ruihangao / visual-tactile-synthesis Goto Github PK

We synthesize synchronized visual appearance and tactile geometry given a sketch of objects and render the multimodal output on a surface haptic device called TanvasTouch.

Home Page: https://visual-tactile-synthesis.github.io/

Python 99.84% Shell 0.16%

generative-model haptics multimodal-synthesis visual-tactile

visual-tactile-synthesis's People

Contributors

Stargazers

Watchers

Forkers

yuanmengzhixing nnzhangup peterzs flazerain jackzhousz mxmx0811

visual-tactile-synthesis's Issues

pip install Conflicts

Hi, thanks for sharing this work. I met severe pip installment conflicts that prevent me from installing some necessary packages. I used a new conda environment to install packages. The error message is shown below:

ERROR: Cannot install -r requirements.txt (line 18), -r requirements.txt (line 22) and -r requirements.txt (line 8) because these package versions have conflicting dependencies.

The conflict is caused by:
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 1.1 depends on torch<1.7.2 and >=1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 1.0.1 depends on torch<1.7.2 and >=1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.5 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.4 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.3 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.2 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.0 depends on torch==1.7.1

To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict

ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts

I followed the recommendation 2. and removed package versions, but pip still failed to solve the dependency conflict:

ERROR: Cannot install -r requirements.txt (line 18), -r requirements.txt (line 22) and -r requirements.txt (line 8) because these package versions have conflicting dependencies.

The conflict is caused by:
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 1.1 depends on torch<1.7.2 and >=1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 1.0.1 depends on torch<1.7.2 and >=1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.5 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.4 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.3 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1.2 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.1 depends on torch==1.7.1
    vision-aided-loss 0.1.0 depends on torch>=1.8.0
    torchmetrics 0.2.0 depends on torch>=1.3.1
    clip-by-openai 0.1.0 depends on torch==1.7.1

To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict

ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts

AttributeError: 'SinSKITGModel' object has no attribute 'metric_I_SIFID'

Hello,when I run material=BlackJeans
CUDA_VISIBLE_DEVICES=0 python train.py --gpu_ids 0 --name "${material}sinskitG_baseline_ours" --model sinskitG --dataroot ./datasets/"singleskit${material}_padded_1800_x1/",the following error occurred:
Preproccess data for singleskit_dataset and save them in cache, len 50...
Finish preprocessing 50 data, takes 111.22777891159058
len dataloader 50
Setting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off]
Loading model from: /home/wzp/anaconda3/envs/VTS/lib/python3.8/site-packages/lpips/weights/v0.1/vgg.pth
Define G network
num_downs 8
Initializing CustomUnetGenerator, ngf 10
Define D network
Define D2 network
model [SinSKITGModel] was created
The number of training images = 50
create web directory ./checkpoints/BluePants_sinskitG_baseline_ours/web...
total epoch opt.epoch_count 1 opt.n_epochs 5 opt.n_epochs_decay 400
check display opt params opt.print_freq 100 opt.display_freq 100
check test setting True
Start epoch 1
---------- Networks initialized -------------
[Network G] Total number of parameters : 1.466 M
[Network D] Total number of parameters : 0.135 M
[Network D2] Total number of parameters : 0.136 M

total_iters 50
can't get metric I_SIFID
Traceback (most recent call last):
File "/home/wzp/visual-tactile-synthesis-main/models/base_model.py", line 196, in get_current_metrics
metrics_ret['m_'+name] = float(getattr(self, 'metric_' + name))
AttributeError: 'SinSKITGModel' object has no attribute 'metric_I_SIFID'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 156, in
eval_metrics = model.get_current_metrics()
File "/home/wzp/visual-tactile-synthesis-main/models/base_model.py", line 199, in get_current_metrics
print("metric", getattr(self, 'metric_' + name))
AttributeError: 'SinSKITGModel' object has no attribute 'metric_I_SIFID'.
Could you tell me how to solve the problem?

asking for help

Hey, I want to use (checkpoints for baselines (21.5G): gdown "https://drive.google.com/uc?export=download&id=1vBd7awJJml5wDEp5gQGeyefpvilTOByw") this commend but it shows that the link acesss to 404. Could you please help me solve this problem? Thanks

Question about 'data_len'

Hi. May I ask if changing the value of 'data_len' to 100 will have any impact on the final rendering result?For example, does it have an impact on the ‘I_LPIPS’ indicator？

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.