def main():
# Parse arguments
parser = argparse.ArgumentParser()
parser.add_argument(dest="data_path",
metavar="DATA_PATH",
help="Path to read data from.")
parser.add_argument(dest="model_path",
metavar="MODEL_PATH",
help="Path to read model from.")
parser.add_argument(
"-b",
"--read_batches",
metavar="READ_BATCHES",
default=False,
help="If true, data is read incrementally in batches during training.")
args = parser.parse_args()
parse_args(args)
# Load model
with CustomObjectScope({
'_euclidean_distance': cnn_siamese_online._euclidean_distance,
'ALPHA': cnn_siamese_online.ALPHA,
"relu_clipped": cnn_siamese_online.relu_clipped
}):
tower_model = load_model(args.model_path)
tower_model.compile(
optimizer='adam',
loss='mean_squared_error') # Model was previously not compile
if not args.read_batches: # Read all data at once
# Load training triplets and validation triplets
X_train, y_train = utils.load_examples(args.data_path, "train")
X_valid, y_valid = utils.load_examples(args.data_path, "valid")
# Get abs(distance) of embeddings
X_train_emb = tower_model.predict(X_train)
X_valid_emb = tower_model.predict(X_valid)
else: # Read data in batches
raise ValueError("Reading in batches is not implemented yet.")
# Shuffle the data
X_train_emb, y_train = shuffle(X_train_emb, y_train)
X_valid_emb, y_valid = shuffle(X_valid_emb, y_valid)
# Run k-means on training data
print("Running K-means...")
k_means_model = KMeans(n_clusters=K, verbose=0)
k_means_model.fit(X_train_emb)
# Plot result
k_means_PCA(k_means_model, X_train_emb, y_train, display_k_means=True)
k_means_PCA(k_means_model, X_train_emb, y_train, display_k_means=False)
# Compute percentage of each class in each cluster
compute_cluster_class_fractions(k_means_model, y_train)
def compute_statistics(dataset, relative_threshold):
path = './' + dataset.dataset_name + '/examples/'
na_ex = load_examples(path+'examples.pkl')
na_train = PerClassDataset(na_ex)
a_ex = load_examples(path+'augmented_examples_topn5_cos_sim0.6.pkl')
a_train = PerClassDataset(a_ex)
threshold = int(a_train.stats()['most common labels number of examples'] / relative_threshold)
valid_ex = load_examples(path+'valid_examples.pkl')
valid = PerClassDataset(valid_ex)
test_ex = load_examples(path+'test_examples.pkl')
test = PerClassDataset(test_ex)
val_test_ex = load_examples(path+'valid_test_examples.pkl')
val_test = PerClassDataset(val_test_ex)
oov_ex = load_examples(path+'oov_examples.pkl')
oov = PerClassDataset(oov_ex)
stats = {'non-augmented':na_train.stats(),
'augmented':a_train.stats(threshold),
'valid':valid.stats(),
'test':test.stats(),
'valid_test':val_test.stats(),
'oov':oov.stats(),
'sentences':{'train':len(dataset.get_train_sentences),
'valid':len(dataset.get_valid_sentences),
'test':len(dataset.get_test_sentences)
}
}
filepath = './'+dataset.dataset_name+'/'
os.makedirs(filepath, exist_ok=True)
with open(filepath + 'statistics.json', 'w') as file:
json.dump(stats, file, indent=4)
def main():
# Parse arguments
args = parse_args()
# Load tower model
with CustomObjectScope({'_euclidean_distance': nn_model.Model._euclidean_distance}):
model = load_model(args.model_path)
model.compile(optimizer='adam', loss='mean_squared_error') # Model was previously not compiled
X_shape, y_shape = utils.get_shapes(args.triplets_path, "train_anchors")
# Build model to compute [A, P, N] => [abs(emb(A) - emb(P)), abs(emb(A) - emb(N))]
pair_distance_model = build_pair_distance_model(model, X_shape[1:])
pair_distance_model.compile(optimizer="adam", loss="mean_squared_error") # Need to compile in order to predict
# Load test data
_, y_test_shape = utils.get_shapes(args.triplets_path, "test")
n_users = y_test_shape[1]
X_test_separated = []
for j in range(n_users):
X_test_j = utils.load_X(args.triplets_path, "test_" + str(j))
X_test_separated.append(X_test_j)
# If no svm model supplied, and no sweep:
# Train a new model
if args.load_model_path is None:
# Load training triplets and validation triplets
X_train_anchors, _ = utils.load_examples(args.triplets_path, "train_anchors")
X_train_positives, _ = utils.load_examples(args.triplets_path, "train_positives")
X_train_negatives, _ = utils.load_examples(args.triplets_path, "train_negatives")
# Get abs(distance) of embeddings
X_train_ap, X_train_an, X_train_pn = pair_distance_model.predict([X_train_anchors, X_train_positives, X_train_negatives])
# Stack positive and negative examples
X_train = np.vstack((X_train_ap, X_train_an, X_train_pn))
y_train = np.hstack((np.ones(X_train_ap.shape[0], ), np.zeros(X_train_an.shape[0] + X_train_pn.shape[0],)))
# Sign of distances should not matter -> Train on both
X_train = np.vstack((X_train, -X_train))
y_train = np.hstack((y_train, y_train))
# Shuffle the data
X_train, y_train = shuffle(X_train, y_train)
# Train SVM
svm_model = svm.SVC(C=C, gamma=GAMMA, kernel=KERNEL, class_weight=CLASS_WEIGHTS, verbose=True, probability=args.sweep)
svm_model.fit(X_train[:20000, :], y_train[:20000])
else: # if svm model supplied
with open(args.load_model_path, "rb") as svm_file:
svm_model = pickle.load(svm_file)
random.seed(1)
accuracy, FAR, FRR = predict_and_evaluate(pair_distance_model, svm_model, X_test_separated,
args.ensemble_size, args.ensemble_type, threshold=0.5, probability=False)
print("\n---- Test Results ----")
print("Accuracy = {}".format(accuracy))
print("FAR = {}".format(FAR))
print("FRR = {}".format(FRR))
if args.sweep:
# Sweep the threshold
FARs, FRRs = [], []
min_diff = float("inf")
FAR_EER, FRR_EER = 1, 1
accuracy_EER = 0
threshold_EER = None
for threshold in np.arange(0, 1, 0.01):
# Predict and evaluate
accuracy, FAR, FRR = predict_and_evaluate(pair_distance_model, svm_model, X_test_separated,
args.ensemble_size, args.ensemble_type, threshold=threshold, probability=True)
# Store results
FARs.append(FAR)
FRRs.append(FRR)
if np.abs(FAR - FRR) < min_diff:
FAR_EER = FAR
FRR_EER = FRR
accuracy_EER = accuracy
threshold_EER = threshold
min_diff = np.abs(FAR - FRR)
# Report EER and corresponding accuracy
print("\n ---- Test Results: EER ----")
print("Accuracy = {}".format(accuracy_EER))
print("FAR = {}".format(FAR_EER))
print("FRR = {}".format(FRR_EER))
print("Threshold EER = {}".format(threshold_EER))
# Plot FRR vs FAR
plt.figure()
plt.scatter(FARs, FRRs)
plt.xlabel("FAR")
plt.ylabel("FRR")
plt.savefig("FRR_FAR.pdf")
else: # no sweep
random.seed(1)
accuracy, FAR, FRR = predict_and_evaluate(pair_distance_model, svm_model, X_test_separated,
args.ensemble_size, args.ensemble_type, threshold=0.5, probability=False)
print("\n---- Test Results ----")
print("Accuracy = {}".format(accuracy))
print("FAR = {}".format(FAR))
print("FRR = {}".format(FRR))
# Save svm model
if args.save_model_path is not None:
with open(args.save_model_path + "svm_model.pkl", "wb") as svm_file:
pickle.dump(svm_model, svm_file)
def prepare_data(
dataset,
embeddings,
vectorizer,
n=15,
ratio=.8,
use_gpu=False,
k=1,
data_augmentation=False,
over_population_threshold=100,
relative_over_population=True,
debug_mode=False,
verbose=True,
):
# Train-validation part
path = './data/' + dataset.dataset_name + '/examples/'
if data_augmentation:
examples = load_examples(path +
'augmented_examples_topn5_cos_sim0.6.pkl')
else:
examples = load_examples(path + 'examples.pkl')
if debug_mode:
examples = list(examples)[:128]
examples = truncate_examples(examples, n)
transform = vectorizer.vectorize_unknown_example
def target_transform(y):
return embeddings[y]
train_valid_dataset = PerClassDataset(
examples,
transform=transform,
target_transform=target_transform,
)
train_dataset, valid_dataset = train_valid_dataset.split(
ratio=.8, shuffle=True, reuse_label_mappings=False)
filter_labels_cond = None
if over_population_threshold != None:
if relative_over_population:
over_population_threshold = int(
train_valid_dataset.stats()
['most common labels number of examples'] /
over_population_threshold)
def filter_labels_cond(label, N):
return N <= over_population_threshold
train_loader = PerClassLoader(dataset=train_dataset,
collate_fn=collate_fn,
batch_size=64,
k=k,
use_gpu=use_gpu,
filter_labels_cond=filter_labels_cond)
valid_loader = PerClassLoader(dataset=valid_dataset,
collate_fn=collate_fn,
batch_size=64,
k=k,
use_gpu=use_gpu,
filter_labels_cond=filter_labels_cond)
# Test part
test_examples = load_examples(path + 'valid_test_examples.pkl')
test_examples = truncate_examples(test_examples, n)
test_dataset = PerClassDataset(dataset=test_examples, transform=transform)
test_loader = PerClassLoader(dataset=test_dataset,
collate_fn=collate_x,
k=-1,
shuffle=False,
batch_size=64,
use_gpu=use_gpu)
# OOV part
oov_examples = load_examples(path + 'oov_examples.pkl')
oov_examples = truncate_examples(oov_examples, n)
oov_dataset = PerClassDataset(dataset=oov_examples, transform=transform)
oov_loader = PerClassLoader(dataset=oov_dataset,
collate_fn=collate_x,
k=-1,
shuffle=False,
batch_size=64,
use_gpu=use_gpu)
if verbose:
logging.info('Number of unique examples: {}'.format(len(examples)))
logging.info('\nGlobal statistics:')
stats = train_valid_dataset.stats()
for stats, value in stats.items():
logging.info(stats + ': ' + str(value))
logging.info('\nStatistics on the training dataset:')
stats = train_dataset.stats(over_population_threshold)
for stats, value in stats.items():
logging.info(stats + ': ' + str(value))
logging.info('\nStatistics on the validation dataset:')
stats = valid_dataset.stats(over_population_threshold)
for stats, value in stats.items():
logging.info(stats + ': ' + str(value))
logging.info('\nStatistics on the test dataset:')
stats = test_dataset.stats()
for stats, value in stats.items():
logging.info(stats + ': ' + str(value))
logging.info('\nFor training, loading ' + str(k) +
' examples per label per epoch.')
return train_loader, valid_loader, test_loader, oov_loader
def main():
parser = argparse.ArgumentParser()
parser.add_argument(dest="data_path", metavar="DATA_PATH", help="Path to read examples from.")
parser.add_argument("-s", "--save_path", metavar="SAVE_PATH", default=None, help="Path to save trained model to. If no path is specified checkpoints are not saved.")
parser.add_argument("-m", "--metrics-path", metavar="METRICS_PATH", default=None, help="Path to save additional performance metrics to (for debugging purposes).")
args = parser.parse_args()
if args.save_path is not None:
if not os.path.isdir(args.save_path):
response = input("Save path does not exist. Create it? (Y/n) >> ")
if response.lower() not in ["y", "yes", "1", ""]:
exit()
else:
os.makedirs(args.save_path)
if args.metrics_path is not None:
if not os.path.isdir(args.metrics_path):
response = input("Metrics path does not exist. Create it? (Y/n) >> ")
if response.lower() not in ["y", "yes", "1", ""]:
exit()
else:
os.makedirs(args.metrics_path)
# Load training and validation data
X_train, y_train = utils.load_examples(args.data_path, "train")
X_valid, y_valid = utils.load_examples(args.data_path, "valid")
# Shuffle the data
X_train, y_train = utils.shuffle_data(X_train, y_train)
X_valid, y_valid = utils.shuffle_data(X_valid, y_valid)
# Build model
input_shape = X_train.shape[1:]
n_classes = y_train.shape[1]
model = build_model(input_shape, n_classes)
# Compile model
adam_optimizer = optimizers.Adam(lr=LEARNING_RATE)
model.compile(loss="categorical_crossentropy", optimizer=adam_optimizer, metrics=["accuracy"])
# Setup callbacks for early stopping and model saving
callback_list = setup_callbacks(args.save_path, n_classes)
# Train model
model.fit(X_train, y_train, validation_data=(X_valid, y_valid), batch_size=BATCH_SIZE,
epochs=EPOCHS, callbacks=callback_list)
global training_complete
training_complete = True
# Load test data
X_test_v, y_test_v = utils.load_examples(args.data_path, "test_valid")
X_test_u, y_test_u = utils.load_examples(args.data_path, "test_unknown")
X_test = np.vstack((X_test_v, X_test_u))
y_test = np.vstack((y_test_v, y_test_u))
# Test model
print("Evaluating model...")
loss, accuracy = model.evaluate(X_test_v, y_test_v, verbose=1)
FAR, FRR = compute_FAR_FRR(model, X_test, y_test)
print("\n---- Test Results ----")
print("Loss = {}, Accuracy = {}".format(loss, accuracy))
print("FAR = {}, FRR = {}".format(FAR, FRR))
# Additional metrics
if args.metrics_path is not None:
# Confusion matrix
y_pred = model.predict(X_test_v)
y_pred = utils.one_hot_to_index(y_pred)
y_true = utils.one_hot_to_index(y_test_v)
conf_matrix = confusion_matrix(y_true, y_pred)
np.savetxt(args.metrics_path + "confusion_matrix.txt", conf_matrix)
def main():
prework()
# load data
examples = load_examples(a)
# load model
model = create_model(examples.blur, examples.pan, examples.mul,
examples.blur_u)
with tf.name_scope("images"):
display_fetches = {
"imnames": examples.imnames,
"blur_u": examples.blur_u,
"blur": examples.blur,
"pan": examples.pan,
"mul": examples.mul,
"mul_hat": model.outputs,
}
with tf.name_scope("blur_u_summary"):
tf.summary.image("blur_u", examples.blur_u)
with tf.name_scope("blur_summary"):
tf.summary.image("blur", examples.blur)
with tf.name_scope("mul_summary"):
tf.summary.image("mul", examples.mul)
with tf.name_scope("mul_hat_summary"):
tf.summary.image("mul_hat", model.outputs)
with tf.name_scope("predict_real_summary"):
tf.summary.image("predict_real", model.predict_real)
with tf.name_scope("predict_fake_summary"):
tf.summary.image("predict_fake", model.predict_fake)
tf.summary.scalar("discriminator_loss", model.discrim_loss)
tf.summary.scalar("generator_loss_GAN", model.gen_loss_GAN)
tf.summary.scalar("generator_loss_L1", model.gen_loss_L1)
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name + "/values", var)
for grad, var in model.discrim_grads_and_vars + model.gen_grads_and_vars:
tf.summary.histogram(var.op.name + "/gradients", grad)
with tf.name_scope("parameter_count"):
parameter_count = tf.reduce_sum(
[tf.reduce_prod(tf.shape(v)) for v in tf.trainable_variables()])
saver = tf.train.Saver(max_to_keep=1)
logdir = a.output_dir if (a.trace_freq > 0 or a.summary_freq > 0) else None
sv = tf.train.Supervisor(logdir=logdir, save_summaries_secs=0, saver=None)
with sv.managed_session() as sess:
print("parameter_count = ", sess.run(parameter_count))
if a.checkpoint is not None:
print("loading model from checkpoint")
checkpoint = tf.train.latest_checkpoint(a.checkpoint)
saver.restore(sess, checkpoint)
max_steps = 100
if a.max_epochs is not None:
max_steps = examples.steps_per_epoch * a.max_epochs
if a.max_steps is not None:
max_steps = a.max_steps
if a.mode == "test":
max_steps = min(examples.steps_per_epoch, max_steps)
for step in range(max_steps):
results = sess.run(display_fetches)
save_images(results, a)
print("test over")
else:
start = time.time()
sv_gloss = -1
for step in range(max_steps):
def should(freq):
return freq > 0 and ((step + 1) % freq == 0
or step == max_steps - 1)
options = None
run_metadata = None
if should(a.trace_freq):
options = tf.RunOptions(
trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
fetches = {
"train": model.train,
"global_step": sv.global_step,
}
if should(a.progress_freq) or should(a.save_freq):
fetches["discrim_loss"] = model.discrim_loss
