def main():
batch_size = 16
epochs = 50
save_dir = os.path.join(os.getcwd(), 'saved_models')
if not os.path.isdir(save_dir):
os.makedirs(save_dir)
filepath = "saved_models/94482_23620_keras_cw_noDropOut_chexpert_pretrained_chexnet_1_{epoch:03d}_{val_loss:.5f}.h5"
checkpoint = ModelCheckpoint(filepath,
monitor='val_loss',
verbose=1,
save_best_only=False,
mode='min')
callbacks_list = [checkpoint]
#new_model_name = '94482_23620_keras_chexpert_pretrained_chexnet_512_6_epochs_1.h5'
base_model, model = get_model()
# load old weights
#old_model_name = 'keras_chexpert_pretrained_chexnet_512_6_epochs_10.h5'
#model_path = os.path.join(save_dir, old_model_name)
# model.load_weights(model_path)
# print a model summary
# print_summary(model)
csv_file_path = 'chexpert/train_94482_frontal_6_classes_real_no_zeros_preprocessed.csv'
#train_df = pd.read_csv(csv_file_path)
class_weight = get_class_weight(csv_file_path, target_classes)
train_generator = AugmentedImageSequence(dataset_csv_file=csv_file_path,
class_names=target_classes,
source_image_dir='./chexpert/',
batch_size=batch_size)
csv_file_path = 'chexpert/train_23620_frontal_6_classes_real_no_zeros_preprocessed.csv'
#valid_df = pd.read_csv(csv_file_path)
valid_generator = AugmentedImageSequence(dataset_csv_file=csv_file_path,
class_names=target_classes,
source_image_dir='./chexpert/',
batch_size=batch_size)
STEP_SIZE_TRAIN = train_generator.steps
STEP_SIZE_VALID = valid_generator.steps
model.fit_generator(generator=train_generator,
steps_per_epoch=STEP_SIZE_TRAIN,
validation_data=valid_generator,
validation_steps=STEP_SIZE_VALID,
epochs=epochs,
callbacks=callbacks_list,
class_weight=class_weight,
use_multiprocessing=True)
def get_generator(csv_path,FLAGS, data_augmenter=None):
return AugmentedImageSequence(
dataset_csv_file=csv_path,
label_columns=FLAGS.csv_label_columns,
class_names=FLAGS.classes,
multi_label_classification=FLAGS.multi_label_classification,
source_image_dir=FLAGS.image_directory,
batch_size=FLAGS.batch_size,
target_size=FLAGS.image_target_size,
augmenter=data_augmenter,
shuffle_on_epoch_end=False,
)
def get_enqueuer(csv,batch_size, FLAGS, tokenizer_wrapper, augmenter=None):
data_generator = AugmentedImageSequence(
dataset_csv_file=csv,
class_names=FLAGS.csv_label_columns,
tokenizer_wrapper=tokenizer_wrapper,
source_image_dir=FLAGS.image_directory,
batch_size=batch_size,
target_size=FLAGS.image_target_size,
augmenter=augmenter,
shuffle_on_epoch_end=True,
)
enqueuer = OrderedEnqueuer(data_generator,
use_multiprocessing=False,
shuffle=False)
return enqueuer, data_generator.steps
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
output_dir = cp["DEFAULT"].get("output_dir")
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
# train config
image_dimension = cp["TRAIN"].getint("image_dimension")
# test config
batch_size = cp["TEST"].getint("batch_size")
test_steps = cp["TEST"].get("test_steps")
use_best_weights = cp["TEST"].getboolean("use_best_weights")
# parse weights file path
output_weights_name = cp["TRAIN"].get("output_weights_name")
weights_path = os.path.join(output_dir, output_weights_name)
best_weights_path = os.path.join(output_dir, f"best_{output_weights_name}")
# get test sample count
test_counts, _ = get_sample_counts(output_dir, "test", class_names)
# compute steps
if test_steps == "auto":
test_steps = int(test_counts / batch_size)
else:
try:
test_steps = int(test_steps)
except ValueError:
raise ValueError(f"""
test_steps: {test_steps} is invalid,
please use 'auto' or integer.
