOTE: MOFED driver for multi-node communication was not detected.
Multi-node communication performance may be reduced.
Traceback (most recent call last):
File "/opt/conda/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/opt/conda/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/sid/vitruvion/vitruvion/img2cad/evaluation/evaluate_image_to_primitive.py", line 18, in <module>
from img2cad import dataset, primitives_data, primitives_models
File "/home/sid/vitruvion/vitruvion/img2cad/dataset.py", line 28, in <module>
import sketchgraphs.data as datalib
ModuleNotFoundError: No module named 'sketchgraphs.data'
Hope you can share a response soon, would appreciate being able to replicate this project.
Also curious - under what license has the project has been released? I cannot seem to find it in the description.
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.