Reproduce ResNet-v2(Identity Mappings in Deep Residual Networks) with MXNet

Related tags

Deep LearningResNet
Overview

Reproduce ResNet-v2 using MXNet

Requirements

  • Install MXNet on a machine with CUDA GPU, and it's better also installed with cuDNN v5
  • Please fix the randomness if you want to train your own model and using this pull request

Trained models

The trained ResNet models achieve better error rates than the original ResNet-v1 models.

ImageNet 1K

Imagenet 1000 class dataset with 1.2 million images.

single center crop (224x224) validation error rate(%)

Network Top-1 error Top-5 error Traind Model
ResNet-18 30.48 10.92 data.dmlc.ml
ResNet-34 27.20 8.86 data.dmlc.ml
ResNet-50 24.39 7.24 data.dmlc.ml
ResNet-101 22.68 6.58 data.dmlc.ml
ResNet-152 22.25 6.42 data.dmlc.ml
ResNet-200 22.14 6.16 data.dmlc.ml

ImageNet 11K:

Full imagenet dataset: fall11_whole.tar from http://www.image-net.org/download-images.

We removed classes with less than 500 images. The filtered dataset contains 11221 classes and 12.4 millions images. We randomly pick 50 images from each class as the validation set. The split is available at http://data.dmlc.ml/mxnet/models/imagenet-11k/

Network Top-1 error Top-5 error Traind Model
ResNet-200 58.4 28.8

cifar10: single crop validation error rate(%):

Network top-1
ResNet-164 4.68

Training Curve

The following curve is ResNet-v2 trainined on imagenet-1k, all the training detail you can found here, which include gpu information, lr schedular, batch-size etc, and you can also see the training speed with the corresponding logs.

you can get the curve by run:
cd log && python plot_curve.py --logs=resnet-18.log,resnet-34.log,resnet-50.log,resnet-101.log,resnet-152.log,resnet-200.log

How to Train

imagenet

first you should prepare the train.lst and val.lst, you can generate this list files by yourself(please ref.make-the-image-list, and do not forget to shuffle the list files!), or just download the provided version from here.

then you can create the *.rec file, i recommend use this cmd parameters:

$im2rec_path train.lst train/ data/imagenet/train_480_q90.rec resize=480 quality=90

set resize=480 and quality=90(quality=100 will be best i think:)) here may use more disk memory(about ~103G), but this is very useful with scale augmentation during training[1][2], and can help reproducing a good result.

because you are training imagenet , so we should set data-type = imagenet, then the training cmd is like this(here i use 6 gpus for training):

python -u train_resnet.py --data-dir data/imagenet \
--data-type imagenet --depth 50 --batch-size 256  --gpus=0,1,2,3,4,5

change depth to different number to support different model, currently support ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152, ResNet-200.

cifar10

same as above, first you should use im2rec to create the .rec file, then training with cmd like this:

python -u train_resnet.py --data-dir data/cifar10 --data-type cifar10 \
  --depth 164 --batch-size 128 --num-examples 50000 --gpus=0,1

change depth when training different model, only support(depth-2)%9==0, such as RestNet-110, ResNet-164, ResNet-1001...

retrain

When training large dataset(like imagenet), it's better for us to change learning rate manually, or the training is killed by some other reasons, so retrain is very important. the code here support retrain, suppose you want to retrain your resnet-50 model from epoch 70 and want to change lr=0.0005, wd=0.001, batch-size=256 using 8gpu, then you can try this cmd:

python -u train_resnet.py --data-dir data/imagenet --data-type imagenet --depth 50 --batch-size 256 \
--gpus=0,1,2,3,4,5,6,7 --model-load-epoch=70 --lr 0.0005 --wd 0.001 --retrain

