ferreirafabio / video2tfrecord
Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.
☆153Updated last year
Related projects: ⓘ
- Functions for creating tfrecords for TensorFlow models.☆110Updated 4 years ago
- ☆176Updated this week
- Detectorch - detectron for PyTorch☆559Updated 5 years ago
- A repository of state-of-the-art deep learning methods in computer vision☆191Updated 6 years ago
- The pretrained models trained on Moments in Time Dataset☆355Updated 3 years ago
- high performance image loading and augmenting routines mimicking PIL.Image interface☆317Updated 3 years ago
- Keras implementation of Mobile Networks☆132Updated 5 years ago
- Hierarchical Attentive Recurrent Tracking☆146Updated 6 years ago
- pytorch model summary, statistic parameters number, memory usage, FLOPs and so on☆95Updated 4 years ago
- Repository for reading Pascal VOC data in Python, rather than requiring MATLAB to read the XML files.☆89Updated 4 years ago
- [CVPR 2017] Unsupervised deep learning using unlabelled videos on the web☆260Updated 5 years ago
- A simpler way of preparing large-scale image dataset by generalizing functions from TensorFlow-slim☆133Updated 4 years ago
- PyTorch code for the "Deep Neural Networks with Box Convolutions" paper☆509Updated 4 years ago
- TorchCV: a PyTorch vision library mimics ChainerCV☆392Updated 5 years ago
- PyTorch Implementation of Realtime Multi-Person Pose Estimation project.☆159Updated 6 years ago
- Tools to participate in the ActivityNet Challenge 2016 (NIPSW 2016)☆195Updated 6 years ago
- A PyTorch Implementation of Single Shot Scale-invariant Face Detector.☆230Updated 4 years ago
- Youtube-8m Videos, Frames and Ids Generator. Extract videos from youtube-8m. Extract frames from youtube-8m.☆125Updated 5 years ago
- Semi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segment…