{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"02f59106-abda-8390-596d-540745dd633a"},"outputs":[],"source":"#The point of this notebook is to do a quick prediction on some sample images with a pretrained network.\nimport sys\nsys.path.append('../')\nimport pickle\nimport re\nimport glob\nimport os\nimport time\nimport theano\nimport theano.tensor as T\nimport numpy as np\nimport pandas as p\nimport lasagne as nn\n#from python_utils import hms, architecture_string, get_img_ids_from_iter\n\n%pylab inline\nrcParams['figure.figsize'] = 16, 6\n# rcParams['text.color'] = 'red'\n# rcParams['xtick.color'] = 'red'\n# rcParams['ytick.color'] = 'red'\n\nnp.set_printoptions(precision=3)\nnp.set_printoptions(suppress=True)\n\n#First we load the dump of the trained network.\ndump_path = '../dumps/2015_07_17_123003.pkl'\nmodel_data = pickle.load(open(dump_path, 'r'))\n\n# Let's set the in and output layers to some local vars.\nl_out = model_data['l_out']\nl_ins = model_data['l_ins']"}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.5.2"}},"nbformat":4,"nbformat_minor":0}