diff options
Diffstat (limited to 'src/train5.py')
| -rw-r--r-- | src/train5.py | 53 |
1 files changed, 24 insertions, 29 deletions
diff --git a/src/train5.py b/src/train5.py index ea25e5e..dd02df7 100644 --- a/src/train5.py +++ b/src/train5.py @@ -1,9 +1,6 @@ import pandas as pd import numpy as np -from tensorflow.keras.regularizers import l1 -from tensorflow.keras.regularizers import l2 - import tensorflow.keras.losses from tensorflow.keras.models import Sequential @@ -11,55 +8,53 @@ from tensorflow.keras.layers import Dropout from tensorflow.keras.layers import Input from tensorflow.keras.layers import Dense from tensorflow.keras.layers import Convolution2D -from tensorflow.keras.layers import MaxPooling2D from tensorflow.keras.layers import Flatten -from tensorflow.keras.layers import Activation -from tensorflow.keras.layers import BatchNormalization # 30 10(11) 5 # 27 17 4 -shape = (-1, 5, 5, 8) +size = 6 +magic = int(size*3/2.0) +shape = (-1, size, size, 8) model = Sequential([ Input(shape[1:]), - Convolution2D(1, kernel_size=3, strides=(1, 1), - padding='same', + Convolution2D(magic, kernel_size=(3, 3), strides=(1, 1), + padding='valid', activation="relu", use_bias=True), - # Dropout(0.2), Flatten(), - Dense(10, activation="relu", use_bias=True), - # Dropout(0.2), - # Dense(10, activation="relu", use_bias=False), - # Dropout(0.2), + Dropout(0.2), + Dense(magic, activation="relu", use_bias=True), Dense(2, activation="softmax") ]) - # bias_regularizer=l2(0.001), - # kernel_regularizer=l1(0.001)), - model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) model.summary() -csv = pd.read_csv("training-5.csv") - -training_data = csv.head(100000).copy() +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:] -test_data = csv.tail(20000).copy() -test_input = np.array(test_data.iloc[:, :-2]).reshape(shape) -test_outcome = test_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 = [] -for i in range(0, 1): +reps = 10 +for i in range(0, reps): print("Iteration ", i) - history = model.fit(training_input, training_outcome, epochs=10, - validation_data=(test_input, test_outcome)) - loss, accuracy = model.evaluate(test_input, test_outcome) - results += [(i, loss, accuracy)] + 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\nResults: ", results) +print("\n\n") +for i in range(0, reps): + print("Iteration ", i, ": ", results[i]) |