mohammed-elkomy / two-stream-action-recognition

My re-implementation of two stream action recognition
Apache License 2.0
60 stars 19 forks source link

Finetuning #4

Open Rasipuram opened 5 years ago

Rasipuram commented 5 years ago

Hi,

Thank you for providing a wonderful repository.

My system requirements are quite low and I want to use a pre-trained action recognition model and fine tune it for my data.

Can you please suggest me a simple approach using your model?

"Where do I get your pre-trained action recognition model?" "Finetuning process: how should I be extracting features and use the model using your code"

mohammed-elkomy commented 5 years ago

Thanks for the motivating words :)

"Where do I get your pre-trained action recognition model?" my code already downloads the pretrained models from mydrive public shared folder, could be found in the readme.

"Finetuning process: how should I be extracting features and use the model using your code" using the keras model you just got, you could print the architecture and layers and get the output of the layer just below the classification step as in here https://keras.io/applications/.

On Wed, Aug 28, 2019 at 7:13 AM Rasipuram notifications@github.com wrote:

Hi,

Thank you for providing a wonderful repository.

My system requirements are quite low and I want to use a pre-trained action recognition model and fine tune it for my data.

Can you please suggest me a simple approach using your model?

"Where do I get your pre-trained action recognition model?" "Finetuning process: how should I be extracting features and use the model using your code"

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/mohammed-elkomy/two-stream-action-recognition/issues/4?email_source=notifications&email_token=AECZSTAS3FSXZZB47FIJLY3QGYCQ3A5CNFSM4IQ2E3I2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HH2JAVA, or mute the thread https://github.com/notifications/unsubscribe-auth/AECZSTCRWAILJFYN7GTJENDQGYCQ3ANCNFSM4IQ2E3IQ .