Notes

  • it's better training the model in imagenet with epoch > 110, because this will lead better result.
  • when epoch is about 95, cancel the scale/color/aspect augmentation during training, this can be done by only comment out 6 lines of the code, like this:
train = mx.io.ImageRecordIter(
        # path_imgrec         = os.path.join(args.data_dir, "train_480_q90.rec"),
        path_imgrec         = os.path.join(args.data_dir, "train_256_q90.rec"),
        label_width         = 1,
        data_name           = 'data',
        label_name          = 'softmax_label',
        data_shape          = (3, 32, 32) if args.data_type=="cifar10" else (3, 224, 224),
        batch_size          = args.batch_size,
        pad                 = 4 if args.data_type == "cifar10" else 0,
        fill_value          = 127,  # only used when pad is valid
        rand_crop           = True,
        # max_random_scale    = 1.0 if args.data_type == "cifar10" else 1.0,  # 480
        # min_random_scale    = 1.0 if args.data_type == "cifar10" else 0.533,  # 256.0/480.0
        # max_aspect_ratio    = 0 if args.data_type == "cifar10" else 0.25,
        # random_h            = 0 if args.data_type == "cifar10" else 36,  # 0.4*90
        # random_s            = 0 if args.data_type == "cifar10" else 50,  # 0.4*127
        # random_l            = 0 if args.data_type == "cifar10" else 50,  # 0.4*127
        rand_mirror         = True,
        shuffle             = True,
        num_parts           = kv.num_workers,
        part_index          = kv.rank)

but you should prepare one train_256_q90.rec using im2rec like:

$im2rec_path train.lst train/ data/imagenet/train_256_q90.rec resize=256 quality=90

cancel this scale/color/aspect augmentation can be done easily by using --aug-level=1 in your cmd.

  • it's better for running longer than 30 epoch before first decrease the lr(such as 60), so you may decide the epoch number by observe the val-acc curve, and set lr with retrain.

Training ResNet-200 by only one gpu with 'dark knowledge' of mxnet

you can training ResNet-200 or even ResNet-1000 on imaget with only one gpu! for example, we can train ResNet-200 with batch-size=128 on one gpu(=12G), or if your gpu memory is less than 12G, you should decrease the batch-size by a little. here is the way of how to using 'dark knowledge' of mxnet:

when turn on memonger, the trainning speed will be about 25% slower, but we can training more depth network, have fun!

ResNet-v2 vs ResNet-v1

Does ResNet-v2 always achieve better result than ResNet-v1 on imagnet? The answer is NO, ResNet-v2 has no advantage or even has disadvantage than ResNet-v1 when depth<152, we can get the following result from paper[2].(why?)

ImageNet: single center crop validation error rate(%)

Network crop-size top-1 top-5
ResNet-101-v1 224x224 23.6 7.1
ResNet-101-v2 224x224 24.6 7.5
ResNet-152-v1 320x320 21.3 5.5
ResNet-152-v2 320x320 21.1 5.5

we can see that:

  • when depth=101, ResNet-v2 is 1% worse than ResNet-v1 on top-1 and 0.4% worse on top-5.
  • when depth=152, ResNet-v2 is only 0.2% better than ResNet-v1 on top-1 and owns the same performance on top-5 even when crop-size=320x320.

How to use Trained Models

we can use the pre-trained model to classify one input image, the step is easy:

  • download the pre-trained model form data.dml.ml and put it into the predict directory.
  • cd predict and run python -u predict.py --img test.jpg --prefix resnet-50 --gpu 0, this means you want to recgnition test.jpg using model resnet-50-0000.params and gpu 0, then it will output the classification result.

Reference

[1] Kaiming He, et al. "Deep Residual Learning for Image Recognition." arXiv arXiv:1512.03385 (2015).
[2] Kaiming He, et al. "Identity Mappings in Deep Residual Networks" arXiv:1603.05027 (2016).
[3] caffe official training code and model, https://github.com/KaimingHe/deep-residual-networks
[4] torch training code and model provided by facebook, https://github.com/facebook/fb.resnet.torch
[5] MXNet resnet-v1 cifar10 examples,https://github.com/dmlc/mxnet/blob/master/example/image-classification/train_cifar10_resnet.py

Owner
Wei Wu
Wei Wu
Semi-supervised Domain Adaptation via Minimax Entropy

Semi-supervised Domain Adaptation via Minimax Entropy (ICCV 2019) Install pip install -r requirements.txt The code is written for Pytorch 0.4.0, but s

Vision and Learning Group 243 Jan 09, 2023
PyTorch implementation of ICLR 2022 paper PiCO: Contrastive Label Disambiguation for Partial Label Learning

