princetonlips / vitruvion Goto Github PK

Code and data for Vitruvion: A Generative Model of Parametric CAD Sketches (ICLR 2022)

Jupyter Notebook 75.09% Dockerfile 0.01% Shell 0.55% Python 24.35%

vitruvion's Issues

Manually drawn pictures are sent to the network

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?

AttributeError: module 'sketchgraphs.data' has no attribute 'ConstructionSequence'

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'

Can we do sketch autocomplete on sample_primitives_primed paralleled?

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

Retraining image to primitive model

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!

ModuleNotFoundError: No module named 'sketchgraphs.data'

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.

princetonlips / vitruvion Goto Github PK

vitruvion's Issues

Manually drawn pictures are sent to the network

AttributeError: module 'sketchgraphs.data' has no attribute 'ConstructionSequence'

Can we do sketch autocomplete on sample_primitives_primed paralleled?

Retraining image to primitive model

ModuleNotFoundError: No module named 'sketchgraphs.data'

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent