wassname (Michael J Clark) wassname
🙃
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] | |
| [email protected] |
wassname
/ pick_image features.ipynb
Created
August 12, 2016 00:07
example of interactive labeling images in jupyter/ipython notebook
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
wassname
/ visualising keras.ipynb
Created
September 9, 2016 03:03
Visualising keras weights and output using matplotlib
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Here is a dice loss for keras which is smoothed to approximate a linear (L1) loss. | |
| It ranges from 1 to 0 (no error), and returns results similar to binary crossentropy | |
| """ | |
| # define custom loss and metric functions | |
| from keras import backend as K | |
| def dice_coef(y_true, y_pred, smooth=1): |
wassname
/ keras_weighted_categorical_crossentropy.py
Last active
October 10, 2024 00:52
Keras weighted categorical_crossentropy (please read comments for updated version)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| A weighted version of categorical_crossentropy for keras (2.0.6). This lets you apply a weight to unbalanced classes. | |
| @url: https://gist.github.com/wassname/ce364fddfc8a025bfab4348cf5de852d | |
| @author: wassname | |
| """ | |
| from keras import backend as K | |
| def weighted_categorical_crossentropy(weights): | |
| """ | |
| A weighted version of keras.objectives.categorical_crossentropy | |
wassname
/ dataset_cmudict.py
Last active
November 4, 2016 01:57
Loader for cmudict dataset (CMU Pronouncing Dictionary) for keras
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Load cmudict/CMU Pronouncing Dictionary as a dataset for keras | |
| author: wassname | |
| url : https://gist.github.com/wassname/ce0ac72c50832b0a27e67bd97ba36080 | |
| """ | |
| from keras.utils.data_utils import get_file | |
| from sklearn.model_selection import train_test_split | |
| import numpy as np |
wassname
/ keras_attention_wrapper.py
Created
November 1, 2016 08:06
A keras attention layer that wraps RNN layers.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| A keras attention layer that wraps RNN layers. | |
| Based on tensorflows [attention_decoder](https://github.com/tensorflow/tensorflow/blob/c8a45a8e236776bed1d14fd71f3b6755bd63cc58/tensorflow/python/ops/seq2seq.py#L506) | |
| and [Grammar as a Foreign Language](https://arxiv.org/abs/1412.7449). | |
| date: 20161101 | |
| author: wassname | |
| url: https://gist.github.com/wassname/5292f95000e409e239b9dc973295327a | |
| """ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Url: https://gist.github.com/wassname/1393c4a57cfcbf03641dbc31886123b8 | |
| """ | |
| import unicodedata | |
| import string | |
| valid_filename_chars = "-_.() %s%s" % (string.ascii_letters, string.digits) | |
| char_limit = 255 | |
| def clean_filename(filename, whitelist=valid_filename_chars, replace=' '): |
wassname
/ classification_report_parse.py
Last active
March 10, 2017 04:25
Digitize scikit-learn's classification_report
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from io import StringIO | |
| import pandas as pd | |
| import numpy as np | |
| import sklearn | |
| def parse_classification_report(classification_report): | |
| """Parses sklearn classification report into a pandas dataframe.""" | |
| return pd.read_fwf(StringIO(classification_report),lineterminator='\n', index_col=0, colspecs=[(0,12),(12,22),(22,32),(32,42),(42,52)]).dropna() | |
| target_names['leak','no leak'] |
wassname
/ find_best_dummy_classification.py
Last active
August 27, 2017 05:56
Try all dummy models in sklearn
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # from https://gist.github.com/wassname/00b94dc7eb7220c136685fce782be3a4 | |
| from io import StringIO | |
| import pandas as pd | |
| import numpy as np | |
| from sklearn import metrics | |
| import sklearn | |
| def parse_classification_report(classification_report): | |
| """Parse a sklearn classification report to a dict.""" | |
| return pd.read_fwf( |