fetches["gen_loss_GAN"] = model.gen_loss_GAN
fetches["gen_loss_L1"] = model.gen_loss_L1
if should(a.summary_freq):
fetches["summary"] = sv.summary_op
if should(a.display_freq):
fetches["display"] = display_fetches
results = sess.run(fetches,
options=options,
run_metadata=run_metadata)
if should(a.summary_freq):
print("recording summary")
sv.summary_writer.add_summary(results["summary"],
results["global_step"])
if should(a.display_freq):
print("saving display images")
save_images(results["display"],
a,
step=results["global_step"])
if should(a.trace_freq):
print("recording trace")
sv.summary_writer.add_run_metadata(
run_metadata, "step_%d" % results["global_step"])
if should(a.progress_freq):
# global_step will have the correct step count if we resume from a checkpoint
train_epoch = math.ceil(results["global_step"] /
examples.steps_per_epoch)
train_step = (results["global_step"] -
1) % examples.steps_per_epoch + 1
rate = (step + 1) * a.batch_size / (time.time() - start)
remaining = (max_steps - step) * a.batch_size / rate
print(
"progress epoch %d step %d image/sec %0.1f remaining %dm"
% (train_epoch, train_step, rate, remaining / 60))
print("discrim_loss", results["discrim_loss"])
print("gen_loss_GAN", results["gen_loss_GAN"])
print("gen_loss_L1", results["gen_loss_L1"])
if should(a.save_freq):
print("saving model")
gloss = results["gen_loss_GAN"] * a.gan_weight + results[
"gen_loss_L1"] * a.l1_weight
if sv_gloss == -1 or gloss < sv_gloss or True:
sv_gloss = gloss
saver.save(sess,
os.path.join(a.output_dir, "model"),
global_step=sv.global_step)
else:
print("skipped because of worse loss")
if sv.should_stop():
break
def main():
# Parse arguments
parser = argparse.ArgumentParser()
parser.add_argument(dest="data_path", metavar="DATA_PATH", help="Path to read examples from.")
parser.add_argument("-sW", "--save_weights_path", metavar="SAVE_WEIGHTS_PATH", default=None, help="Path to save trained weights to. If no path is specified checkpoints are not saved.")
parser.add_argument("-sM", "--save_model_path", metavar="SAVE_MODEL_PATH", default=None, help="Path to save trained model to.")
parser.add_argument("-l", "--load_path", metavar="LOAD_PATH", default=None, help="Path to load trained model from. If no path is specified model is trained from scratch.")
parser.add_argument("-m", "--metrics-path", metavar="METRICS_PATH", default=None, help="Path to save additional performance metrics to (for debugging purposes).")
parser.add_argument("-b", "--read_batches", metavar="READ_BATCHES", default=False, help="If true, data is read incrementally in batches during training.")
parser.add_argument("--PCA", metavar="PCA", default=False, help="If true, a PCA plot is saved.")
parser.add_argument("--TSNE", metavar="TSNE", default=False, help="If true, a TSNE plot is saved.")
parser.add_argument("--output_loss_threshold", metavar="OUTPUT_LOSS_THRESHOLD", default=None, help="Value between 0.0-1.0. Main function will return loss value of triplet at set percentage.")
args = parser.parse_args()
parse_args(args)
X_shape, y_shape = utils.get_shapes(args.data_path, "train_anchors")
# Build model
input_shape = X_shape[1:]
tower_model = build_tower_cnn_model(input_shape) # single input model
triplet_model = build_triplet_model(input_shape, tower_model) # siamese model
if args.load_path is not None:
triplet_model.load_weights(args.load_path)
# Setup callbacks for early stopping and model saving
callback_list = setup_callbacks(args.save_weights_path)
# Compile model
adam = Adam(lr=LEARNING_RATE)
triplet_model.compile(optimizer=adam, loss='mean_squared_error')
if not args.read_batches: # Read all data at once
# Load training triplets and validation triplets
X_train_anchors, y_train_anchors = utils.load_examples(args.data_path, "train_anchors")
X_train_positives, _ = utils.load_examples(args.data_path, "train_positives")
X_train_negatives, _ = utils.load_examples(args.data_path, "train_negatives")
X_valid_anchors, y_valid_anchors = utils.load_examples(args.data_path, "valid_anchors")
X_valid_positives, _ = utils.load_examples(args.data_path, "valid_positives")
X_valid_negatives, _ = utils.load_examples(args.data_path, "valid_negatives")
# Create dummy y = 0 (since output of siamese model is triplet loss)
y_train_dummy = np.zeros((X_shape[0],))
y_valid_dummy = np.zeros((X_valid_anchors.shape[0],))
# Train the model
triplet_model.fit([X_train_anchors, X_train_positives, X_train_negatives],
y_train_dummy, validation_data=([X_valid_anchors, X_valid_positives, X_valid_negatives], y_valid_dummy),
epochs=EPOCHS, batch_size=BATCH_SIZE, callbacks=callback_list)
global training_complete
training_complete = True
else: # Read data in batches
training_batch_generator = utils.DataGenerator(args.data_path, "train", batch_size=1000)
validation_batch_generator = utils.DataGenerator(args.data_path, "valid", batch_size=1000)
triplet_model.fit_generator(generator=training_batch_generator, validation_data=validation_batch_generator,
callbacks=callback_list, epochs=EPOCHS)
# Save weights
if args.save_weights_path is not None:
triplet_model.save_weights(args.save_weights_path + "final_weights.hdf5")
# Save model
if args.save_model_path is not None:
tower_model.save(args.save_model_path + "tower_model.hdf5")
triplet_model.save(args.save_model_path + "triplet_model.hdf5")
# Plot PCA/TSNE
# For now, read all the valid anchors to do PCA
# TODO: add function in util that reads a specified number of random samples from a dataset.
if args.PCA is not False or args.TSNE is not False:
X_valid_anchors, y_valid_anchors = utils.load_examples(args.data_path, "valid_anchors")
X, Y = utils.shuffle_data(X_valid_anchors[:, :, :], y_valid_anchors[:, :], one_hot_labels=True)
X = X[:5000, :, :]
Y = Y[:5000, :]
X = tower_model.predict(X)
if args.PCA:
utils.plot_with_PCA(X, Y)
if args.TSNE:
utils.plot_with_TSNE(X, Y)
# Calculate loss value of triplet at a certain threshold
if args.output_loss_threshold is not None:
if not args.read_batches: # Read all data at once
# Load training triplets and validation triplets
X_train_anchors, _ = utils.load_examples(args.data_path, "train_anchors")
X_train_positives, _ = utils.load_examples(args.data_path, "train_positives")
X_train_negatives, _ = utils.load_examples(args.data_path, "train_negatives")
# Get abs(distance) of embeddings
X_train = triplet_model.predict([X_train_anchors, X_train_positives, X_train_negatives])
else: # Read data in batches
training_batch_generator = utils.DataGenerator(args.data_path, "train", batch_size=100, stop_after_batch=10)
# Get abs(distance) of embeddings (one batch at a time)
X_train = triplet_model.predict_generator(generator=training_batch_generator, verbose=1)
X_train = np.sort(X_train, axis=None)
print(X_train[int(float(args.output_loss_threshold) * X_train.shape[0])])
Les résultats sont écrits en CSV dans la sortie standard.
"""
from contextlib import contextmanager
import csv
import time
import sys
from aima.search import Node, depth_first_graph_search, hill_climbing, greedy_best_first_graph_search
from sudoku import Sudoku, FilledSudoku, NormalizedSudoku, RandomizedSudoku, SortedSudoku
from heuristics import most_constrained_cell
from utils import load_examples, compact
examples = load_examples(sys.argv[1])
results = csv.DictWriter(sys.stdout, fieldnames=('initial', 'algorithm', 'heuristic', 'bound', 'final', 'score','explored', 'time'))
results.writeheader()
def bench(algorithm, problem, *argv, **kwargs):
"""Benchmark an algorithm and write the results in the standard output."""
# benchmark algorithm runtime
a = time.clock()
solution, explored = algorithm(problem, *argv, **kwargs)
delta = time.clock() - a
if isinstance(solution, Node):
solution = solution.state
# write results
import sys
from aima.search import depth_first_graph_search
from sudoku import Sudoku, RandomizedSudoku, SortedSudoku
from utils import load_examples
for example in load_examples(sys.argv[1]):
s = Sudoku(example)
r = RandomizedSudoku(example)
sorted_sudoku = SortedSudoku(example)
print depth_first_graph_search(s, bound=10000)
print depth_first_graph_search(r, bound=10000)
print depth_first_graph_search(sorted_sudoku, bound=10000)
def main():
if tf.__version__ != "1.0.0":
raise Exception("Tensorflow version 1.0.0 required")
if a.seed is None:
a.seed = random.randint(0, 2**31 - 1)
tf.set_random_seed(a.seed)
np.random.seed(a.seed)
random.seed(a.seed)
if not os.path.exists(a.output_dir):
os.makedirs(a.output_dir)
if a.mode == "test" or a.mode == "export":
if a.checkpoint is None:
raise Exception("checkpoint required for test mode")
# load some options from the checkpoint
options = {"which_direction", "ngf", "ndf", "lab_colorization"}
with open(os.path.join(a.checkpoint, "options.json")) as f:
for key, val in json.loads(f.read()).items():
if key in options:
print("loaded", key, "=", val)
setattr(a, key, val)
# disable these features in test mode
a.scale_size = CROP_SIZE
a.flip = False
for k, v in a._get_kwargs():
print(k, "=", v)
with open(os.path.join(a.output_dir, "options.json"), "w") as f:
f.write(json.dumps(vars(a), sort_keys=True, indent=4))
if a.mode == "export":
# export the generator to a meta graph that can be imported later for standalone generation
if a.lab_colorization:
raise Exception("export not supported for lab_colorization")
input = tf.placeholder(tf.string, shape=[1])
input_data = tf.decode_base64(input[0])
input_image = tf.image.decode_png(input_data)
# remove alpha channel if present
input_image = input_image[:, :, :3]
input_image = tf.image.convert_image_dtype(input_image,
dtype=tf.float32)
input_image.set_shape([CROP_SIZE, CROP_SIZE, 3])
batch_input = tf.expand_dims(input_image, axis=0)
with tf.variable_scope("generator") as scope:
batch_output = deprocess(
create_generator_Unet(a, preprocess(batch_input), 3))
output_image = tf.image.convert_image_dtype(batch_output,
dtype=tf.uint8)[0]
output_data = tf.image.encode_png(output_image)
output = tf.convert_to_tensor([tf.encode_base64(output_data)])
key = tf.placeholder(tf.string, shape=[1])
