Finally fixed memory order of weights!

1 files changed, 32 insertions, 15 deletions

diff --git a/src/train5.py b/src/train5.py
index 5c45564..2fc0d6f 100644
--- a/src/train5.py
+++ b/src/train5.py
@@ -3,7 +3,6 @@ import pandas as pd
 import numpy as np
 
 # Output of weights
-import re
 from tensorflow import transpose
 
 # Custom activation function
@@ -33,6 +32,16 @@ def clipped_pade_logistic(x):
     return clip_by_value(divide(val, k(24.0)), 0.0, 1.0)
 
 
+# A cheaper version of tanh, x/6+25*x/(6*(2*x*x+5)),
+# clipped between -1 and 1.
+def clipped_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 clip_by_value(val, -1.0, 1.0)
+
+
 def make_model(size, magic=[12, 9, 9]):
     # Our model for the stacks, a small CNN
     stack_shape = (size, size, 6)
@@ -51,6 +60,8 @@ def make_model(size, magic=[12, 9, 9]):
     model = Model(inputs=[stack_model.input, flats_input], outputs=model)
     model.compile(optimizer='adam',
                   loss='mean_squared_error',
+                  # loss='mean_absolute_error',
+                  # loss='mean_absolute_percentage_error',
                   metrics=['accuracy'])
     model.summary()
     return model
@@ -75,6 +86,7 @@ def load_data(size):
     val_outcome = val_data.iloc[:, -1:]
     return [(training_input, training_outcome), (val_input, val_outcome)]
 
+
 def train(size, model, data, iterations=1, epochs=10):
     (training_input, training_outcome), (val_input, val_outcome) = data
     results = []
@@ -84,7 +96,7 @@ def train(size, model, data, iterations=1, epochs=10):
                   validation_data=(val_input, val_outcome),
                   verbose=True)
         v_loss, v_accuracy = model.evaluate(val_input, val_outcome,
-                                            verbose=False, batch_size=32)
+                                            verbose=False, batch_size=16)
         t_loss, t_accuracy = model.evaluate(training_input, training_outcome,
                                             verbose=False, batch_size=32)
         results += [((v_loss, t_loss), (v_accuracy, t_accuracy))]
@@ -112,18 +124,21 @@ def magic_search(data):
 
 def write_weights(model):
     def fix(val):
-        string = str(val.tolist())
+        string = str(np.array(val).tolist())
         string = string.replace("[", "{").replace("]", "}")
         return string
-    # Prepare everything in a sane memory order
-    conv2d_weights = np.array(transpose(model.trainable_variables[0], perm=[3, 1, 0, 2]))
-    conv2d_biases = np.array(model.trainable_variables[1])
-    dense1_weights = np.array(transpose(model.trainable_variables[2], perm=[1, 0]))
-    dense1_biases = np.array(model.trainable_variables[3])
-    dense2_weights = np.array(transpose(model.trainable_variables[4], perm=[1, 0]))
-    dense2_biases = np.array(model.trainable_variables[5])
-    output_weights = np.array(transpose(model.trainable_variables[6], perm=[1, 0])[0])
-    output_bias = np.array(model.trainable_variables[7][0])
+    # Prepare everything in a sane memory order This isn't exactly in
+    # the correct order that tensorflow uses, because memory access
+    # out of order is an eyesore. Compared to tensorflow, the C
+    # implementation has the board reflected about the diagonal.
+    conv2d_weights = transpose(model.trainable_variables[0], perm=[3, 0, 1, 2])
+    conv2d_biases = model.trainable_variables[1]
+    dense1_weights = transpose(model.trainable_variables[2], perm=[1, 0])
+    dense1_biases = model.trainable_variables[3])
+    dense2_weights = transpose(model.trainable_variables[4], perm=[1, 0])
+    dense2_biases = model.trainable_variables[5])
+    output_weights = transpose(model.trainable_variables[6], perm=[1, 0])[0]
+    output_bias = model.trainable_variables[7][0]
     # Prepare formatting
     names = ["conv2d_weights[KERN_NUM][KERN_SIZE][KERN_SIZE][KERN_CHAN]",
              "conv2d_biases[KERN_NUM]",
@@ -146,10 +161,12 @@ def write_weights(model):
 
 
 data = load_data(5)
-model = make_model(5, [12, 9, 10])
-results = train(5, model, data, iterations=20, epochs=10)
+model = make_model(5, [12, 11, 8])
+results = train(5, model, data, iterations=5, epochs=10)
 print("\nScores")
 for i in range(len(results)):
-   print("Iteration {0}: {1}".format(i+1, results[i]))
+    print("Iteration {0}: {1}".format(i+1, results[i]))
 
 write_weights(model)
+
+# results = magic_search(data)