Mercurial > ift6266
annotate data_generation/transformations/pycaptcha/Captcha/File.py @ 626:75dbbe409578
Added code for deep mlp, experiment code to go along with it. Also added code I used to filter the P07 / PNIST07 datasets to keep only digits.
| author | fsavard |
|---|---|
| date | Wed, 16 Mar 2011 13:43:32 -0400 |
| parents | 7800be7bce66 |
| children |
| rev | line source |
|---|---|
| 87 | 1 """ Captcha.File |
| 2 | |
| 3 Utilities for finding and picking random files from our 'data' directory | |
| 4 """ | |
| 5 # | |
| 6 # PyCAPTCHA Package | |
| 7 # Copyright (C) 2004 Micah Dowty <micah@navi.cx> | |
| 8 # | |
| 9 | |
|
273
7800be7bce66
changes in ttf2jpg and pycaptcha to load a file list with cPickle (instead of doing a listdir()) in order to have always the same list order from different machine (to reproduce generation)
Xavier Glorot <glorotxa@iro.umontreal.ca>
parents:
184
diff
changeset
|
10 import os, random, cPickle |
| 87 | 11 |
| 12 # Determine the data directory. This can be overridden after import-time if needed. | |
| 13 dataDir = os.path.join(os.path.split(os.path.abspath(__file__))[0], "data") | |
| 14 | |
| 15 | |
| 16 class RandomFileFactory(object): | |
| 17 """Given a list of files and/or directories, this picks a random file. | |
| 18 Directories are searched for files matching any of a list of extensions. | |
| 19 Files are relative to our data directory plus a subclass-specified base path. | |
| 20 """ | |
| 21 extensions = [] | |
| 22 basePath = "." | |
| 23 | |
| 24 def __init__(self, *fileList): | |
| 25 self.fileList = fileList | |
| 26 self._fullPaths = None | |
| 27 | |
| 28 def _checkExtension(self, name): | |
| 29 """Check the file against our given list of extensions""" | |
| 30 for ext in self.extensions: | |
| 31 if name.endswith(ext): | |
| 32 return True | |
| 33 return False | |
| 34 | |
| 35 def _findFullPaths(self): | |
| 36 """From our given file list, find a list of full paths to files""" | |
| 37 paths = [] | |
| 38 for name in self.fileList: | |
|
184
81f8466dc121
Transient exception handling in captchas (ie. lorsque le NFS est temporairement inaccessible)
boulanni <nicolas_boulanger@hotmail.com>
parents:
167
diff
changeset
|
39 if name[0] == '/': |
|
81f8466dc121
Transient exception handling in captchas (ie. lorsque le NFS est temporairement inaccessible)
boulanni <nicolas_boulanger@hotmail.com>
parents:
167
diff
changeset
|
40 path = name |
|
81f8466dc121
Transient exception handling in captchas (ie. lorsque le NFS est temporairement inaccessible)
boulanni <nicolas_boulanger@hotmail.com>
parents:
167
diff
changeset
|
41 else: |
|
81f8466dc121
Transient exception handling in captchas (ie. lorsque le NFS est temporairement inaccessible)
boulanni <nicolas_boulanger@hotmail.com>
parents:
167
diff
changeset
|
42 path = os.path.join(dataDir, self.basePath, name) |
| 87 | 43 if os.path.isdir(path): |
|
273
7800be7bce66
changes in ttf2jpg and pycaptcha to load a file list with cPickle (instead of doing a listdir()) in order to have always the same list order from different machine (to reproduce generation)
Xavier Glorot <glorotxa@iro.umontreal.ca>
parents:
184
diff
changeset
|
44 f = open(path + '/filelist.pkl') |
|
7800be7bce66
changes in ttf2jpg and pycaptcha to load a file list with cPickle (instead of doing a listdir()) in order to have always the same list order from different machine (to reproduce generation)
Xavier Glorot <glorotxa@iro.umontreal.ca>
parents:
184
diff
changeset
|
45 filelist = cPickle.load(f) |
|
7800be7bce66
changes in ttf2jpg and pycaptcha to load a file list with cPickle (instead of doing a listdir()) in order to have always the same list order from different machine (to reproduce generation)
Xavier Glorot <glorotxa@iro.umontreal.ca>
parents:
184
diff
changeset
|
46 f.close() |
|
7800be7bce66
changes in ttf2jpg and pycaptcha to load a file list with cPickle (instead of doing a listdir()) in order to have always the same list order from different machine (to reproduce generation)
Xavier Glorot <glorotxa@iro.umontreal.ca>
parents:
184
diff
changeset
|
47 for content in filelist: |
| 87 | 48 if self._checkExtension(content): |
| 49 paths.append(os.path.join(path, content)) | |
| 50 else: | |
| 51 paths.append(path) | |
| 52 return paths | |
| 53 | |
| 54 def pick(self): | |
| 55 if self._fullPaths is None: | |
| 56 self._fullPaths = self._findFullPaths() | |
| 57 return random.choice(self._fullPaths) | |
| 58 | |
| 59 ### The End ### |