inputs = {"key": key.name, "input": input.name}
tf.add_to_collection("inputs", json.dumps(inputs))
outputs = {
"key": tf.identity(key).name,
"output": output.name,
}
tf.add_to_collection("outputs", json.dumps(outputs))
init_op = tf.global_variables_initializer()
restore_saver = tf.train.Saver()
export_saver = tf.train.Saver()
# config = tf.ConfigProto()
# config.allow_soft_placement = False
# config.log_device_placement = True
# config.gpu_options.allow_growth = True
# config.gpu_options.per_process_gpu_memory_fraction = 0.4
with tf.Session() as sess:
sess.run(init_op)
print("loading model from checkpoint")
checkpoint = tf.train.latest_checkpoint(a.checkpoint)
restore_saver.restore(sess, checkpoint)
print("exporting model")
export_saver.export_meta_graph(
filename=os.path.join(a.output_dir, "export.meta"))
export_saver.save(sess,
os.path.join(a.output_dir, "export"),
write_meta_graph=False)
return
examples = load_examples(a)
print("examples count = %d" % examples.count)
# inputs and targets are [batch_size, height, width, channels]
model = create_model(examples.inputs, examples.targets)
# undo colorization splitting on images that we use for display/output
if a.lab_colorization:
if a.which_direction == "AtoB":
# inputs is brightness, this will be handled fine as a grayscale image
# need to augment targets and outputs with brightness
targets = augment(examples.targets, examples.inputs)
outputs = augment(model.outputs, examples.inputs)
# inputs can be deprocessed normally and handled as if they are single channel
# grayscale images
inputs = deprocess(examples.inputs)
elif a.which_direction == "BtoA":
# inputs will be color channels only, get brightness from targets
inputs = augment(examples.inputs, examples.targets)
targets = deprocess(examples.targets)
outputs = deprocess(model.outputs)
else:
raise Exception("invalid direction")
else:
inputs = deprocess(examples.inputs)
targets = deprocess(examples.targets)
outputs = deprocess(model.outputs)
def convert(image):
if a.aspect_ratio != 1.0:
# upscale to correct aspect ratio
size = [CROP_SIZE, int(round(CROP_SIZE * a.aspect_ratio))]
image = tf.image.resize_images(
image, size=size, method=tf.image.ResizeMethod.BICUBIC)
return tf.image.convert_image_dtype(image,
dtype=tf.uint8,
saturate=True)
# reverse any processing on images so they can be written to disk or displayed to user
with tf.name_scope("convert_inputs"):
converted_inputs = convert(inputs)
with tf.name_scope("convert_targets"):
converted_targets = convert(targets)
with tf.name_scope("convert_outputs"):
converted_outputs = convert(outputs)
with tf.name_scope("encode_images"):
display_fetches = {
"paths":
examples.paths,
"inputs":
tf.map_fn(tf.image.encode_png,
converted_inputs,
dtype=tf.string,
name="input_pngs"),
"targets":
tf.map_fn(tf.image.encode_png,
converted_targets,
dtype=tf.string,
name="target_pngs"),
"outputs":
tf.map_fn(tf.image.encode_png,
converted_outputs,
dtype=tf.string,
name="output_pngs"),
}
# summaries
with tf.name_scope("inputs_summary"):
tf.summary.image("inputs", converted_inputs)
with tf.name_scope("targets_summary"):
tf.summary.image("targets", converted_targets)
with tf.name_scope("outputs_summary"):
tf.summary.image("outputs", converted_outputs)
with tf.name_scope("predict_real_summary"):
tf.summary.image(
"predict_real",
tf.image.convert_image_dtype(model.predict_real, dtype=tf.uint8))
with tf.name_scope("predict_fake_summary"):
tf.summary.image(
"predict_fake",
tf.image.convert_image_dtype(model.predict_fake, dtype=tf.uint8))
tf.summary.scalar("discriminator_loss", model.discrim_loss)
tf.summary.scalar("gennerator_loss", model.gen_loss)
tf.summary.scalar("generator_loss_GAN", model.gen_loss_GAN)
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name + "/values", var)
for grad, var in model.discrim_grads_and_vars + model.gen_grads_and_vars:
tf.summary.histogram(var.op.name + "/gradients", grad)
with tf.name_scope("parameter_count"):
parameter_count = tf.reduce_sum(
[tf.reduce_prod(tf.shape(v)) for v in tf.trainable_variables()])
saver = tf.train.Saver(max_to_keep=1)
logdir = a.output_dir if (a.trace_freq > 0 or a.summary_freq > 0) else None
sv = tf.train.Supervisor(logdir=logdir, save_summaries_secs=0, saver=None)
with sv.managed_session() as sess:
print("parameter_count =", sess.run(parameter_count))
if a.checkpoint is not None:
print("loading model from checkpoint")
checkpoint = tf.train.latest_checkpoint(a.checkpoint)
saver.restore(sess, checkpoint)
max_steps = 2**32
if a.max_epochs is not None:
max_steps = examples.steps_per_epoch * a.max_epochs
if a.max_steps is not None:
max_steps = a.max_steps
if a.mode == "test":
# testing
# at most, process the test data once
test_start = time.time()
