Move weights init to config files ; fix s/time/travel_time

4 files changed, 16 insertions, 97 deletions

diff --git a/model/dest_simple_mlp.py b/model/dest_simple_mlp.py
index f422f11..a9e97cb 100644
--- a/model/dest_simple_mlp.py
+++ b/model/dest_simple_mlp.py
@@ -1,8 +1,6 @@
 from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity
 from blocks.bricks.lookup import LookupTable
 
-from blocks.initialization import IsotropicGaussian, Constant
-
 from theano import tensor
 
 import data
@@ -58,9 +56,9 @@ class Model(object):
 
         # Initialization
         for tbl in embed_tables:
-            tbl.weights_init = IsotropicGaussian(0.001)
-        mlp.weights_init = IsotropicGaussian(0.01)
-        mlp.biases_init = Constant(0.001)
+            tbl.weights_init = config.embed_weights_init
+        mlp.weights_init = config.mlp_weights_init
+        mlp.biases_init = config.mlp_biases_init
 
         for tbl in embed_tables:
             tbl.initialize()
diff --git a/model/dest_simple_mlp_tgtcls.py b/model/dest_simple_mlp_tgtcls.py
index a7b6f9b..1381d4c 100644
--- a/model/dest_simple_mlp_tgtcls.py
+++ b/model/dest_simple_mlp_tgtcls.py
@@ -6,8 +6,6 @@ from theano import tensor
 from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax
 from blocks.bricks.lookup import LookupTable
 
-from blocks.initialization import IsotropicGaussian, Constant
-
 import data
 import error
 
@@ -60,9 +58,9 @@ class Model(object):
 
         # Initialization
         for tbl in embed_tables:
-            tbl.weights_init = IsotropicGaussian(0.001)
-        mlp.weights_init = IsotropicGaussian(0.01)
-        mlp.biases_init = Constant(0.001)
+            tbl.weights_init = config.embed_weights_init
+        mlp.weights_init = config.mlp_weights_init
+        mlp.biases_init = config.mlp_biases_init
 
         for tbl in embed_tables:
             tbl.initialize()
diff --git a/model/dest_simple_mlp_tgtcls_alexandre.py b/model/dest_simple_mlp_tgtcls_alexandre.py
deleted file mode 100644
index 825bf80..0000000
--- a/model/dest_simple_mlp_tgtcls_alexandre.py
+++ /dev/null
@@ -1,75 +0,0 @@
-import numpy 
-
-import theano
-from theano import tensor
-
-from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax
-from blocks.bricks.lookup import LookupTable
-
-from blocks.initialization import IsotropicGaussian, Constant
-
-import data
-import error
-
-class Model(object):
-    def __init__(self, config):
-        # The input and the targets
-        x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0]
-        x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1]
-
-        x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0]
-        x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1]
-
-        input_list = [x_firstk_latitude, x_firstk_longitude, x_lastk_latitude, x_lastk_longitude]
-        embed_tables = []
-
-        self.require_inputs = ['first_k_latitude', 'first_k_longitude', 'last_k_latitude', 'last_k_longitude']
-
-        for (varname, num, dim) in config.dim_embeddings:
-            self.require_inputs.append(varname)
-            vardata = tensor.lvector(varname)
-            tbl = LookupTable(length=num, dim=dim, name='%s_lookup'%varname)
-            embed_tables.append(tbl)
-            input_list.append(tbl.apply(vardata))
-
-        y = tensor.concatenate((tensor.vector('destination_latitude')[:, None],
-                                tensor.vector('destination_longitude')[:, None]), axis=1)
-
-        # Define the model
-        mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + [Softmax()],
-                           dims=[config.dim_input] + config.dim_hidden + [config.dim_output])
-        classes = theano.shared(numpy.array(config.tgtcls, dtype=theano.config.floatX), name='classes')
-
-        # Create the Theano variables
-        inputs = tensor.concatenate(input_list, axis=1)
-
-        # inputs = theano.printing.Print("inputs")(inputs)
-        cls_probas = mlp.apply(inputs)
-        outputs = tensor.dot(cls_probas, classes)
-
-        # outputs = theano.printing.Print("outputs")(outputs)
-        # y = theano.printing.Print("y")(y)
-
-        outputs.name = 'outputs'
-
-        # Calculate the cost
-        cost = error.erdist(outputs, y).mean()
-        cost.name = 'cost'
-        hcost = error.hdist(outputs, y).mean()
-        hcost.name = 'hcost'
-
-        # Initialization
-        for tbl in embed_tables:
-            tbl.weights_init = IsotropicGaussian(0.01)
-        mlp.weights_init = IsotropicGaussian(0.1)
-        mlp.biases_init = Constant(0.01)
-
-        for tbl in embed_tables:
-            tbl.initialize()
-        mlp.initialize()
-
-        self.cost = cost
-        self.monitor = [cost, hcost]
-        self.outputs = outputs
-        self.pred_vars = ['destination_latitude', 'destination_longitude']
-
diff --git a/model/time_simple_mlp.py b/model/time_simple_mlp.py
index 1568ed3..9e1b10a 100644
--- a/model/time_simple_mlp.py
+++ b/model/time_simple_mlp.py
@@ -1,8 +1,6 @@
 from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity
 from blocks.bricks.lookup import LookupTable
 
-from blocks.initialization import IsotropicGaussian, Constant
-
 from theano import tensor
 
 import data
@@ -11,11 +9,11 @@ import error
 class Model(object):
     def __init__(self, config):
         # The input and the targets
-        x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.porto_center[0]) / data.data_std[0]
-        x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.porto_center[1]) / data.data_std[1]
+        x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0]
+        x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1]
 
-        x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.porto_center[0]) / data.data_std[0]
-        x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.porto_center[1]) / data.data_std[1]
+        x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0]
+        x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1]
 
         input_list = [x_firstk_latitude, x_firstk_longitude, x_lastk_latitude, x_lastk_longitude]
         embed_tables = []
@@ -29,7 +27,7 @@ class Model(object):
             embed_tables.append(tbl)
             input_list.append(tbl.apply(vardata))
 
-        y = tensor.lvector('time')
+        y = tensor.lvector('travel_time')
 
         # Define the model
         mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + [Identity()],
@@ -38,7 +36,7 @@ class Model(object):
         # Create the Theano variables
         inputs = tensor.concatenate(input_list, axis=1)
         # inputs = theano.printing.Print("inputs")(inputs)
-        outputs = tensor.exp(mlp.apply(inputs) + 2)
+        outputs = config.exp_base ** mlp.apply(inputs)
 
         # outputs = theano.printing.Print("outputs")(outputs)
         # y = theano.printing.Print("y")(y)
@@ -51,9 +49,9 @@ class Model(object):
 
         # Initialization
         for tbl in embed_tables:
-            tbl.weights_init = IsotropicGaussian(0.001)
-        mlp.weights_init = IsotropicGaussian(0.01)
-        mlp.biases_init = Constant(0.001)
+            tbl.weights_init = config.embed_weights_init
+        mlp.weights_init = config.mlp_weights_init
+        mlp.biases_init = config.mlp_biases_init
 
         for tbl in embed_tables:
             tbl.initialize()
@@ -62,4 +60,4 @@ class Model(object):
         self.cost = cost
         self.monitor = [cost]
         self.outputs = outputs
-        self.pred_vars = ['time']
+        self.pred_vars = ['travel_time']