While converting a model using tflite, I want to understand the internal block diagram of it. How the conversion is taking place.
Is there internal pruning happening in it ??
If yes, then does it make sense to prune a network beforehand ??
1 Like
Generally I suggest you to select tags and category from the menu on a new thread cause specialized technical team members could be subscribed only to a tag subset (e.g. in this case I suggest tflite and docs)
1 Like
Ah ! Thanks 
Done !
2 Likes
Completely agree with @Bhack on this. TensorFlow Lite and TensorFlow Model Optimization Toolkit have very well documentation and tutorials. They are the first-hand resource.
1 Like
The pruning is not happening during the tf-lite conversion. To add sparsity, your model need to be updated by following a specific procedure - Please refer the official guide. Pruning in Keras example | TensorFlow Model Optimization
1 Like
If you are interested about pruning for latency on TFLite you can follow or ask an update at:
1 Like
Thank you so much for your answers
1 Like