millskyle / extensive_deep_neural_networks Goto Github PK
View Code? Open in Web Editor NEWSimple examples of extensive deep neural networks in action
Simple examples of extensive deep neural networks in action
The research article "Extensive deep neural networks for transferring small scale learning to large scale systems" links this GitHub repository for code that uses the "Porous Graphene" dataset.
There is an issue with the dataset, that is, I am unable to extract the 'energy' or 'file_source' label:
$ python sample_explore.py
KEYS <KeysViewHDF5 ['cell', 'coordinates', 'energy', 'file_source']>
CLASS: cell
DIMENSIONS: (3, 3)
DATA: <HDF5 dataset "cell": shape (3, 3), type "<f8">
CLASS: coordinates
DIMENSIONS: (390, 4)
DATA: <HDF5 dataset "coordinates": shape (390, 4), type "<f8">
CLASS: energy
DIMENSIONS: ()
DATA: <HDF5 dataset "energy": shape (), type "<f8">
CLASS: file_source
DIMENSIONS: ()
DATA: <HDF5 dataset "file_source": shape (), type "|O">
I'm assuming 'file_source' should point to something like /archive/01/kmills/ednn_for_paper/training_data/holey_sheets/unprocessed/vasprun/train/904efc8c-63ed-4644-8abc-ec5c4a470359/vasprun.xml
, but this file is absent from the archive
https://nrc-digital-repository.canada.ca/eng/view/object/?id=9f09901d-0736-4204-a35d-0c88ffb8da3b
Hi, when i run your code.
**for iTile in range(l/f):**
for jTile in range(l/f):
#calculate the indices of the centre of this tile (i.e. the centre of the focus region)
cot = (iTile*f + f/2, jTile*f + f/2) #centre of tile
foc_centered = in_
#shift the picture, wrapping the image around,
#so that the focus is centered in the middle of the image
foc_centered = roll(foc_centered, l/2-cot[0], 0)
foc_centered = roll(foc_centered, l/2-cot[1], 1)
#Finally slice away the excess image that we don't want to appear in this tile
final = slice_(foc_centered, l/2-f/2-c, l/2-f/2-c, 2*c+f, 2*c+f)
tiles.append(final)
TypeError: 'float' object cannot be interpreted as an integer
I don't know how to fix it? Could you help me?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.