max_steps = min(examples.steps_per_epoch, max_steps)
for step in range(max_steps):
results = sess.run(display_fetches)
filesets = save_images(a, results)
for i, f in enumerate(filesets):
print("evaluated image", f["name"])
index_path = append_index(a, filesets)
with open(a.output_dir + '/test.time', 'w') as f:
f.write(str(time.time() - test_start) + '\n')
print("wrote index at", index_path)
else:
# training
start = time.time()
with open(a.output_dir + '/train.precession', 'a') as f:
f.write('step RFE ACC \n')
for step in range(max_steps):
def should(freq):
return freq > 0 and ((step + 1) % freq == 0
or step == max_steps - 1)
options = None
run_metadata = None
if should(a.trace_freq):
options = tf.RunOptions(
trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
fetches = {
"train": model.train,
"global_step": sv.global_step,
}
if should(a.progress_freq):
fetches["discrim_loss"] = model.discrim_loss
fetches["gen_loss"] = model.gen_loss
fetches["gen_loss_GAN"] = model.gen_loss_GAN
if should(a.summary_freq):
fetches["summary"] = sv.summary_op
if should(a.display_freq):
fetches["display"] = display_fetches
results = sess.run(fetches,
options=options,
run_metadata=run_metadata)
if should(a.summary_freq):
print("recording summary")
sv.summary_writer.add_summary(results["summary"],
results["global_step"])
if should(a.display_freq):
print("saving display images")
filesets = save_images(a,
results["display"],
step=results["global_step"])
append_index(a, filesets, step=True)
if should(a.trace_freq):
print("recording trace")
sv.summary_writer.add_run_metadata(
run_metadata, "step_%d" % results["global_step"])
if should(a.progress_freq):
# global_step will have the correct step count if we resume from a checkpoint
train_epoch = math.ceil(results["global_step"] /
examples.steps_per_epoch)
train_step = (results["global_step"] -
1) % examples.steps_per_epoch + 1
rate = (step + 1) * a.batch_size / (time.time() - start)
remaining = (max_steps - step) * a.batch_size / rate
print(
"progress epoch %d step %d image/sec %0.1f remaining %dm"
% (train_epoch, train_step, rate, remaining / 60))
print("discrim_loss", results["discrim_loss"])
print("gen_loss", results["gen_loss"])
print("gen_loss_GAN", results["gen_loss_GAN"])
#with open(a.output_dir + '/train.log', 'a') as f:
# f.write('step gen_loss discrim_loss')
if should(a.save_freq):
print("saving model")
saver.save(sess,
os.path.join(a.output_dir, "model"),
global_step=sv.global_step)
line_str = '%s %s %s\n' % (results["global_step"],
results["gen_loss"],
results["discrim_loss"])
with open(a.output_dir + '/train.log', 'a') as f:
f.write(line_str)
if should(a.test_freq):
if a.output_dir is None:
raise Exception("checkpoint required for test mode")
# load some options from the checkpoint
options = {
"which_direction", "ngf", "ndf", "lab_colorization"
}
with open(os.path.join(a.output_dir, "options.json")) as f:
for key, val in json.loads(f.read()).items():
if key in options:
print("loaded", key, "=", val)
setattr(a, key, val)
# disable these features in test mode
a.scale_size = CROP_SIZE
a.flip = False
# testing
# at most, process the test data once
max_steps = min(examples.steps_per_epoch, max_steps)
for step in range(max_steps):
test_results = sess.run(display_fetches)
test_filesets = save_images(
a, test_results, step=results["global_step"])
index_path = append_index(a, test_filesets)
if 'ThreeObj_gamma_1.0' in test_filesets[0]['outputs']:
#pdb.set_trace()
print(
'file',
'checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s'
%
(a.lr, a.f_type, test_filesets[0]['outputs']))
outp = cv2.imread(
'checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s'
%
(a.lr, a.f_type, test_filesets[0]['outputs']))
targ = cv2.imread(
'checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s'
%
(a.lr, a.f_type, test_filesets[0]['targets']))
inp = cv2.imread(
'checkpoints.lr.%s/simulation_test/ossgan_sgan_l1/%s/images/%s'
% (a.lr, a.f_type, test_filesets[0]['inputs']))
rfe = region_fitting_error(outp, targ)
acc = calculate_accuracy(inp, outp, targ)
#print('region fitting error', rfe)
#print('accuracy', acc)
line_str = '%s %s %s\n' % (results["global_step"],
rfe, acc)
with open(a.output_dir + '/train.precession',
'a') as f:
f.write(line_str)
print("wrote index at", index_path)
if sv.should_stop():
break
with open(a.output_dir + '/train.time', 'w') as f:
f.write(str(time.time() - start) + '\n')
def main():
# Parse arguments
parser = argparse.ArgumentParser()
parser.add_argument(dest="data_path",
metavar="DATA_PATH",
help="Path to read examples from.")
parser.add_argument(
"-sW",
"--save_weights_path",
metavar="SAVE_WEIGHTS_PATH",
default=None,
help=
"Path to save trained weights to. If no path is specified checkpoints are not saved."