""")
print(f"** test_steps: {test_steps} **")
print("** load model **")
if use_best_weights:
print("** use best weights **")
model_weights_path = best_weights_path
else:
print("** use last weights **")
model_weights_path = weights_path
model_factory = ModelFactory()
model = model_factory.get_model(class_names,
model_name=base_model_name,
use_base_weights=False,
weights_path=model_weights_path)
print("** load test generator **")
test_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(output_dir, "test.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=None,
steps=test_steps,
shuffle_on_epoch_end=False,
)
print("** make prediction **")
logs = []
starttime = time()
y_hat = model.predict_generator(test_sequence, verbose=1)
logs.append(time() - starttime)
print("time: " + str(logs))
y = test_sequence.get_y_true()
test_log_path = os.path.join(output_dir, "test.log")
print(f"** write log to {test_log_path} **")
aurocs = []
with open(test_log_path, "w") as f:
for i in range(len(class_names)):
try:
score = roc_auc_score(y[:, i], y_hat[:, i])
aurocs.append(score)
except ValueError:
score = 0
f.write(f"{class_names[i]}: {score}\n")
mean_auroc = np.mean(aurocs)
f.write("-------------------------\n")
f.write(f"mean auroc: {mean_auroc}\n")
print(f"mean auroc: {mean_auroc}")
# compute steps
steps = int(training_counts / batch_size)
print(f"** train_steps: {steps} **")
print("** load training generator **")
tokenizer_wrapper = TokenizerWrapper(os.path.join(data_dir, all_data_csv),
class_names[0], max_sequence_length,
tokenizer_vocab_size)
data_generator = AugmentedImageSequence(
dataset_csv_file=os.path.join(data_dir, training_csv),
class_names=class_names,
tokenizer_wrapper=tokenizer_wrapper,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=augmenter,
steps=steps,
shuffle_on_epoch_end=True,
)
medical_w2v = Medical_W2V_Wrapper()
embeddings = medical_w2v.get_embeddings_matrix_for_words(
tokenizer_wrapper.get_word_tokens_list(), tokenizer_vocab_size)
print(embeddings.shape)
del medical_w2v
encoder = CNN_Encoder(embedding_dim)
decoder = RNN_Decoder(embedding_dim, units, tokenizer_vocab_size, embeddings)
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
output_dir = cp["DEFAULT"].get("output_dir")
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
image_dimension = cp["TRAIN"].getint("image_dimension")
# parse weights file path
output_weights_name = cp["TRAIN"].get("output_weights_name")
weights_path = os.path.join(output_dir, output_weights_name)
best_weights_path = os.path.join(output_dir, f"best_{output_weights_name}")
# CAM config
bbox_list_file = cp["CAM"].get("bbox_list_file")
use_best_weights = cp["CAM"].getboolean("use_best_weights")
print("** load model **")
if use_best_weights:
print("** use best weights **")
model_weights_path = best_weights_path
else:
print("** use last weights **")
model_weights_path = weights_path
model_factory = ModelFactory()
model = model_factory.get_model(class_names,
model_name=base_model_name,
use_base_weights=False,
weights_path=model_weights_path)
print("read bbox list file")
df_images = pd.read_csv(bbox_list_file, header=None, skiprows=1)
df_images.columns = ["file_name", "label", "x", "y", "w", "h"]
print("create a generator for loading transformed images")
cam_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(output_dir, "test.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=1,
target_size=(image_dimension, image_dimension),
augmenter=None,
steps=1,
shuffle_on_epoch_end=False,
)
image_output_dir = os.path.join(output_dir, "cam")
if not os.path.isdir(image_output_dir):
os.makedirs(image_output_dir)
print("create CAM")
df_images.apply(
lambda g: create_cam(
df_g=g,
output_dir=image_output_dir,
image_source_dir=image_source_dir,
model=model,
generator=cam_sequence,
class_names=class_names,
),
axis=1,
)
