We introduce End2You -- the Imperial College London toolkit for multimodal\nprofiling by end-to-end deep learning. End2You is an open-source toolkit\nimplemented in Python and is based on Tensorflow. It provides capabilities to\ntrain and evaluate models in an end-to-end manner, i.e., using raw input. It\nsupports input from raw audio, visual, physiological or other types of\ninformation or combination of those, and the output can be of an arbitrary\nrepresentation, for either classification or regression tasks. To our\nknowledge, this is the first toolkit that provides generic end-to-end learning\nfor profiling capabilities in either unimodal or multimodal cases. To test our\ntoolkit, we utilise the RECOLA database as was used in the AVEC 2016 challenge.\nExperimental results indicate that End2You can provide comparable results to\nstate-of-the-art methods despite no need of expert-alike feature\nrepresentations, but self-learning these from the data "end to end".\n