"Weight, weight, don't tell me!"
You can now easily apply weight pruning to your tf.keras models, to obtain smaller models for inference:https://medium.com/tensorflow/tensorflow-model-optimization-toolkit-pruning-api-42cac9157a6a …
-
-
-
I'm disappointed your New Yorker profile didn't mention any of your dad jokes
- Još 1 odgovor
Novi razgovor -
-
-
The COLAB NB w/ the MNIST example is so good:https://colab.research.google.com/github/tensorflow/model-optimization/blob/master/tensorflow_model_optimization/g3doc/guide/pruning/pruning_with_keras.ipynb …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
This method seems to prune based purely on weight magnitude. How does this pruning method perform in terms of maintaining performance while increasing sparsity?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Finally there... I am als waiting for an optimized reduced model, relearned based on an existing complex model. A zipped version which might even be more general. The complex model could be used to generate more trainig data, and the original data could be used as test data.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
This will go a long way in explaining how the model works for removing local and global bias.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
This is fantastic... will definitely be using this!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Can this work on any given CNN?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.