StrangerZhang / Pyeco
Licence: mit
python implementation of efficient convolution operators for tracking
Stars: ✭ 150
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pyeco
Tusimple Duc
Understanding Convolution for Semantic Segmentation
Stars: ✭ 567 (+278%)
Mutual labels: mxnet, convolution
Ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+8817.33%)
Mutual labels: mxnet
Mxnet.sharp
.NET Standard bindings for Apache MxNet with Imperative, Symbolic and Gluon Interface for developing, training and deploying Machine Learning models in C#. https://mxnet.tech-quantum.com/
Stars: ✭ 134 (-10.67%)
Mutual labels: mxnet
Facerecognition
This is an implematation project of face detection and recognition. The face detection using MTCNN algorithm, and recognition using LightenenCNN algorithm.
Stars: ✭ 137 (-8.67%)
Mutual labels: mxnet
Mxnet Mobilenet V2
Reproduction of MobileNetV2 using MXNet
Stars: ✭ 134 (-10.67%)
Mutual labels: mxnet
Machine Learning Using K8s
Train and Deploy Machine Learning Models on Kubernetes using Amazon EKS
Stars: ✭ 145 (-3.33%)
Mutual labels: mxnet
Jamesdspmanager
Audio DSP effects build on Android system framework layer. This is a repository contains a pack of high quality DSP algorithms specialized for audio processing.
Stars: ✭ 136 (-9.33%)
Mutual labels: convolution
Horovod
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
Stars: ✭ 11,943 (+7862%)
Mutual labels: mxnet
Redis Operator
Redis Operator creates/configures/manages Redis clusters atop Kubernetes
Stars: ✭ 142 (-5.33%)
Mutual labels: operator
Deep Face Alignment
The MXNet Implementation of Stacked Hourglass and Stacked SAT for Robust 2D and 3D Face Alignment
Stars: ✭ 134 (-10.67%)
Mutual labels: mxnet
Postgres Operator
Postgres operator creates and manages PostgreSQL clusters running in Kubernetes
Stars: ✭ 2,194 (+1362.67%)
Mutual labels: operator
Single Path One Shot Nas Mxnet
Single Path One-Shot NAS MXNet implementation with full training and searching pipeline. Support both Block and Channel Selection. Searched models better than the original paper are provided.
Stars: ✭ 136 (-9.33%)
Mutual labels: mxnet
Psconv
[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
Stars: ✭ 138 (-8%)
Mutual labels: convolution
Redis Cluster Operator
Redis Cluster Operator creates and manages Redis Clusters atop Kubernetes.
Stars: ✭ 150 (+0%)
Mutual labels: operator
Etcd Cloud Operator
Deploying and managing production-grade etcd clusters on cloud providers: failure recovery, disaster recovery, backups and resizing.
Stars: ✭ 149 (-0.67%)
Mutual labels: operator
Python Implementation of ECO
Run demo
cd pyECO/eco/features/
python setup.py build_ext --inplace
pip install numpy scipy python-opencv glob pandas pillow
# if you want to use deep feature
pip install mxnet-cu80(or 90 according to your cuda version)
pip install cupy-cu80(or 90 according to your cuda version)
cd pyECO/
python bin/demo_ECO_hc.py --video_dir path/to/video
Convert to deep feature version
uncomment eco/config/config.py at line5 and comment eco/config/config.py at line 6
Benchmark results
OTB100
Tracker | AUC | Speed |
---|---|---|
ECO_deep | 68.7(vs 69.1) | 6~8fps on GTX 1080 Ti |
ECO_hc | 65.2(vs 65.0) | 40~60fps on Intel i5 |
Visualization Results
Note
we use ResNet50 feature instead of the original imagenet-vgg-m-2048
code tested on mac os 10.13 and python 3.6, ubuntu 16.04 and python 3.6
Reference
[1] Danelljan, Martin and Bhat, Goutam and Shahbaz Khan, Fahad and Felsberg, Michael ECO: Efficient Convolution Operators for Tracking In Conference on Computer Vision and Pattern Recognition (CVPR), 2017
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].