DeepLearning

顶峰报告 数据清理： - The Dataset is a text file with pair's of english text and python code. - Each example is seperated by a new_line character and '#' symbol**(\n#) **. - Additionally some sentences start with a space after the '#' symbol and some don't, to remove them the queue is first tokenised and checked for space's in the beginning of the sentence. 数据准备： * During the training of the mod