All Projects → davidgengenbach → vgg-caffe

davidgengenbach / vgg-caffe

Licence: GPL-3.0 license
The VGG16 and VGG19 networks in caffe with jupyter notebook

Programming Languages

Jupyter Notebook
11667 projects
shell
77523 projects

Projects that are alternatives of or similar to vgg-caffe

Image-Classification
Pre-trained VGG-Net Model for image classification using tensorflow
Stars: ✭ 29 (-35.56%)
Mutual labels:  vgg16, vgg19
Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+5768.89%)
Mutual labels:  vgg16, vgg19
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+3004.44%)
Mutual labels:  vgg16
Deepfashion
Apparel detection using deep learning
Stars: ✭ 223 (+395.56%)
Mutual labels:  vgg16
Resnet Cifar10 Caffe
ResNet-20/32/44/56/110 on CIFAR-10 with Caffe
Stars: ✭ 161 (+257.78%)
Mutual labels:  vgg16
Image Caption Generator
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Stars: ✭ 126 (+180%)
Mutual labels:  vgg16
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (+333.33%)
Mutual labels:  vgg16
Alpha pooling
Code for our paper "Generalized Orderless Pooling Performs Implicit Salient Matching" published at ICCV 2017.
Stars: ✭ 51 (+13.33%)
Mutual labels:  vgg16
Retrieval 2017 Cam
Class-Weighted Convolutional Features for Image Retrieval (BMVC 2017)
Stars: ✭ 219 (+386.67%)
Mutual labels:  vgg16
Tensorflow Vgg16 Train And Test
The purpose of this program is for studying. Using tensorflow trains the vgg16 and recognizes only two kinds of picture(cat and dog).
Stars: ✭ 158 (+251.11%)
Mutual labels:  vgg16
Fcn For Semantic Segmentation
Implemention of FCN-8 and FCN-16 with Keras and uses CRF as post processing
Stars: ✭ 155 (+244.44%)
Mutual labels:  vgg16
Keras Vgg16 Places365
Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification
Stars: ✭ 138 (+206.67%)
Mutual labels:  vgg16
Freezeout
Accelerate Neural Net Training by Progressively Freezing Layers
Stars: ✭ 196 (+335.56%)
Mutual labels:  vgg16
Ds bowl 2018
Kaggle Data Science Bowl 2018
Stars: ✭ 116 (+157.78%)
Mutual labels:  vgg16
Dsfd.pytorch
DSFD implement with pytorch
Stars: ✭ 153 (+240%)
Mutual labels:  vgg16
Image Segmentation Fcn
Semantic Image Segmentation using a Fully Convolutional Neural Network in TensorFlow
Stars: ✭ 82 (+82.22%)
Mutual labels:  vgg16
Ssd Tensorflow
A Single Shot MultiBox Detector in TensorFlow
Stars: ✭ 169 (+275.56%)
Mutual labels:  vgg16
vgg16 batchnorm
VGG16 architecture with BatchNorm
Stars: ✭ 14 (-68.89%)
Mutual labels:  vgg16
tf-semantic-segmentation-FCN-VGG16
Semantic segmentation for classifying road. "Fully Convolutional Networks for Semantic Segmentation (2015)" implemented using TF
Stars: ✭ 30 (-33.33%)
Mutual labels:  vgg16
S3fd.pytorch
SFD implement with pytorch
Stars: ✭ 212 (+371.11%)
Mutual labels:  vgg16

VGG16 and VGG19 caffe net

Uses the VGG16 and VGG19 nets from the modelzoo. Minor changes in the *.prototxt to adapt it to the new caffe version.

See net.ipynb.

Instructions

# Download models 
wget --show-progress -P 'model/' 'http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel'
wget --show-progress -P 'model/' 'http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_19_layers.caffemodel'

# Convert models to new caffe format (caffe needed)
# (Not strictly needed. Removes deprecation notice)
upgrade_net_proto_binary MODEL.caffemodel MODEL.new.caffemodel

# Build docker image
docker build docker/ -t caffe-jupyter

# Start jupyter notebook
./docker/start-jupyter.sh

# Open browser at 127.0.0.1:8888
# Enter 'a' as the password to enter the jupyter env

# Maybe you have to adapt some paths to the models. See net.ipynb

# Docker terminal to image to execute "upgrade_net_proto_binary" etc. and run python files normally
docker run --entrypoint  --rm -v $(pwd):$(pwd) -w $(pwd) -it caffe-jupyter bash
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].