weiliu89 / vatic
vatic is an online, interactive video annotation tool for computer vision research that crowdsources work to Amazon's Mechanical Turk. Our tool makes it easy to build massive, affordable video data sets. Written in Python + C + Javascript, vatic is free and open-source software.
☆13Updated 8 years ago
Alternatives and similar repositories for vatic:
Users that are interested in vatic are comparing it to the libraries listed below
- Caffe: a fast open framework for deep learning.☆16Updated 8 years ago
- caffe-regression examples ,kaggle face keypoint detection☆58Updated 7 years ago
- VGG16 architecture with BatchNorm☆14Updated 7 years ago
- Spatial Transformer Network Implementation in Caffe☆27Updated 9 years ago
- Training the inception resnet v2 architecture in caffe☆44Updated 8 years ago
- Spatial Transformer Networks☆76Updated 8 years ago
- Code to convert a MXNet model into Caffe (C++)☆53Updated 8 years ago
- a branc caffe with feature of Data Augmentation using a configurable stochastic combination of 7 data augmentation techniques.☆32Updated 9 years ago
- Caffe: a fast open framework for deep learning.☆16Updated 8 years ago
- optimized caffe for GBD☆26Updated 8 years ago
- ShuffleNet implementation in mxnet☆41Updated 6 years ago
- caffe-yolo-9000☆48Updated 7 years ago
- tensorflow-wrapped layers from Caffe☆16Updated 8 years ago
- Codes for CVPR2016 paper "CRAFT Objects from Images"☆49Updated 8 years ago
- Model Converter from Torch to Caffe☆30Updated 7 years ago
- Some tools and examples for pyCaffe including LMDB I/O, custom Python layers and monitoring training error and loss.☆77Updated 8 years ago
- ☆28Updated 8 years ago
- DeepPyramid DPM☆43Updated 8 years ago
- An implementation of the RoiAlign operation for Theano☆11Updated 6 years ago
- First step towards...☆33Updated 8 years ago
- ☆11Updated 8 years ago
- ☆45Updated 7 years ago
- Generate Caffe Prototxt for Deep Residual Learning Network☆71Updated 9 years ago
- A simplify version of mobilenet, with less group and feature maps, trained on Imagenet.☆17Updated 7 years ago
- A Method for Unconstrained Salient Object Detection☆60Updated 8 years ago
- MXNet port of R-FCN☆51Updated 8 years ago
- Image Retrieval Experiment Using Triplet Loss☆26Updated 8 years ago
- Yet Another MXnet DETection☆60Updated 6 years ago
- Full convolution MultiBox Detector ( like SSD) implemented in Torch.☆40Updated 8 years ago
- Implement of 'Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues' by Ning Zhang, et al☆24Updated 9 years ago