Keras Kinetics I3d Save

keras implementation of inflated 3d from Quo Vardis paper + weights

Project README


Keras implementation (including pretrained weights) of Inflated 3d Inception architecture reported in the paper Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset.

Original implementation by the authors can be found in this repository.

Sample Data (for Evaluation)

Similar to the original implementation, we evaluate the keras models using the RGB sample and Optical Flow sample (processed from video data) provided in the repository of the authors (see the data/ directory). Details about the preprocessing techniques applied to the data are specified in the authors' repository.




[For help]
python -h

With default flags settings, the script builds two I3d Inception architecture (2 stream: RGB and Optical Flow), loads their respective pretrained weights and evaluates RGB sample and Optical Flow sample obtained from video data.

You can set flags to evaluate model using only one I3d Inception architecture (RGB or Optical Flow) as shown below:

# For RGB
python --eval-type rgb

# For Optical Flow
python --eval-type flow

Addtionally, as described in the paper (and the authors repository), there are two types of pretrained weights for RGB and Optical Flow models respectively. These are;

  • RGB I3d Inception:
    • Weights Pretrained on Kinetics dataset only
    • Weights pretrained on Imagenet and Kinetics datasets
  • Optical Flow I3d Inception:
    • Weights Pretrained on Kinetics dataset only
    • Weights pretrained on Imagenet and Kinetics datasets

The above usage examples loads weights pretrained on Imagenet and Kinetics datasets. To load weight pretrained on Kinetics dataset only add the flag --no-imagenet-pretrained to the above commands. See an example below:

# RGB I3d Inception model pretrained on kinetics dataset only
python --eval-type rgb --no-imagenet-pretrained


  • Keras
  • Keras Backend: Tensorflow (tested) or Theano (not tested) or CNTK (not tested)
  • h5py


  • All code in this repository are licensed under the MIT license as specified by the LICENSE file.
  • The i3d (rgb and flow) pretrained weights were ported from the ones released Deepmind in this repository under Apache-2.0 License
Open Source Agenda is not affiliated with "Keras Kinetics I3d" Project. README Source: dlpbc/keras-kinetics-i3d
Open Issues
Last Commit
4 years ago

Open Source Agenda Badge

Open Source Agenda Rating