lambda labs deep learning

Flow: Model Family----depth network----depth learningModel family: The model has a super-parameter, and gives different parameters corresponding to different models, it forms the model familyAlgorithm family: Each model corresponds to a complete algorithm, the entire model family corresponds to an algorithm family to expand the algorithm family into a deep network, the network layer represents the number of iterations, the model's hyper-parameters bec

Python deep learning "Fluent python" Part 1From the beginning of last weekend to see this "fluent python", technology is slowly accumulated, Python is slowly to write elegant (pythonic).Data modelPython Solitaireimport collections# 用来构建一个只有属性，没有方法的简单类，来代表扑克牌的号码和花色。Card = collections.namedtuple('Card', ['rank', 'suit'])class FrenchDeck: # 扑克牌的号码 ranks = [str(n) for n in range(2,11) + list('JQKA')] #

: #808080" > through inheritance we can extract duplicate code from subclasses into the parent class. # subclass by inheritance , and reuse the code to reduce the coding of the duplicate code # In the future if you want to maintain the public code of a subclass, you only need to do it in the parent class Seven main principlesSingle principle of responsibilityOpening and closing principleDependency reversal principleThe principle of the Richter replacementInterface Isolation princi