Documentation
The full documentation is at http://brainstorm.rtfd.org.
History
0.5 (2015-12-01)
Changed Behaviour
examples now run on CPU by default
added brainstorm.tools.shuffle_data and brainstorm.tools.split to help with data preparation
SigmoidCE and SquaredDifference layers now outputs a loss for each dimension instead of summing over features.
SquaredDifference layer does no longer scale by one half.
Added a SquaredLoss layer that computes half the squared difference and has an interface that is compatible with the SigmoidCE and SigmoidCE layers.
Output probabilities renamed to predictions in SigmoidCE and SigmoidCE layers.
New Features
added a use_conv option to brainstorm.tools.create_net_from_spec
added criterion option to brainstorm.hooks.EarlyStopper hook
added brainstorm.tools.get_network_info function that returns information about the network as a string
added brainstorm.tools.extract function that applies a network to some data and saves a set of requested buffers.
brainstorm.layers.mask layer now supports masking individual features
added brainstorm.hooks.StopAfterThresholdReached hook
Improvements
EarlyStopper now works for any timescale and interval
Recurrent, Lstm, Clockwork, and ClockworkLstm layers now accept inputs of arbitrary shape by implicitly flattening them.
several fixes to make building the docs easier
some performance improvements of NumpyHandler operations binarize_t and index_m_by_v
sped up tests
several improvements to installation scripts
Bugfixes
fixed sqrt operation for PyCudaHandler. This should fix problems with BatchNormalization on GPU.
fixed a bug for task_type=’regression’ in brainstorm.tools.get_in_out_layers and brainstorm.tools.create_net_from_spec
removed defunct name argument from input layer
fixed a crash when applying brainstorm.hooks.SaveBestNetwork to rolling_training loss
various minor fixes of the brainstorm.hooks.BokehVisualizer
fixed a problem with sum_t operation in brainstorm.handlers.PyCudaHandler
fixed a blocksize problem in convolutional and pooling operations in brainstorm.handlers.PyCudaHandler
0.5b0 (2015-10-25)
First release on PyPI.
2 maintainers
Metadata
2 maintainers
Release files for brainstorm 0.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| brainstorm-0.5.tar.gz | 246.3 kB | Without provenance | Details |
Release files / brainstorm-0.5.tar.gz
| Download URL | brainstorm-0.5.tar.gz |
|---|---|
| Size | 246.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e8fde7eb1edda32b528db80f36c90abe59647e0ce1e43ebc74ce0f7d285728fd
|
|
BLAKE2b-256 checksum How to use checksums |
6bce2f4cac3346bb75fbd284d33502df1bfb7a027e9d54c11409af372bc0f7f8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
Security for brainstorm 0.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