PiCO: Contrastive Label Disambiguation for Partial Label Learning This is a PyTorch implementation of ICLR 2022 paper PiCO: Contrastive Label Disambig

王皓波 147 Jan 07, 2023
Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)

Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble This is the code for reproducing the results of the paper Uncertainty-Bas

43 Nov 23, 2022
U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Xuebin Qin 6.5k Jan 09, 2023
The Official Repository for "Generalized OOD Detection: A Survey"

Generalized Out-of-Distribution Detection: A Survey 1. Overview This repository is with our survey paper: Title: Generalized Out-of-Distribution Detec

Jingkang Yang 338 Jan 03, 2023
Official implementation of the Neurips 2021 paper Searching Parameterized AP Loss for Object Detection.

Parameterized AP Loss By Chenxin Tao, Zizhang Li, Xizhou Zhu, Gao Huang, Yong Liu, Jifeng Dai This is the official implementation of the Neurips 2021

46 Jul 06, 2022
Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)

Deep Networks from the Principle of Rate Reduction This repository is the official NumPy implementation of the paper Deep Networks from the Principle

Ryan Chan 49 Dec 16, 2022
Study of human inductive biases in CNNs and Transformers.

Are Convolutional Neural Networks or Transformers more like human vision? This repository contains the code and fine-tuned models of popular Convoluti

Shikhar Tuli 39 Dec 08, 2022
Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks

Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks This is a Pytorch-Lightning implementation of the paper "Self-s

Photogrammetry & Robotics Bonn 111 Dec 06, 2022
Fair Recommendation in Two-Sided Platforms

Fair Recommendation in Two-Sided Platforms

gourabgggg 1 Nov 10, 2021
VideoGPT: Video Generation using VQ-VAE and Transformers

VideoGPT: Video Generation using VQ-VAE and Transformers [Paper][Website][Colab][Gradio Demo] We present VideoGPT: a conceptually simple architecture

Wilson Yan 470 Dec 30, 2022
LogDeep is an open source deeplearning-based log analysis toolkit for automated anomaly detection.

LogDeep is an open source deeplearning-based log analysis toolkit for automated anomaly detection.

donglee 279 Dec 13, 2022
《Improving Unsupervised Image Clustering With Robust Learning》(2020)

Improving Unsupervised Image Clustering With Robust Learning This repo is the PyTorch codes for "Improving Unsupervised Image Clustering With Robust L

Sungwon Park 129 Dec 27, 2022
Various operations like path tracking, counting, etc by using yolov5

Object-tracing-with-YOLOv5 Various operations like path tracking, counting, etc by using yolov5

Pawan Valluri 5 Nov 28, 2022
Cross-modal Deep Face Normals with Deactivable Skip Connections

Cross-modal Deep Face Normals with Deactivable Skip Connections Victoria Fernández Abrevaya*, Adnane Boukhayma*, Philip H. S. Torr, Edmond Boyer (*Equ

72 Nov 27, 2022
Implementation of Nalbach et al. 2017 paper.

Deep Shading Convolutional Neural Networks for Screen-Space Shading Our project is based on Nalbach et al. 2017 paper. In this project, a set of buffe

Marcel Santana 17 Sep 08, 2022
CLOOB training (JAX) and inference (JAX and PyTorch)

cloob-training Pretrained models There are two pretrained CLOOB models in this repo at the moment, a 16 epoch and a 32 epoch ViT-B/16 checkpoint train

Katherine Crowson 64 Nov 27, 2022
PPO Lagrangian in JAX

PPO Lagrangian in JAX This repository implements PPO in JAX. Implementation is tested on the safety-gym benchmark. Usage Install dependencies using th

Karush Suri 2 Sep 14, 2022
An example showing how to use jax to train resnet50 on multi-node multi-GPU

jax-multi-gpu-resnet50-example This repo shows how to use jax for multi-node multi-GPU training. The example is adapted from the resnet50 example in d

Yangzihao Wang 20 Jul 04, 2022
Deeprl - Standard DQN and dueling network for simple games

DeepRL This code implements the standard deep Q-learning and dueling network with experience replay (memory buffer) for playing simple games. DQN algo

Yao Zhou 6 Apr 12, 2020