yihui-he / Resnet Cifar10 Caffe
Licence: mit
ResNet-20/32/44/56/110 on CIFAR-10 with Caffe
Stars: ✭ 161
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Resnet Cifar10 Caffe
Resnet On Cifar10
Reimplementation ResNet on cifar10 with caffe
Stars: ✭ 123 (-23.6%)
Mutual labels: caffe, resnet, cifar10
Cnn Models
ImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (+120.5%)
Mutual labels: caffe, resnet, vgg16
Vgg16 Pytorch
VGG16 Net implementation from PyTorch Examples scripts for ImageNet dataset
Stars: ✭ 26 (-83.85%)
Mutual labels: resnet, vgg16
Bsconv
Reference implementation for Blueprint Separable Convolutions (CVPR 2020)
Stars: ✭ 84 (-47.83%)
Mutual labels: resnet, cifar10
Grad Cam Tensorflow
tensorflow implementation of Grad-CAM (CNN visualization)
Stars: ✭ 261 (+62.11%)
Mutual labels: resnet, vgg16
Jacinto Ai Devkit
Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-69.57%)
Mutual labels: caffe, resnet
caffe-wrn-generator
Caffe Wide-Residual-Network (WRN) Generator
Stars: ✭ 19 (-88.2%)
Mutual labels: caffe, resnet
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+767.7%)
Mutual labels: resnet, vgg16
Pytorch Classification
Classification with PyTorch.
Stars: ✭ 1,268 (+687.58%)
Mutual labels: resnet, cifar10
Resnet Imagenet Caffe
train resnet on imagenet from scratch with caffe
Stars: ✭ 105 (-34.78%)
Mutual labels: caffe, resnet
ReZero-ResNet
Unofficial pytorch implementation of ReZero in ResNet
Stars: ✭ 23 (-85.71%)
Mutual labels: resnet, cifar10
Classification Nets
Implement popular models by different DL framework. Such as tensorflow and caffe
Stars: ✭ 17 (-89.44%)
Mutual labels: caffe, cifar10
Resnet
Tensorflow ResNet implementation on cifar10
Stars: ✭ 10 (-93.79%)
Mutual labels: resnet, cifar10
Caffe Model
Caffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+681.37%)
Mutual labels: caffe, resnet
Pytorch Speech Commands
Speech commands recognition with PyTorch
Stars: ✭ 128 (-20.5%)
Mutual labels: resnet, cifar10
ResNet 20/32/44/56/110 for CIFAR10 with caffe
Testing
~/caffe/build/tools/caffe test -gpu 0 -iterations 100 -model resnet-20/trainval.prototxt -weights resnet-20/snapshot/solver_iter_64000.caffemodel
Model | Acc | Claimed Acc |
---|---|---|
ResNet-20 | 91.4% | 91.25% |
ResNet-32 | 92.48% | 92.49% |
ResNet-44 | % | 92.83% |
ResNet-56 | 92.9% | 93.03% |
ResNet-110 | % | 93.39% |
Citation
If you find the code useful in your research, please consider citing:
@InProceedings{He_2017_ICCV,
author = {He, Yihui and Zhang, Xiangyu and Sun, Jian},
title = {Channel Pruning for Accelerating Very Deep Neural Networks},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}
Training
#build caffe
git clone https://github.com/yihui-he/resnet-cifar10-caffe
./download_cifar.sh
./train.sh [GPUs] [NET]
#eg., ./train.sh 0 resnet-20
#find logs at resnet-20/logs
Visualization
specify caffe path in cfgs.py and use plot.py to generate beautful loss plots.
python plot.py PATH/TO/LOGS
Results are consistent with original paper. seems there's no much difference between resnet-20 and plain-20. However, from the second plot, you can see that plain-110 have difficulty to converge.
How I generate prototxts:
use net_generator.py to generate solver.prototxt
and trainval.prototxt
, you can generate resnet or plain net of depth 20/32/44/56/110, or even deeper if you want. you just need to change n
according to depth=6n+2
How I generate lmdb data:
./create_cifar.sh
create 4 pixel padded training LMDB and testing LMDB, then create a soft link ln -s cifar-10-batches-py
in this folder.
- get cifar10 python version
- use data_utils.py to generate 4 pixel padded training data and testing data. Horizontal flip and random crop are performed on the fly while training.
Other models in Caffe
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].