Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/RBirkeland/MVCNN-PyTorch

3d deep-learning neural-network pytorch resnet

Last synced: about 2 months ago
JSON representation

Host: GitHub
URL: https://github.com/RBirkeland/MVCNN-PyTorch
Owner: RBirkeland
License: mit
Created: 2018-05-15T10:05:18.000Z (over 6 years ago)
Default Branch: master
Last Pushed: 2019-02-19T14:26:49.000Z (over 5 years ago)
Last Synced: 2024-07-22T04:34:01.873Z (2 months ago)
Topics: 3d, deep-learning, neural-network, pytorch, resnet
Language: Python
Size: 29.3 KB
Stars: 99
Watchers: 4
Forks: 32
Open Issues: 5
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # MVCNN-PyTorch

## Multi-View CNN built on ResNet/AlexNet to classify 3D objects

A PyTorch implementation of MVCNN using ResNet, inspired by the paper by [Hang Su](http://vis-www.cs.umass.edu/mvcnn/docs/su15mvcnn.pdf).

MVCNN uses multiple 2D images of 3D objects to classify them. You can use the provided dataset or create your own.

Also check out my [RotationNet](https://github.com/RBirkeland/RotationNet) implementation whitch outperforms MVCNN (Under construction).

![MVCNN](https://preview.ibb.co/eKcJHy/687474703a2f2f7669732d7777772e63732e756d6173732e6564752f6d76636e6e2f696d616765732f6d76636e6e2e706e67.png)

### Dependencies

* torch

* torchvision

* numpy

* tensorflow (for logging)

### Dataset

ModelNet40 12-view PNG dataset can be downloaded from [Google Drive](https://drive.google.com/file/d/0B4v2jR3WsindMUE3N2xiLVpyLW8/view).

You can also create your own 2D dataset from 3D objects (.obj, .stl, and .off), using [BlenderPhong](https://github.com/WeiTang114/BlenderPhong)

### Setup

```bash

mkdir checkpoint

mkdir logs

```

### Train

To start training, simply point to the path of the downloaded dataset. All the other settings are optional.

```

python controller.py   [--depth N] [--model MODEL] [--epochs N] [-b N]

                                        [--lr LR] [--momentum M] [--lr-decay-freq W]

                                        [--lr-decay W] [--print-freq N] [-r PATH] [--pretrained]

```

To resume from a checkpoint, use the -r tag together with the path to the checkpoint file.

### Tensorboard

To view training logs

```

tensorboard --logdir='logs' --port=6006

```