Implementation of ResMLP, an all MLP solution to image classification, in Pytorch

Overview

ResMLP - Pytorch

Implementation of ResMLP, an all MLP solution to image classification out of Facebook AI, in Pytorch

Install

$ pip install res-mlp-pytorch

Usage

import torch
from res_mlp_pytorch import ResMLP

model = ResMLP(
    image_size = 256,
    patch_size = 16,
    dim = 512,
    depth = 12,
    num_classes = 1000
)

img = torch.randn(1, 3, 256, 256)
pred = model(img) # (1, 1000)

Citations

@misc{touvron2021resmlp,
    title   = {ResMLP: Feedforward networks for image classification with data-efficient training}, 
    author  = {Hugo Touvron and Piotr Bojanowski and Mathilde Caron and Matthieu Cord and Alaaeldin El-Nouby and Edouard Grave and Armand Joulin and Gabriel Synnaeve and Jakob Verbeek and Hervé Jégou},
    year    = {2021},
    eprint  = {2105.03404},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
Issues
  • torch dataset example

    torch dataset example

    I wrote this examples with a data loader:

    import os
    import natsort
    from PIL import Image
    import torch
    import torchvision.transforms as T
    from res_mlp_pytorch.res_mlp_pytorch import ResMLP
    
    class LPCustomDataSet(torch.utils.data.Dataset):
        '''
            Naive Torch Image Dataset Loader
            with support for Image loading errors
            and Image resizing
        '''
        def __init__(self, main_dir, transform):
            self.main_dir = main_dir
            self.transform = transform
            all_imgs = os.listdir(main_dir)
            self.total_imgs = natsort.natsorted(all_imgs)
    
        def __len__(self):
            return len(self.total_imgs)
    
        def __getitem__(self, idx):
            img_loc = os.path.join(self.main_dir, self.total_imgs[idx])
            try:
                image = Image.open(img_loc).convert("RGB")
                tensor_image = self.transform(image)
                return tensor_image
            except:
                pass
                return None
    
        @classmethod
        def collate_fn(self, batch):
            '''
                Collate filtering not None images
            '''
            batch = list(filter(lambda x: x is not None, batch))
            return torch.utils.data.dataloader.default_collate(batch)
    
        @classmethod
        def transform(self,img):
            '''
                Naive image resizer
            '''
            transform = T.Compose([
                T.Resize(256),
                T.CenterCrop(224),
                T.ToTensor(),
                T.Normalize(
                    mean=[0.485, 0.456, 0.406],
                    std=[0.229, 0.224, 0.225]
                )
            ])
            return transform(img)
    

    to feed ResMLP:

    model = ResMLP(
        image_size = 256,
        patch_size = 16,
        dim = 512,
        depth = 12,
        num_classes = 1000
    )
    batch_size = 2
    my_dataset = LPCustomDataSet(os.path.join(os.path.dirname(
        os.path.abspath(__file__)), 'data'), transform=LPCustomDataSet.transform)
    train_loader = torch.utils.data.DataLoader(my_dataset , batch_size=batch_size, shuffle=False, 
                                   num_workers=4, drop_last=True, collate_fn=LPCustomDataSet.collate_fn)
    for idx, img in enumerate(train_loader):
        pred = model(img) # (1, 1000)
        print(idx, img.shape, pred.shape
    

    But I get this error

    RuntimeError: Given groups=1, weight of size [256, 256, 1], expected input[1, 196, 512] to have 256 channels, but got 196 channels instead
    

    not sure if LPCustomDataSet.transform has the correct for the input image

    opened by loretoparisi 3
Releases(0.0.6)
Owner
Phil Wang
Working with Attention.
Phil Wang
Implements MLP-Mixer: An all-MLP Architecture for Vision.

MLP-Mixer-CIFAR10 This repository implements MLP-Mixer as proposed in MLP-Mixer: An all-MLP Architecture for Vision. The paper introduces an all MLP (

Sayak Paul 25 Jun 10, 2021
Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision

MLP-Mixer: An all-MLP Architecture for Vision This repo contains PyTorch implementation of MLP-Mixer: An all-MLP Architecture for Vision. Usage : impo

Rishikesh (ऋषिकेश) 124 Jun 7, 2021
Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch is a Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration Deep neural networks b

null 48.8k Jun 13, 2021
Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch is a Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration Deep neural networks b

null 46.1k Feb 13, 2021
Accelerated deep learning R&D

Accelerated deep learning R&D PyTorch framework for Deep Learning research and development. It focuses on reproducibility, rapid experimentation, and

Catalyst-Team 2.6k Jun 13, 2021
An All-MLP solution for Vision, from Google AI

MLP Mixer - Pytorch An All-MLP solution for Vision, from Google AI, in Pytorch. No convolutions nor attention needed! Yannic Kilcher video Install $ p

Phil Wang 428 Jun 12, 2021
Geometric Deep Learning Extension Library for PyTorch

Documentation | Paper | Colab Notebooks | External Resources | OGB Examples PyTorch Geometric (PyG) is a geometric deep learning extension library for

Matthias Fey 11.3k Jun 13, 2021
ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

Overview | Tutorials | Examples | Installation | FAQ | How to Cite Welcome to ktrain News and Announcements 2020-11-08: ktrain v0.25.x is released and

Arun S. Maiya 834 Jun 12, 2021
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

TL;DR Ignite is a high-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently. Click on the image to

null 3.6k Jun 13, 2021
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

null 1.7k Jun 13, 2021
Implementation for paper MLP-Mixer: An all-MLP Architecture for Vision

MLP Mixer Implementation for paper MLP-Mixer: An all-MLP Architecture for Vision. Give us a star if you like this repo. Author: Github: bangoc123 Emai

Ngoc Nguyen Ba 45 Jun 14, 2021
Aerial Imagery dataset for fire detection: classification and segmentation (Unmanned Aerial Vehicle (UAV))

Aerial Imagery dataset for fire detection: classification and segmentation using Unmanned Aerial Vehicle (UAV) Title FLAME (Fire Luminosity Airborne-b

null 35 Jun 13, 2021
Unofficial Implementation of MLP-Mixer in TensorFlow

mlp-mixer-tf Unofficial Implementation of MLP-Mixer [abs, pdf] in TensorFlow. Note: This project may have some bugs in it. I'm still learning how to i

Rishabh Anand 19 Jun 10, 2021
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate. Website • Key Features • How To Use • Docs •

Pytorch Lightning 13.8k Jun 13, 2021