Here's regression example on the Ames Housing Price dataset. This dataset turns out to be great for demonstrating how to vectorize structured data, and how to handle missing features. https://t.co/aEQDn38psw
— François Chollet (@fchollet) June 3, 2019
Thanks to @micahjsmith for suggesting this dataset!
#3: a @TensorFlow @home_assistant project that uses a #Coral Edge TPU for inferencing. Example use case: send a text notification and photo when someone you don't recognize is at your front door.https://t.co/Wc0SyXY9Ld
— 👩💻 DynamicWebPaige (@DynamicWebPaige) June 3, 2019
#Keras re-implementation of EfficientNet: https://t.co/8BEh92QIXE
— Alexandr Kalinin (@alxndrkalinin) May 31, 2019
- EfficientNet-B1 is 7.6x smaller and 5.7x faster on CPU inference than ResNet-152
- EfficientNet-B4 improves the top-1 accuracy from 76.3% of ResNet-50 to 82.6% (+6.3%), under similar FLOPS constraint pic.twitter.com/ZhQiDK8Itw
An self-contained image segmentation example (model trained from scratch on the Oxford Pets dataset): https://t.co/GLbowTf9ie
— François Chollet (@fchollet) May 29, 2019
Another great tutorial from @PyImageSearch, on feature extraction for large datasets https://t.co/6Ar5Sz73Dy
— François Chollet (@fchollet) May 27, 2019
You can now add gesture based interactions to your web app!
— TensorFlow (@TensorFlow) May 27, 2019
The @handtrackjs library by @vykthur lets you track hands (bounding box) from any #html image, video, or canvas element.
Learn more here → https://t.co/3dEkNFEbF6 pic.twitter.com/x01kEg6WjL
A great object detection tutorial for Keras (YOLOv3) https://t.co/yw7AzzcOlO
— François Chollet (@fchollet) May 26, 2019
Gradient Flow: a new notebook that explains automatic differentiation using eager execution in @TensorFlow. I go over computational graphs, vector valued functions, gradient, etc .. https://t.co/BFfvvslz9b
— Zaid زيد (@zaidalyafeai) May 25, 2019
If your model creates additional losses during its forward pass (i.e. if you called `self.add_loss` in a custom layer), collect them in one line like this. pic.twitter.com/tuvBdibMAP
— François Chollet (@fchollet) May 24, 2019
This is a great tutorial: building a Transformer with the Keras functional API in TensorFlow 2.0. https://t.co/mxgAvG8tSR
— François Chollet (@fchollet) May 24, 2019
Naver uses TensorFlow to match millions of products daily to over 5,000 shopping categories.
— TensorFlow (@TensorFlow) May 20, 2019
Find out how they improve accuracy and create a more user-friendly shopping experience in this guest article by the engineering team.
Read more here ↓ https://t.co/xbHsGKyhbT
Translatotron is our experimental model for direct end-to-end speech-to-speech translation, which demonstrates the potential for improved translation efficiency, fewer errors, and better handling of proper nouns. Learn all about it below! https://t.co/CvXL4lbPvP
— Google AI (@GoogleAI) May 15, 2019
