cnn+dropout: reproduce: 0.60379

hw3/test_cnn.py

@@ -14,7 +14,7 @@ def ensure_dir(file_path):
 height = width = 48
 num_classes = 7
 input_shape = (height, width, 1)
-model_name = 'cnn_d3.h5'
+model_name = 'try.h5'
 
 # Read the test data
 with open(sys.argv[1], "r+") as f:

hw3/train_cnn.py

@@ -12,10 +12,9 @@
 height = width = 48
 num_classes = 7
 input_shape = (height, width, 1)
-batch_size = 32
+batch_size = 128
 epochs = 20
-pool_size = (2, 2)
-model_name = 'cnn_d3.h5'
+model_name = 'try.h5'
 isValid = 1
 
 # Read the train data
@@ -33,26 +32,20 @@
 # Change data into CNN format
 X = X.reshape(X.shape[0], height, width, 1)
 
-# Split data
-if isValid:
- valid_num = 1000
- X_train, Y_train = X[:-valid_num], Y[:-valid_num]
- X_valid, Y_valid = X[-valid_num:], Y[-valid_num:]
-else:
- X_train, Y_train = X, Y
+X_train, Y_train = X, Y
 
 # Construct the model
 model = Sequential()
-model.add(Conv2D(25, (3, 3), activation='relu', input_shape=input_shape))
-model.add(Conv2D(50, (3, 3), activation='relu'))
-model.add(MaxPooling2D(pool_size=pool_size))
-model.add(Dropout(0.25))
-model.add(Conv2D(50, (3, 3), activation='relu'))
-model.add(Conv2D(100, (3, 3), activation='relu'))
-model.add(AveragePooling2D(pool_size=pool_size))
-model.add(Dropout(0.25))
+model.add(Conv2D(32, (3, 3), activation='relu', input_shape=input_shape))
+model.add(Conv2D(64, (3, 3), activation='relu'))
+model.add(MaxPooling2D(pool_size=(3, 3)))
+model.add(Dropout(0.5))
+model.add(Conv2D(128, (3, 3), activation='relu'))
+model.add(Conv2D(256, (3, 3), activation='relu'))
+model.add(AveragePooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.5))
 model.add(Flatten())
-model.add(Dense(500, activation='relu'))
+model.add(Dense(128, activation='relu'))
 model.add(Dropout(0.5))
 model.add(Dense(num_classes))
 model.add(Activation('softmax'))
@@ -69,20 +62,12 @@
  batch_size=batch_size,
  epochs=epochs,
  verbose=1,
- validation_data=(X_valid, Y_valid))
+ validation_split=0.2)
 else:
  model.fit(X_train, Y_train,
  batch_size=batch_size,
  epochs=epochs,
  verbose=1)
 
-# Evaluate the test data
-if isValid:
- score = model.evaluate(X_valid, Y_valid, verbose=0)
-else:
- score = model.evaluate(X_train, Y_train, verbose=0)
-print('Test loss:', score[0])
-print('Test accuracy:', score[1])
-
 # Save model
 model.save(model_name)