|
|
|
|
|
|
0 Replies and 461 Views
Update codes from Tensorflow 1.0 to 2.0 - Road Taken 461 0
Started by Patrick Ng
If you are, like me, having bunch of deep neural network (DNN) Tensorflow 1.0 (tf.1) codes that served their purpose, but now want to run on GPU and perform more experiments faster, then the following may help save a weekend (rather than banging head tracking down barrage of error messages). Issue - Tensorflow 2 (tf.2) supports GPU but is not backward compatible (tf.1 codes won't run as is). Lesson 1 - upgrade from tf.1 to tf.2 (i.e., completed installation), the first roadblock is...
|
|
|
|
0 |
461 |
10 May 2022 08:38 PM |
|
0 Replies and 411 Views
Update codes from Tensorflow 1.0 to 2.0 - Road Taken 411 0
Started by Patrick Ng
If you are, like me, have bunch of deep neural network (DNN) Tensorflow 1.0 (tf.1) codes that served their purpose, but now want to run on GPU and perform more experiments faster, then the following may help save a weekend (rather than banging head tracking down barrage of error messages). Issue - Tensorflow 2 (tf.2) supports GPU but is not backward compatible (tf.1 codes won't run as is). Lesson 1 - upgrade from tf.1 to tf.2 (i.e., completed installation), the first roadblock is that plac...
|
|
|
|
0 |
411 |
10 May 2022 08:38 PM |
|
0 Replies and 404 Views
The Great Debate Series - Future of Petroleum 404 0
Started by Patrick Ng
https://aapg.informz.net/informzdataservice/onlineversion/ind/bWFpbGluZ2luc3RhbmNlaWQ9MTA1NjQ3NTUmc3Vic2NyaWJlcmlkPTEwNTUyOTczMTg= To make sure your voice is heard, sign up for free and be part of the Great Debate. Then on an ongoing basis, we can come back here and share insights on using data analytics and AI-ML to further explore new possibilities and push the frontier of sustainable energy supply in the post-Ukraine world. ...
|
|
|
|
0 |
404 |
07 May 2022 09:28 AM |
|
0 Replies and 389 Views
Energy in Data 2022 - Tackling the Challenges 389 0
Started by Patrick Ng
The first in-person (after debut 2019) Energy in Data event Austin Feb 21 - 23, 2022 was a productive endeavor. Of particular interest to this community is the data-centric challenges identified by the participants in breakout sessions at the end of each day. Instead of happy hour, EiD had working breakouts so we could dive in, generate deeper and richer experience. See summary table below. Call for volunteers - anyone interested in helping us crack the 'code' tack...
|
|
|
|
0 |
389 |
23 Apr 2022 04:24 PM |
|
0 Replies and 341 Views
Image Segmentation Algo applied to Surface Wave Dispersion and S-wave Inversion 341 0
Started by Patrick Ng
Saw a practical example using open source DeepLab V3 applied to transformed surface wave data (i.e., in frequency-wavenumber and Radon domain), followed by inversion to derive the subsurface shear-wave velocity structure. Takeaway Automated 'picking' of dispersion curves in appropriate feature-engineering space, using deep learning algo can minimize the pain points out of data prep and processing (otherwise time-consuming and labor-intensive). Possibility DeepLab next-gen can be...
|
|
|
|
0 |
341 |
20 Apr 2022 01:02 PM |
|