brew install youtube-dlhere's for fast ai's course:
| <div class="world"></div> | |
| <div class="title"> | |
| <p>Looking at these waves for 1 minute<br/>will bring you 56% more serenity*</p> | |
| <p class="remark">* According to a very serious and reliable study conducted by myself.</p> | |
| <div class="credits"> | |
| <a href="https://codepen.io/Yakudoo/" target="blank">my other codepens</a> | <a href="https://www.epic.net" target="blank">epic.net</a></div> | |
| </div> |
| from keras.layers import Dense | |
| from keras.layers import Flatten | |
| from keras.layers import Conv2D | |
| from keras.layers import MaxPooling2D | |
| from keras.layers import Dropout | |
| from keras.models import Sequential | |
| def vgg16(): | |
| model = Sequential() | |
| model.add(Conv2D(64, (3, 3), padding='same', activation='relu', input_shape=(224, 224, 3))) |
| """ | |
| Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy) | |
| BSD License | |
| """ | |
| import numpy as np | |
| # data I/O | |
| data = open('input.txt', 'r').read() # should be simple plain text file | |
| chars = list(set(data)) | |
| data_size, vocab_size = len(data), len(chars) |
| import string, sklearn, random | |
| from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer | |
| from sklearn.svm import SVC | |
| from sklearn.pipeline import Pipeline | |
| from sklearn.grid_search import GridSearchCV | |
| from sklearn.cross_validation import StratifiedKFold | |
| def tok(m): | |
| return m.split() |
| # coding: utf-8 | |
| import requests | |
| import os.path | |
| import time | |
| def multiple_tries(func, times, timeout): | |
| for cnt in xrange(1, times + 1): | |
| try: | |
| return func() | |
| except Exception, e: |
| ############################################################################## | |
| ## ## | |
| ## ## | |
| ## ( \/ )( ) ___( _ \ / \(_ _) ## | |
| ## / \/ \/ (_/\(___)) _ (( O ) )( ## | |
| ## \_)(_/\____/ (____/ \__/ (__) ## | |
| ## ## | |
| ## ## | |
| ## ## | |
| ## The beginings of an ml-bot. To start, he'll let us know when ## |
| ### Keybase proof | |
| I hereby claim: | |
| * I am adammenges on github. | |
| * I am adammenges (https://keybase.io/adammenges) on keybase. | |
| * I have a public key whose fingerprint is 4C50 C670 FDCD 994E EC08 D308 C8A2 1C16 63B6 3476 | |
| To claim this, I am signing this object: |
| ############################# | |
| # | |
| # Needed it to download this guy: https://www.youtube.com/playlist?list=PLPemlF-zX2ydW5QoNsHpQiLCQKIKdjvoo | |
| # | |
| # Figured why not stick it up on github too. | |
| # | |
| ############################# | |
| import pafy | |
| import os |
| def balancedParens(s): | |
| stack, opens, closes = [], ['(', '[', '{'], [')', ']', '}'] | |
| for c in s: | |
| if c in opens: | |
| stack.append(c) | |
| elif c in closes: | |
| try: | |
| if opens.index(stack.pop()) != closes.index(c): | |
| return False | |
| except (ValueError, IndexError): |