diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/cnn_train.py | 59 | ||||
| -rw-r--r-- | src/pptdb.c | 2 |
2 files changed, 13 insertions, 48 deletions
diff --git a/src/cnn_train.py b/src/cnn_train.py index 0580b03..1264e9f 100644 --- a/src/cnn_train.py +++ b/src/cnn_train.py @@ -40,27 +40,17 @@ from tensorflow.keras.layers import Convolution2D from tensorflow.keras.layers import Flatten -# We need something that's close to logistic, but cheaper to compute. -# (12.0+x+50.0*x/(x*x+10.0))/24.0, clipped between 0 and 1 -# as it would otherwise exceed this range at +- 4.6 or so +# We need something that's close to 2*logistic-1, but cheaper to +# compute: (12+x+50*x/(x*x+10))/12-1, clipped between -1 and 1 as it +# would otherwise exceed this range at +- 4.6 or so def clipped_pade_logistic(x): val = add(k(12.0), add(x, multiply(k(50.0), divide(x, add(square(x), k(10.0)))))) - return clip_by_value(divide(val, k(24.0)), 0.0, 1.0) + return clip_by_value(add(k(-1.0), divide(val, k(12.0))), -1.0, +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]): +def make_model(size, magic=[12, 11, 8]): # Our model for the stacks, a small CNN stack_shape = (size, size, 6) stack_input = Input(shape=stack_shape) @@ -76,11 +66,7 @@ def make_model(size, magic=[12, 9, 9]): model = Dense(magic[2], activation="relu", use_bias=True)(model) model = Dense(1, activation=clipped_pade_logistic, use_bias=True)(model) 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.compile(optimizer='adam', loss='mean_squared_error') model.summary() return model @@ -89,7 +75,7 @@ def load_data(size): shape = (-1, size, size, 6) # Load training data tr_fn = "training-"+str(size)+".csv" - training_csv = pd.read_csv(tr_fn) #.head(100000) + training_csv = pd.read_csv(tr_fn) training_data = training_csv training_stack_input = np.array(training_data.iloc[:, 2:-1]).reshape(shape, order='F') training_flats_input = np.array(training_data.iloc[:, 0:2]) @@ -113,36 +99,17 @@ def train(size, model, data, iterations=1, epochs=10): model.fit(training_input, training_outcome, epochs=epochs, validation_data=(val_input, val_outcome), verbose=True) - v_loss, v_accuracy = model.evaluate(val_input, val_outcome, - 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))] + v_loss = model.evaluate(val_input, val_outcome, + verbose=False, batch_size=16) + t_loss = model.evaluate(training_input, training_outcome, + verbose=False, batch_size=32) + results += [(v_loss, t_loss)] print("\nScores") for i in range(len(results)): print("Iteration {0}: {1}".format(i+1, results[i])) return results -def model_size(model): - return sum([np.prod(get_value(w).shape) for w in model.trainable_weights]) - - -def magic_search(data): - results = [] - for width in range(9, 18): - for dense1 in range(9, 16): - for dense2 in range(9, max(32, dense1*2)): - m = make_model(5, [width, dense1, dense2]) - if model_size(m) < 1990: - results += [([width, dense1, dense2], - train(5, m, data, iterations=1, epochs=20))] - print("\nSummary") - for r in results: - print("Parameters {0}: {1}".format(r[0], r[1][0])) - return results - - def write_weights(model): def fix(val): string = str(np.array(val).tolist()) @@ -185,5 +152,3 @@ data = load_data(5) model = make_model(5, [12, 11, 8]) results = train(5, model, data, iterations=5, epochs=10) write_weights(model) - -# results = magic_search(data) diff --git a/src/pptdb.c b/src/pptdb.c index ecf5caa..557b894 100644 --- a/src/pptdb.c +++ b/src/pptdb.c @@ -198,7 +198,7 @@ int main(int argc, char **argv) { reset_state(size); // Store the outcome of this game. Black win = 1 if (line[read-4] == '0') outcome_black = 1; - else outcome_black = 0; + else outcome_black = -1; // Parse the line r = parse_line(line,read-4); // Adjust counts if we're not generating training data |