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

10 files changed, 69 insertions, 1 deletions

diff --git a/config/dest_simple_mlp_2_cs.py b/config/dest_simple_mlp_2_cs.py
index 0dd2704..accb611 100644
--- a/config/dest_simple_mlp_2_cs.py
+++ b/config/dest_simple_mlp_2_cs.py
@@ -1,3 +1,5 @@
+from blocks.initialization import IsotropicGaussian, Constant
+
 import model.dest_simple_mlp as model
 
 import data
@@ -16,6 +18,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [200, 100]
 dim_output = 2
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_2_cswdt.py b/config/dest_simple_mlp_2_cswdt.py
index 1011488..62d0db4 100644
--- a/config/dest_simple_mlp_2_cswdt.py
+++ b/config/dest_simple_mlp_2_cswdt.py
@@ -1,5 +1,7 @@
 import model.dest_simple_mlp as model
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
@@ -20,6 +22,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [200, 100]
 dim_output = 2
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_2_noembed.py b/config/dest_simple_mlp_2_noembed.py
index 3cddcb9..bbe7798 100644
--- a/config/dest_simple_mlp_2_noembed.py
+++ b/config/dest_simple_mlp_2_noembed.py
@@ -1,5 +1,7 @@
 import model.dest_simple_mlp as model
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
@@ -13,6 +15,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [200, 100]
 dim_output = 2
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_0_cs.py b/config/dest_simple_mlp_tgtcls_0_cs.py
index 031cd12..704e62c 100644
--- a/config/dest_simple_mlp_tgtcls_0_cs.py
+++ b/config/dest_simple_mlp_tgtcls_0_cs.py
@@ -1,5 +1,7 @@
 import cPickle
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 import model.dest_simple_mlp_tgtcls as model
@@ -20,6 +22,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = []
 dim_output = tgtcls.shape[0]
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cs.py b/config/dest_simple_mlp_tgtcls_1_cs.py
index 48d9fa0..f2a22a5 100644
--- a/config/dest_simple_mlp_tgtcls_1_cs.py
+++ b/config/dest_simple_mlp_tgtcls_1_cs.py
@@ -1,5 +1,7 @@
 import cPickle
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 import model.dest_simple_mlp_tgtcls as model
@@ -20,6 +22,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [500]
 dim_output = tgtcls.shape[0]
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdt.py b/config/dest_simple_mlp_tgtcls_1_cswdt.py
index 6aa2a03..a3ae654 100644
--- a/config/dest_simple_mlp_tgtcls_1_cswdt.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdt.py
@@ -1,5 +1,7 @@
 import cPickle
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 import model.dest_simple_mlp_tgtcls as model
@@ -24,6 +26,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [500]
 dim_output = tgtcls.shape[0]
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdtx.py b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
index 7918242..6306c15 100644
--- a/config/dest_simple_mlp_tgtcls_1_cswdtx.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
@@ -1,5 +1,7 @@
 import cPickle
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 import model.dest_simple_mlp_tgtcls as model
@@ -25,6 +27,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [500]
 dim_output = tgtcls.shape[0]
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
 learning_rate = 0.0001
 momentum = 0.99
 batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py b/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
index 5642f27..8c090c7 100644
--- a/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
@@ -1,8 +1,10 @@
 import cPickle
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
-import model.dest_simple_mlp_tgtcls_alexandre as model
+import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
@@ -25,6 +27,10 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [500]
 dim_output = tgtcls.shape[0]
 
+embed_weights_init = IsotropicGaussian(0.01)
+mlp_weights_init = IsotropicGaussian(0.1) 
+mlp_biases_init = Constant(0.01)
+
 learning_rate = 0.01
 momentum = 0.9
 batch_size = 200
diff --git a/config/time_simple_mlp_1.py b/config/time_simple_mlp_1.py
index eea4159..bf3699d 100644
--- a/config/time_simple_mlp_1.py
+++ b/config/time_simple_mlp_1.py
@@ -1,5 +1,7 @@
 import model.time_simple_mlp as model
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
@@ -14,6 +16,14 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [200]
 dim_output = 1
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
+exp_base = 1.5
+
 learning_rate = 0.00001
 momentum = 0.99
 batch_size = 32
+
+valid_set = 'cuts/test_times_0'
diff --git a/config/time_simple_mlp_2_cswdtx.py b/config/time_simple_mlp_2_cswdtx.py
index ceb66e8..98467e3 100644
--- a/config/time_simple_mlp_2_cswdtx.py
+++ b/config/time_simple_mlp_2_cswdtx.py
@@ -1,5 +1,7 @@
 import model.time_simple_mlp as model
 
+from blocks.initialization import IsotropicGaussian, Constant
+
 import data
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
@@ -21,6 +23,14 @@ dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
 dim_hidden = [500, 100]
 dim_output = 1
 
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
+exp_base = 1.5
+
 learning_rate = 0.00001
 momentum = 0.99
 batch_size = 32
+
+valid_set = 'cuts/test_times_0'