Fixed minimax (!), fixed bugs in tak.c

With minimax of depth 1 the evaluation function seems alright with the
current method of training and generating weights

1 files changed, 16 insertions, 6 deletions

diff --git a/src/train5.py b/src/train5.py
index 71a8652..c3fec82 100644
--- a/src/train5.py
+++ b/src/train5.py
@@ -31,6 +31,17 @@ def truncated_pade_logistic(x):
                               divide(x, add(square(x), k(10.0))))))
     return minimum(k(1.0), maximum(k(0.0), divide(val, k(24.0))))
 
+
+# A cheaper version of tanh, x/6+25*x/(6*(2*x*x+5)),
+# clamped between -1 and 1.
+def truncated_pade_tanh(x):
+    val = add(divide(x, k(6.0)),
+              multiply(k(25.0),
+                       divide(x, multiply(k(6.0), add(k(5.0),
+                                                      multiply(k(2.0), square(x)))))))
+    return minimum(k(1.0), maximum(k(-1.0), val))
+
+
 def make_model(size, magic=[12, 9, 9]):
     # Our model for the stacks, a small CNN
     stack_shape = (size, size, 8)
@@ -59,7 +70,7 @@ def make_model(size, magic=[12, 9, 9]):
 
 def load_data(size):
     shape = (-1, size, size, 8)
-
+    # Load training data
     tr_fn = "training-"+str(size)+".csv"
     training_csv = pd.read_csv(tr_fn)  #.head(100000)
     training_data = training_csv
@@ -67,14 +78,13 @@ def load_data(size):
     training_flats_input = np.array(training_data.iloc[:, 0:2])
     training_input = [training_stack_input, training_flats_input]
     training_outcome = training_data.iloc[:, -1:]
-
+    # Load validation data
     val_fn = "validation-"+str(size)+".csv"
-    val_data = pd.read_csv(val_fn)  #.tail(20000)
+    val_data = pd.read_csv(val_fn).tail(20000)
     val_stack_input = np.array(val_data.iloc[:, 2:-1]).reshape(shape, order='F')
     val_flats_input = np.array(val_data.iloc[:, 0:2])
     val_input = [val_stack_input, val_flats_input]
     val_outcome = val_data.iloc[:, -1:]
-
     return [(training_input, training_outcome), (val_input, val_outcome)]
 
 def train(size, model, data, iterations=1, epochs=10):
@@ -150,8 +160,8 @@ def write_weights(model):
 
 
 data = load_data(5)
-model = make_model(5, [12, 9, 9])
-results, model = train(5, model, data, iterations=10, epochs=20)
+model = make_model(5, [12, 9, 10])
+results, model = train(5, model, data, iterations=1, epochs=10)
 print("\nScores")
 for i in range(len(results)):
     print("Iteration {0}: {1}".format(i+1, results[i]))