I made available VGG16, VGG19, ResNet50: Keras code +ImageNet weights for both TF and Theano.https://github.com/fchollet/deep-learning-models …
You can now literally do: ``` model = VGG16(weights='imagenet') preds = model.predict(imgs) print(decode_predictions(preds)) ```
-
-
amazing
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Hoping to see great new models from the community --NLP, vision, speech, and more.
-
We have a complete ASR workflow in Torch, would love to port it over to Keras, just need some good CNN>LSTM examples to build on.
- Show replies
New conversation -
-
-
Can I do just `model = VGG16()`? Can you please pick the best weights for me?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
you're seriously my hero for making things easy for people to play around with :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Game changer. I see Keras in my future.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
cool, must try immediatly.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.