GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → axon-research → C3d Keras

axon-research / C3d Keras

Licence: other
C3D for Keras + TensorFlow

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningtensorflowvideokerasaction-recognitionkeras-tensorflowactivity-recognition

Projects that are alternatives of or similar to C3d Keras

Timeception
Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)
Stars: ✭ 153 (-10.53%)
Mutual labels:  action-recognition, activity-recognition
Awesome Activity Prediction
Paper list of activity prediction and related area
Stars: ✭ 147 (-14.04%)
Mutual labels:  action-recognition, activity-recognition
Hake
HAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20)
Stars: ✭ 132 (-22.81%)
Mutual labels:  action-recognition, activity-recognition
Step
STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)
Stars: ✭ 196 (+14.62%)
Mutual labels:  action-recognition, activity-recognition
Awesome Action Recognition
A curated list of action recognition and related area resources
Stars: ✭ 3,202 (+1772.51%)
Mutual labels:  action-recognition, activity-recognition
Hake Action Torch
HAKE-Action in PyTorch
Stars: ✭ 74 (-56.73%)
Mutual labels:  action-recognition, activity-recognition
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 (+0.58%)
Mutual labels:  action-recognition, activity-recognition
Squeeze-and-Recursion-Temporal-Gates
Code for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".
Stars: ✭ 62 (-63.74%)
Mutual labels:  activity-recognition, action-recognition
Robust-Deep-Learning-Pipeline
Deep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)
Stars: ✭ 20 (-88.3%)
Mutual labels:  activity-recognition, action-recognition
Hake Action
As a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).
Stars: ✭ 72 (-57.89%)
Mutual labels:  action-recognition, activity-recognition
M Pact
A one stop shop for all of your activity recognition needs.
Stars: ✭ 85 (-50.29%)
Mutual labels:  action-recognition, activity-recognition
Keras Fewshotlearning
Some State-of-the-Art few shot learning algorithms in tensorflow 2
Stars: ✭ 135 (-21.05%)
Mutual labels:  keras-tensorflow
Intelegent lock
lock mechanism with face recognition and liveness detection
Stars: ✭ 134 (-21.64%)
Mutual labels:  keras-tensorflow
Deep Learning Activity Recognition
A tutorial for using deep learning for activity recognition (Pytorch and Tensorflow)
Stars: ✭ 159 (-7.02%)
Mutual labels:  activity-recognition
Untrimmednet
Weakly Supervised Action Recognition and Detection
Stars: ✭ 152 (-11.11%)
Mutual labels:  action-recognition
Repo 2019
BERT, AWS RDS, AWS Forecast, EMR Spark Cluster, Hive, Serverless, Google Assistant + Raspberry Pi, Infrared, Google Cloud Platform Natural Language, Anomaly detection, Tensorflow, Mathematics
Stars: ✭ 133 (-22.22%)
Mutual labels:  keras-tensorflow
Inferpy
InferPy: Deep Probabilistic Modeling with Tensorflow Made Easy
Stars: ✭ 130 (-23.98%)
Mutual labels:  keras-tensorflow
Motion Sense
MotionSense Dataset for Human Activity and Attribute Recognition ( time-series data generated by smartphone's sensors: accelerometer and gyroscope)
Stars: ✭ 159 (-7.02%)
Mutual labels:  activity-recognition
Stock Price Predictor
This project seeks to utilize Deep Learning models, Long-Short Term Memory (LSTM) Neural Network algorithm, to predict stock prices.
Stars: ✭ 146 (-14.62%)
Mutual labels:  keras-tensorflow
Action Recognition
Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.
Stars: ✭ 129 (-24.56%)
Mutual labels:  action-recognition
View All Similar Projects ➔

C3D Model for Keras + TensorFlow

The scripts here are inspired by C3D Model for Keras gist, but specifically for Keras + TensorFlow (not Theano-backend).

To reproduce results:

  • Run a script that does everything: bash do_everything.sh

OR, build a docker image, which will do all the steps of replication during the build:

docker build -t c3d-keras .

OR, run each of these steps:

  1. Download pretrained model: bash models/get_weights_and_mean.sh
  2. Download sport1mil labels: bash sports1m/get_labels.sh
  3. Download facebook/C3D caffe.proto file for conversion from caffe to Keras: wget https://raw.githubusercontent.com/facebook/C3D/master/C3D-v1.0/src/caffe/proto/caffe.proto
  4. Install protobuf per instruction in https://github.com/google/protobuf. In Ubuntu, sudo apt-get install protobuf-compiler will do.
  5. Compile the caffe.proto file for python: protoc --python_out=. caffe.proto
  6. Make sure the default keras config (in ~/.keras/keras.json) has: tf image_dim_ordering, and tensorflow backend.
  7. Convert the pre-trained model from Caffe format to Keras: python convert_caffe_model.py
  8. Download test video: bash download_test_video.sh
  9. Run test: python test_model.py

Prerequisites

Known to work with the following python packages:

  • Keras==2.0.0
  • tensorflow==0.12.1
  • h5py==2.6.0
  • numpy==1.12.0
  • cv2==3.1.0
  • pydot==1.1.0
  • graphviz

Some basic command-line tools:

Results

A following classification probability plot is expected (saved as probabilities.png). A peak at 367th class (probability = 71%) corresponds to basketball label.

Classification Probability Plot

The top 5 labels will also be reported, and should look something like:

Position of maximum probability: 367
Maximum probability: 0.57953
Corresponding label: basketball

Top 5 probabilities and labels:
basketball: 0.57953
volleyball: 0.14435
streetball: 0.06718
freestyle wrestling: 0.03323
greco-roman wrestling: 0.03293

References

  1. C3D Model for Keras
  2. Original C3D implementation in Caffe
  3. C3D paper

Comment / Feedback

Feel free to contact Chuck Cho (cycho at axon.com) for any comment or feedback.

License

  • Source code: 2-clause BSD.
  • Data: various Creative Commons licenses. See LICENSE.md for details.
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].