Minhhuy Le

icon indicating a website link https://www.researchgate.net/profile/Minhhuy_Le icon indicating an email [email protected]

icon location South of Korea icon location I'm a post-doc research in Nondestructive Testing. And currently interested in Artificial Intelligence and Deep Learning.

Results 4 comments of Minhhuy Le

sim.predict make GPU full memory

Dear Drasmuss, Thank you for your comment. Here is my code: with nengo.Network(seed=42) as net: net.config[nengo.Ensemble].max_rates = nengo.dists.Choice([100]) net.config[nengo.Ensemble].intercepts = nengo.dists.Choice([0]) net.config[nengo.Connection].synapse = None neuron_type = nengo.LIF(amplitude=0.01) nengo_dl.configure_settings(stateful=False) input =...

sim.predict make GPU full memory

Dear Drasmuss, Thank you for checking the issue. There are two issues: 1. Attaching probe after each layer will lead to full memory if calling sim.predict For example: nengo_dl.configure_settings(stateful=False) input...

sim.predict make GPU full memory

Here I produce two codes for the two errors. [https://drive.google.com/drive/folders/1jsdqj9F-FHQD9xh8kne1CI0PIbUQpJ2D?usp=sharing](url) Thank you very much!!!!

sim.predict make GPU full memory

Dear Drasmuss, Problem 1 is understood. But, still "tf.keras.backend.clear_session"does not solve the second problem. Event I added more: "delete sim" and "tf.compat.v1.reset_default_graph()"