Two inputs to model, stacks and flat counts

1 files changed, 67 insertions, 49 deletions

diff --git a/src/train5.py b/src/train5.py
index dd02df7..99ebd68 100644
--- a/src/train5.py
+++ b/src/train5.py
@@ -1,10 +1,8 @@
 import pandas as pd
 import numpy as np
 
-import tensorflow.keras.losses
-
-from tensorflow.keras.models import Sequential
-from tensorflow.keras.layers import Dropout
+from tensorflow.keras.models import Model
+from tensorflow.keras.layers import Concatenate
 from tensorflow.keras.layers import Input
 from tensorflow.keras.layers import Dense
 from tensorflow.keras.layers import Convolution2D
@@ -13,48 +11,68 @@ from tensorflow.keras.layers import Flatten
 # 30 10(11) 5
 # 27 17 4
 
-size = 6
-magic = int(size*3/2.0)
-shape = (-1, size, size, 8)
-
-model = Sequential([
-    Input(shape[1:]),
-    Convolution2D(magic, kernel_size=(3, 3), strides=(1, 1),
-                  padding='valid',
-                  activation="relu", use_bias=True),
-    Flatten(),
-    Dropout(0.2),
-    Dense(magic, activation="relu", use_bias=True),
-    Dense(2, activation="softmax")
-])
-
-model.compile(loss='categorical_crossentropy',
-              optimizer='adam',
-              metrics=['accuracy'])
-
-model.summary()
-
-tr_fn = "validation-"+str(size)+".csv"
-training_csv = pd.read_csv(tr_fn).head(80000)
-training_data = training_csv
-training_input = np.array(training_data.iloc[:, :-2]).reshape(shape)
-training_outcome = training_data.iloc[:, -2:]
-
-val_fn = "validation-"+str(size)+".csv"
-val_data = pd.read_csv(val_fn).tail(20000)
-val_input = np.array(val_data.iloc[:, :-2]).reshape(shape)
-val_outcome = val_data.iloc[:, -2:]
-
-results = []
-reps = 10
-for i in range(0, reps):
-    print("Iteration ", i)
-    history = model.fit(training_input, training_outcome, epochs=1,
-                        validation_data=(val_input, val_outcome),
-                        verbose=False)
-    loss, accuracy = model.evaluate(val_input, val_outcome, verbose=False)
-    results += [(loss, accuracy)]
-
-print("\n\n")
-for i in range(0, reps):
-    print("Iteration ", i, ": ", results[i])
+def make_model(size, magic=6):
+    # Our model for the stacks, a small CNN
+    stack_shape = (size, size, 8)
+    stack_input = Input(shape=stack_shape)
+    stack_model = Convolution2D(magic, kernel_size=(3, 3), strides=(1, 1),
+                                padding='valid', activation="relu",
+                                use_bias=True)(stack_input)
+    stack_model = Flatten()(stack_model)
+    # stack_model = Dense(magic, activation="relu", use_bias=True)(stack_model)
+    stack_model = Model(inputs=stack_input, outputs=stack_model)
+
+    # The overall model
+    flats_input = Input(shape=(2,))
+    combn_input = Concatenate()([stack_model.output, flats_input])
+    model = Dense(magic+2, activation="relu", use_bias=True)(combn_input)
+    model = Dense(magic, activation="relu", use_bias=True)(model)
+    model = Dense(2, activation="sigmoid", use_bias=True)(model)
+    model = Model(inputs=[stack_model.input, flats_input], outputs=model)
+
+    model.compile(optimizer='adam',
+                  loss='binary_crossentropy',
+                  # loss='categorical_crossentropy',
+                  # loss='mean_squared_error',
+                  metrics=['accuracy'])
+
+    model.summary()
+    return model
+
+def train(size, model, reps):
+    shape = (-1, size, size, 8)
+
+    tr_fn = "training-"+str(size)+".csv"
+    training_csv = pd.read_csv(tr_fn) # .head(80000)
+    training_data = training_csv
+    training_stack_input = np.array(training_data.iloc[:, 2:-2]).reshape(shape)
+    training_flats_input = np.array(training_data.iloc[:, 0:2])
+    training_input = [training_stack_input, training_flats_input]
+    training_outcome = training_data.iloc[:, -2:]
+
+    val_fn = "validation-"+str(size)+".csv"
+    val_data = pd.read_csv(val_fn).tail(20000)
+    val_stack_input = np.array(val_data.iloc[:, 2:-2]).reshape(shape)
+    val_flats_input = np.array(val_data.iloc[:, 0:2])
+    val_input = [val_stack_input, val_flats_input]
+    val_outcome = val_data.iloc[:, -2:]
+
+    results = []
+    for i in range(0, reps):
+        print("Iteration {0}/{1}".format(i+1, reps))
+        model.fit(training_input, training_outcome, epochs=5,
+                  validation_data=(val_input, val_outcome),
+                  verbose=True)
+        v_loss, v_accuracy = model.evaluate(val_input, val_outcome, verbose=False)
+        t_loss, t_accuracy = model.evaluate(training_input, training_outcome,
+                                            verbose=False)
+        results += [((v_loss, t_loss), (v_accuracy, t_accuracy))]
+
+    print("\n\n")
+    for i in range(0, reps):
+        print("Iteration {0}/{1}: {2}".format(i+1, reps, results[i]))
+
+    return model
+
+# model = train(5, make_model(5), 50)
+# print(model.trainable_variables)