An executor that wraps 3D mesh models and encodes 3D content documents to d-dimension vector.

Last update: Dec 14, 2022

Related tags

Overview

3D Mesh Encoder

An Executor that receives Documents containing point sets data in its blob attribute, with shape (N, 3) and encodes it to embeddings of shape (D,). Now, the following pretrained models are ready to be used to create embeddings:

PointConv-Shapenet-d512: A PointConv model resulted in 512 dimension of embeddings, which is finetuned based on ShapeNet dataset.
PointConv-Shapenet-d1024: A PointConv model resulted in 1024 dimension of embeddings, which is finetuned based on ShapeNet dataset.

Usage

via Docker image (recommended)

from jina import Flow

f = Flow().add(uses='jinahub+docker://3DMeshEncoder', \
               uses_with={'pretrained_model': 'PointConv-Shapenet-d512'})

via source code

from jina import Flow

f = Flow().add(uses='jinahub://3DMeshEncoder', \
               uses_with={'pretrained_model': 'PointConv-Shapenet-d512'})

This Executor offers a GPU tag to speed up encoding. For more information on how to run the executor on GPU, check out the documentation.

How to finetune pretrained-model?

install finetuner

$ pip install finetuner

prepare dataset

TBD...

finetuning model with labeled dataset

$ python finetune.py --help

$ python finetune.py --model_name pointconv \
    --train_dataset /path/to/train.bin \
    --eval_dataset /path/to/eval.bin \
    --batch_size 128 \
    --epochs 50

finetuning model with unlabeled dataset

$ python finetune.py --model_name pointconv \
    --train_dataset /path/to/unlabeled_data.bin \
    --interactive

References

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
PointConv: Deep Convolutional Networks on 3D Point Clouds

Comments

which version should the `finetuner` module be?
I was preparing the environment of this repo. However, I found it confused that the python import code in finetune.py gives error message:

from finetuner.tuner.callback import BestModelCheckpoint from finetuner.tuner.pytorch.losses import TripletLoss from finetuner.tuner.pytorch.miner import TripletEasyHardMiner

It seems that there's no finetuner.tuner in finetuner module but finetuner.finetuner. Besides, callback/pytorch is not in finetuner.finetuner now.

Now my finetuner module installed by running pip install -U finetuner is 0.5.0. Is there any solution? Maybe you can freeze the version in requirements.txt.
opened by elenacliu 4
fix: fix previous structure

I got pretrain and finetune process mixed up, and previously I pretrained the models using finetune model structure, which might lead to worse results. The fix code is in process and may be finished in a few days.

opened by elenacliu 2
Add dataset, preprocess and pointnet2

Here is the modification of the structure. There are still some bugs in my pointnet2 codes. I will solve the possible problems after you comment.

@numb3r3 @jemmyshin

opened by elenacliu 1
In `farthest_point_sample` function, the first centroid sampled is not random.

I'm reading your codes.

https://github.com/jina-ai/executor-3d-encoder/blob/main/executor/models/modules.py#L75

The randint line is commented, but in the original implementation and the algorithm itself, it should be random? Maybe we can provide a fixed seed if we want to get the same result?

opened by elenacliu 1
Provide diffusion encoder

https://github.com/nmwsharp/diffusion-net

I'm unfamiliar with the jina ecosystem. So this is my first issue.

Final goal is to have dalle generate 3d digital human meshes like https://github.com/jina-ai/dalle-flow

opened by fire 2

Releases(v0.3.0)

v0.3.0(May 6, 2022)

Source code(tar.gz)
Source code(zip)
v0.2.0(Feb 21, 2022)

Source code(tar.gz)
Source code(zip)

Owner

Jina AI

A Neural Search Company. We provide the cloud-native neural search solution powered by state-of-the-art AI technology.

GitHub Repository

👷 Build images with images

👷 Build images with images. About Tiler is a tool to create an image using all kinds of other smaller images (tiles). It is different from other mosa

5.5k Jan 03, 2023

Glyph-graph - A simple, yet versatile, package for graphing equations on a 2-dimensional text canvas

Glyth Graph Revision for 0.01 A simple, yet versatile, package for graphing equations on a 2-dimensional text canvas List of contents: Brief Introduct

2 Oct 21, 2022

Kimimaro: Skeletonize Densely Labeled Images

Kimimaro: Skeletonize Densely Labeled Images # Produce SWC files from volumetric images. kimimaro forge labels.npy --progress # writes to ./kimimaro_o

92 Dec 17, 2022

A simple programme for converting url into a qr code (.png file)

QrTk A simple lightweight programme for converting url into a qr code (.png file) Pre-Requisites Before installing the programme , you need to run the

4 Nov 08, 2021

SimpleITK is an image analysis toolkit with a large number of components supporting general filtering operations, image segmentation and registration

672 Jan 05, 2023

CropImage is a simple toolkit for image cropping, detecting and cropping main body from pictures.

CropImage is a simple toolkit for image cropping, detecting and cropping main body from pictures. Support face and saliency detection.

15 Dec 22, 2022

Python Script to generate posters out of the images in directory.

Poster-Maker Python Script to generate posters out of the images in directory. This version is very basic ligthweight code to combine organize images

1 Feb 02, 2022

Computational Xmas Tree lights!

Computational Xmas Tree This repo contains the code for the computational illumination of a Christmas Tree! It is based on the work by Matt Parker fro

146 Dec 23, 2022

QSIprep: Preprocessing and analysis of q-space images

QSIprep: Preprocessing and analysis of q-space images Full documentation at https://qsiprep.readthedocs.io About qsiprep configures pipelines for proc

88 Dec 15, 2022

Bringing vtk.js into Dash and Python

Dash VTK Dash VTK lets you integrate the vtk.js visualization pipeline directly into your Dash app. It is powered by react-vtk-js. Docs Demo Explorer

88 Nov 29, 2022

Avatar Generator Python

This is a simple avatar generator project which uses your webcam to take pictures and saves five different types of your images into your device including the original image.

3 Jan 23, 2022

With this simple py script you will be able to get all the .png from a folder and generate a yml for Oraxen

Oraxen-item-to-yml With this simple py script you will be able to get all the .png from a folder and generate a yml for Oraxen How to use Install the

1 Dec 29, 2021

Script for the creation of metadatas and the randomization of images of MekaVerse

MekaVerse-random Script for the creation of metadata and the randomization of images of MekaVerse Step to replay the random : Create a folder : output

8 Sep 07, 2022

Plots is a graph plotting app for GNOME.

Plots is a graph plotting app for GNOME. Plots makes it easy to visualise mathematical formulae. In addition to basic arithmetic operations, it supports trigonometric, hyperbolic, exponential and log

138 Dec 14, 2022

Extracts dominating colors from an image and presents them as a palette.

ColorPalette A simple web app to extract dominant colors from an image. Demo Live View it live at : https://colorpalettedemo.herokuapp.com/ You can de

214 Dec 29, 2022

Python library for ascii graphics

6 Oct 20, 2021

An ascii art generator that's actually good. Does edge detection and selects the most appropriate characters.

Ascii Artist An ascii art generator that's actually good. Does edge detection and selects the most appropriate characters. Installing Installing with

18 Jan 03, 2023

Python avatar generator for absolute nerds

pagan Welcome to the Python Avatar Generator for Absolute Nerds. Current version: 0.4.3 View the change history here. Remember those good old days whe

280 Dec 16, 2022

A Blender add-on to create interesting meshes using symmetry

Procedural Symmetries This Blender add-on automates the process of iteratively applying a set of reflection planes to a base mesh. The result will con