From 98139f573eb179c8f5a06ba6c8d8883376814ccf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=89tienne=20Simon?= Date: Thu, 2 Jul 2015 12:59:15 -0400 Subject: Remove _simple --- ..._simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py | 60 ---------------------- 1 file changed, 60 deletions(-) delete mode 100644 config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py (limited to 'config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py') diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py deleted file mode 100644 index 4476879..0000000 --- a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py +++ /dev/null @@ -1,60 +0,0 @@ -import os -import cPickle - -from blocks.initialization import IsotropicGaussian, Constant -from blocks.bricks import Rectifier, Tanh, Logistic -from blocks.filter import VariableFilter -from blocks import roles - -import data -from model.joint_simple_mlp_tgtcls import Model, Stream - - -n_begin_end_pts = 10 # how many points we consider at the beginning and end of the known trajectory - -with open(os.path.join(data.path, 'arrival-clusters.pkl')) as f: - dest_tgtcls = cPickle.load(f) - -# generate target classes for time prediction as a Fibonacci sequence -time_tgtcls = [1, 2] -for i in range(21): - time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) - -dim_embeddings = [ - ('origin_call', data.origin_call_size, 15), - ('origin_stand', data.stands_size, 10), - ('week_of_year', 52, 10), - ('day_of_week', 7, 10), - ('qhour_of_day', 24 * 4, 10), - ('day_type', 3, 10), - ('taxi_id', 448, 10), -] - -# Common network part -dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) -dim_hidden = [5000] - -# Destination prediction part -dim_hidden_dest = [1000] -dim_output_dest = dest_tgtcls.shape[0] - -# Time prediction part -dim_hidden_time = [500] -dim_output_time = len(time_tgtcls) - -# Cost ratio between distance cost and time cost -time_cost_factor = 4 - -embed_weights_init = IsotropicGaussian(0.01) -mlp_weights_init = IsotropicGaussian(0.1) -mlp_biases_init = Constant(0.01) - -dropout = 0.5 -dropout_inputs = VariableFilter(bricks=[Rectifier], name='output') - -# use adadelta, so no learning_rate or momentum -batch_size = 200 - -valid_set = 'cuts/test_times_0' - -max_splits = 100 -- cgit v1.2.3