twtygqyy / Caffe Augmentation
Licence: other
Data Augmentation for Caffe
Stars: ✭ 178
Labels
Projects that are alternatives of or similar to Caffe Augmentation
Splitbrainauto
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction. In CVPR, 2017.
Stars: ✭ 137 (-23.03%)
Mutual labels: caffe
Deformable Convnets Caffe
Deformable Convolutional Networks on caffe
Stars: ✭ 166 (-6.74%)
Mutual labels: caffe
Anomaly Detection In Surveillance Videos
Real-World Anomaly Detection in Surveillance Videos
Stars: ✭ 139 (-21.91%)
Mutual labels: caffe
Caffe Mobilenet
A caffe implementation of mobilenet's depthwise convolution layer.
Stars: ✭ 146 (-17.98%)
Mutual labels: caffe
Py Rfcn Priv
code for py-R-FCN-multiGPU maintained by bupt-priv
Stars: ✭ 153 (-14.04%)
Mutual labels: caffe
Facerecognition
This is an implematation project of face detection and recognition. The face detection using MTCNN algorithm, and recognition using LightenenCNN algorithm.
Stars: ✭ 137 (-23.03%)
Mutual labels: caffe
Video Caffe
Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
Stars: ✭ 172 (-3.37%)
Mutual labels: caffe
Turkce Yapay Zeka Kaynaklari
Türkiye'de yapılan derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) çalışmalarının derlendiği sayfa.
Stars: ✭ 1,900 (+967.42%)
Mutual labels: caffe
Nnef Tools
The NNEF Tools repository contains tools to generate and consume NNEF documents
Stars: ✭ 165 (-7.3%)
Mutual labels: caffe
Mobilenet Ssd
Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
Stars: ✭ 1,805 (+914.04%)
Mutual labels: caffe
Ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+7414.61%)
Mutual labels: caffe
Resnet Cifar10 Caffe
ResNet-20/32/44/56/110 on CIFAR-10 with Caffe
Stars: ✭ 161 (-9.55%)
Mutual labels: caffe
Caffe Segnet Cudnn5
This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet (https://github.com/alexgkendall/caffe-segnet) to run SegNet with cuDNN version 5.
Stars: ✭ 167 (-6.18%)
Mutual labels: caffe
Flownet2 Docker
Dockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)
Stars: ✭ 137 (-23.03%)
Mutual labels: caffe
Sphereface Plus
SphereFace+ Implementation for <Learning towards Minimum Hyperspherical Energy> in NIPS'18.
Stars: ✭ 151 (-15.17%)
Mutual labels: caffe
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+0.56%)
Mutual labels: caffe
Caffe Augmentation Extension
This is a modified caffe fork (version of 2017/3/10) with ImageData layer data augmentation, which is based on:
@kevinlin311tw's caffe-augmentation, @ChenlongChen's caffe-windows, @ShaharKatz's Caffe-Data-Augmentation, @senecaur's caffe-rta. @kostyaev's caffe-augmentation
min_side_min nad min_side_max are added for random cropping while keeping the aspect ratio, as mentioned in "Deep Residual Learning for Image Recognition"(http://arxiv.org/abs/1512.03385)
and all functions
- min_side - resize and crop preserving aspect ratio, default 0 (disabled);
- max_rotation_angle - max angle for an image rotation, default 0;
- contrast_brightness_adjustment - enable/disable contrast adjustment, default false;
- smooth_filtering - enable/disable smooth filterion, default false;
- min_contrast - min contrast multiplier (min alpha), default 0.8;
- max_contrast - min contrast multiplier (max alpha), default 1.2;
- max_brightness_shift - max brightness shift in positive and negative directions (beta), default 5;
- max_smooth - max smooth multiplier, default 6;
- max_color_shift - max color shift along RGB axes
- apply_probability - how often every transformation should be applied, default 0.5;
- debug_params - enable/disable printing tranformation parameters, default false;
from @kostyaev's caffe-augmentation are kept with slightly modifications:
How to use
You could specify your network prototxt as:
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
contrast_brightness_adjustment: true
smooth_filtering: true
min_side_min: 256
min_side_max: 480
crop_size: 224
mean_file: "imagenet_mean.binaryproto"
min_contrast: 0.8
max_contrast: 1.2
max_smooth: 6
apply_probability: 0.5
max_color_shift: 20
debug_params: false
}
image_data_param {
source: "train_list.txt"
batch_size: 64
}
}
while in testing phase:
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
min_side: 256
crop_size: 224
mean_file: "imagenet_mean.binaryproto"
}
image_data_param {
source: "test_list.txt"
batch_size: 32
}
}
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].