diff options
| -rwxr-xr-x | extract.sh | 19 | ||||
| -rw-r--r-- | src/pptdb.c | 21 | ||||
| -rw-r--r-- | src/train5.py | 102 |
3 files changed, 75 insertions, 67 deletions
@@ -5,8 +5,8 @@ db_file=games_anon.db query() { query="(size == $1) and (result != '1-0') and (result != '0-1') and (result != '0-0')" selct="" - # for player in rabbitboy84 fwwwwibib archvenison Simmon AaaarghBot; do - for player in; do + for player in rabbitboy84 fwwwwibib archvenison Simmon AaaarghBot; do + # for player in; do selct="$selct(player_black == '$player') or (player_white == '$player') or " done; if [ -n "$selct" ]; then @@ -30,14 +30,13 @@ process() { num_games=$2 ./pptdb "$size" "data/playtak-$size" > "data/check-$size" tail -n22 "data/check-$size" - echo -ne "\tStripping overflows and illegal games..." + echo -ne "\tStripping overflows and illegal games... " grep -Fvxf "data/check-$size" "data/playtak-$size" > "data/good-playtak-$size" - echo -e "Done\n\tChoosing $num_games from what remains ..." + echo -en "Done.\n\tChoosing $num_games from what remains... " shuf -n $num_games "data/good-playtak-$size" > "data/smalltak-$size" - echo -en "Done\n\tGenerating training data... " + echo -en "Done.\n\tGenerating training data... " ./pptdb "$size" "data/smalltak-$size" generate - echo -e "\tDone, $(wc -l data/training-$size.csv | cut -d\ -f1) samples." - echo -en "\tShuffling... " + echo -en "\tShuffling $(wc -l data/training-$size.csv | cut -d\ -f1) samples... " head -n 1 "data/training-$size.csv" > "data/shuf-$size.csv" tail -n+2 "data/training-$size.csv" | shuf >> "data/shuf-$size.csv" mv "data/shuf-$size.csv" "data/training-$size.csv" @@ -46,14 +45,14 @@ process() { rm "data/training-$size.csv.gz" fi gzip "data/training-$size.csv" - echo -e "Done!\n\tCompressed version available in data/training-$size.csv.gz" + echo "Done, available in data/training-$size.csv.gz" } make pptdb for size in 5 6; do - extract $size notation,result - process $size 20000 echo + extract $size notation,result + process $size 30000 done diff --git a/src/pptdb.c b/src/pptdb.c index e681735..8e8285a 100644 --- a/src/pptdb.c +++ b/src/pptdb.c @@ -17,12 +17,11 @@ write_input(void) { /* fprintf(training_fh,"%d,",current_colour == C_BLACK); */ // Two numbers for flats remaining - /* - * fprintf(training_fh,"%.6f,%.6f,", - * (float)(white_count & 127)/max_flats, - * (float)(black_count & 127)/max_flats); - */ + fprintf(training_fh,"%.8f,%.8f,", + (float)(white_count & 127)/max_flats, + (float)(black_count & 127)/max_flats); + // Top layer of stacks is handled differently to indicate stone type float val; uint16_t mask = 1; for (int k = 0; k < board_size * board_size; k++) { @@ -38,7 +37,7 @@ write_input(void) { } fprintf(training_fh,"%.2f,", val); } - + // Layers underneath for (int depth = 1; depth < max_depth; depth++) { for (int k = 0; k < board_size * board_size; k++) { val = 0; @@ -48,7 +47,6 @@ write_input(void) { mask <<= 1; } - /* * float t; * for (int k = 0; k < board_size * board_size; k++) { @@ -165,19 +163,12 @@ main(int argc, char **argv) { if (training_fh == NULL) exit(EXIT_FAILURE); // Write header - /* fputs("\"Player\",\"White flats\",\"Black flats\",",training_fh); */ + fputs("\"White flats\",\"Black flats\",",training_fh); for (int depth = 0; depth < max_depth; depth++) { for (int k = 0; k < size*size; k++) { fprintf(training_fh,"\"Stack %d %d\",",depth,k); } } - - /* - * for (int k = 0; k < size*size; k++) { - * fprintf(training_fh,"\"BT %d\",",k); - * } - */ - fputs("\"White win\",\"Black win\"\n",training_fh); } else generate=0; 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) +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 -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") -]) +def train(size, model, reps): + shape = (-1, size, size, 8) -model.compile(loss='categorical_crossentropy', - optimizer='adam', - metrics=['accuracy']) + 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:] -model.summary() + 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:] -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:] + 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))] -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:] + print("\n\n") + for i in range(0, reps): + print("Iteration {0}/{1}: {2}".format(i+1, reps, results[i])) -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)] + return model -print("\n\n") -for i in range(0, reps): - print("Iteration ", i, ": ", results[i]) +# model = train(5, make_model(5), 50) +# print(model.trainable_variables) |