)
parser.add_argument("-sM",
"--save_model_path",
metavar="SAVE_MODEL_PATH",
default=None,
help="Path to save trained model to.")
parser.add_argument(
"-l",
"--load_path",
metavar="LOAD_PATH",
default=None,
help=
"Path to load trained model from. If no path is specified model is trained from scratch."
)
parser.add_argument("--PCA",
metavar="PCA",
default=False,
help="If true, a PCA plot is saved.")
parser.add_argument("--TSNE",
metavar="TSNE",
default=False,
help="If true, a TSNE plot is saved.")
args = parser.parse_args()
parse_args(args)
X_shape, y_shape = utils.get_shapes(args.data_path, "train")
# Build model
input_shape = X_shape[1:]
tower_model = build_tower_cnn_model(input_shape) # single input model
triplet_model = build_triplet_model(input_shape,
tower_model) # siamese model
if args.load_path is not None:
triplet_model.load_weights(args.load_path)
# Setup callbacks for early stopping and model saving
callback_list = setup_callbacks(args.save_weights_path)
# Compile model
adam = Adam(lr=LEARNING_RATE)
triplet_model.compile(optimizer=adam, loss=custom_loss)
tower_model.predict(np.zeros(
(1, ) +
input_shape)) # predict on some random data to activate predict()
# Initializate online triplet generators
training_batch_generator = OnlineTripletGenerator(args.data_path,
"train",
tower_model,
batch_size=BATCH_SIZE,
triplet_mode="batch_all")
validation_batch_generator = utils.DataGenerator(args.data_path,
"valid",
batch_size=BATCH_SIZE)
triplet_model.fit_generator(generator=training_batch_generator,
validation_data=validation_batch_generator,
callbacks=callback_list,
epochs=EPOCHS)
# Save weights
if args.save_weights_path is not None:
triplet_model.save_weights(args.save_weights_path +
"final_weights.hdf5")
# Save model
if args.save_model_path is not None:
tower_model.save(args.save_model_path + "tower_model.hdf5")
# Plot PCA/TSNE
# TODO: add function in util that reads a specified number of random samples from a dataset.
if args.PCA is not False or args.TSNE is not False:
X_valid, y_valid = utils.load_examples(args.data_path, "train")
X, Y = utils.shuffle_data(X_valid[:, :, :],
y_valid[:, :],
one_hot_labels=True)
X = X[:5000, :, :]
Y = Y[:5000, :]
X = tower_model.predict(X)
if args.PCA:
utils.plot_with_PCA(X, Y)
if args.TSNE:
utils.plot_with_TSNE(X, Y)
def main():
# Parse arguments
parser = argparse.ArgumentParser()
parser.add_argument(dest="triplets_path",
metavar="TRIPLETS_PATH",
help="Path to read triplets from.")
parser.add_argument(dest="model_path",
metavar="MODEL_PATH",
help="Path to read model from.")
parser.add_argument(
"-e",
"--ensemble",
metavar="ENSEMBLE",
default=1,
help="How many examples to ensemble when predicting. Default: 1")
parser.add_argument(
"-b",
"--read_batches",
metavar="READ_BATCHES",
default=False,
help="If true, data is read incrementally in batches during training.")
args = parser.parse_args()
parse_args(args)
# Load model
with CustomObjectScope({
'_euclidean_distance': cnn_siamese_online._euclidean_distance,
'ALPHA': cnn_siamese_online.ALPHA,
"relu_clipped": cnn_siamese_online.relu_clipped
}):
tower_model = load_model(args.model_path)
tower_model.compile(
optimizer='adam',
loss='mean_squared_error') # Model was previously not compiled
X_shape, y_shape = utils.get_shapes(args.triplets_path, "train_anchors")
# Build model to compute [A, P, N] => [abs(emb(A) - emb(P)), abs(emb(A) - emb(N))]
pair_distance_model = build_pair_distance_model(tower_model, X_shape[1:])
pair_distance_model.compile(
optimizer="adam",
loss="mean_squared_error") # Need to compile in order to predict
if not args.read_batches: # Read all data at once
# Load training triplets
X_train_anchors, _ = utils.load_examples(args.triplets_path,
"train_anchors")
X_train_positives, _ = utils.load_examples(args.triplets_path,
"train_positives")
X_train_negatives, _ = utils.load_examples(args.triplets_path,
"train_negatives")
# Get abs(distance) of embeddings
X_train_1, X_train_0 = pair_distance_model.predict(
[X_train_anchors, X_train_positives, X_train_negatives])
# Stack positive and negative examples
X_train = np.vstack((X_train_1, X_train_0))
y_train = np.hstack(
(np.ones(X_train_1.shape[0], ), np.zeros(X_train_0.shape[0], )))
# Shuffle the data
X_train, y_train = shuffle(X_train, y_train)
# Train SVM
clf = svm.SVC(gamma='scale', verbose=True)
clf.fit(X_train[:10000, :], y_train[:10000])
# Evaluate SVM
y_pred = clf.predict(X_train)
if args.ensemble > 1:
accuracy, FAR, FRR = ensemble_accuracy_FAR_FRR(y_train, y_pred,
args.ensemble)
print("\n\n---- Validation Results. With ensembling = {}. ----".format(
args.ensemble))
else:
accuracy, FAR, FRR = accuracy_FAR_FRR(y_train, y_pred)
print("\n\n---- Validation Results. No ensembling. ----")
print("Accuracy = {}".format(accuracy))
print("FAR = {}".format(FAR))
print("FRR = {}".format(FRR))