def train(self, log_dir, show_model=True):
""" Training classification model
"""
###################################################################################
augs = augmentation()
optimizer = Adam(lr=config.LEARNING_RATE,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=0.0)
early_stop = EarlyStopping(monitor="val_loss",
min_delta=0,
patience=20,
verbose=1)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.8,
patience=10,
verbose=1,
mode='auto',
epsilon=0.0001,
cooldown=5,
min_lr=0.0001)
###################################################################################
TRAIN_CSV_FP, tmp_train = tool.prepare_dataset(config.TRAIN)
VAL_CSV_FP, tmp_val = tool.prepare_dataset(config.VAL)
SAVE_WEIGHT_FP = os.path.join(log_dir, "{epoch:03d}-{val_loss:.4f}.h5")
AUC_LOG_FP = os.path.join(log_dir, "auc.txt")
# Make log directory if not exist
if not os.path.isdir(log_dir):
os.makedirs(log_dir)
# Training dataset
train_sequence = AugmentedImageSequence(
csv_fp=TRAIN_CSV_FP,
class_names=config.CLASS_NAMES,
batch_size=config.BATCH_SIZE,
target_size=(config.NET_INPUT_DIM, config.NET_INPUT_DIM),
steps=config.TRAIN_STEPS,
augmenter=augs,
)
# Validation dataset
validation_sequence = AugmentedImageSequence(
csv_fp=VAL_CSV_FP,
class_names=config.CLASS_NAMES,
batch_size=config.BATCH_SIZE,
target_size=(config.NET_INPUT_DIM, config.NET_INPUT_DIM),
steps=config.VAL_STEPS,
shuffle_on_epoch_end=False,
)
# Load classification model
model = ModelFactory().get_classification_model(
class_num=len(config.CLASS_NAMES),
model_name=config.MODEL_NAME,
base_weights="imagenet",
input_shape=(config.NET_INPUT_DIM, config.NET_INPUT_DIM, 3))
if show_model: print(model.summary())
model.compile(optimizer=optimizer,
loss=config.LOSS,
metrics=config.METRICS)
# Callbacks
checkpoint = ModelCheckpoint(SAVE_WEIGHT_FP,
save_weights_only=False,
save_best_only=False,
verbose=0)
tensorboard = TensorBoard(log_dir=os.path.join(log_dir, "logs"))
csv_logger = CSVLogger(os.path.join(log_dir, "my_logger.csv"))
auroc = MultipleClassAUROC(AUC_LOG_FP, validation_sequence,
config.CLASS_NAMES,
config.GENERATOR_WORKERS)
callbacks = [
checkpoint, tensorboard, csv_logger, early_stop, reduce_lr, auroc
]
history = model.fit_generator(generator=train_sequence,
steps_per_epoch=config.TRAIN_STEPS,
epochs=config.EPOCH,
verbose=2,
validation_data=validation_sequence,
callbacks=callbacks,
workers=config.GENERATOR_WORKERS,
shuffle=False)
print("\nFinished training")
if tmp_train: os.remove(TRAIN_CSV_FP)
if tmp_val: os.remove(VAL_CSV_FP)
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
output_dir = cp["DEFAULT"].get("output_dir")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
# train config
use_base_model_weights = cp["TRAIN"].getboolean("use_base_model_weights")
use_trained_model_weights = cp["TRAIN"].getboolean(
"use_trained_model_weights")
use_best_weights = cp["TRAIN"].getboolean("use_best_weights")
output_weights_name = cp["TRAIN"].get("output_weights_name")
epochs = cp["TRAIN"].getint("epochs")
batch_size = cp["TRAIN"].getint("batch_size")
initial_learning_rate = cp["TRAIN"].getfloat("initial_learning_rate")
generator_workers = cp["TRAIN"].getint("generator_workers")
image_dimension = cp["TRAIN"].getint("image_dimension")
train_steps = cp["TRAIN"].get("train_steps")
patience_reduce_lr = cp["TRAIN"].getint("patience_reduce_lr")
min_lr = cp["TRAIN"].getfloat("min_lr")
validation_steps = cp["TRAIN"].get("validation_steps")
positive_weights_multiply = cp["TRAIN"].getfloat(
"positive_weights_multiply")
dataset_csv_dir = cp["TRAIN"].get("dataset_csv_dir")
# if previously trained weights is used, never re-split
if use_trained_model_weights:
# resuming mode
print("** use trained model weights **")
# load training status for resuming
training_stats_file = os.path.join(output_dir, ".training_stats.json")
if os.path.isfile(training_stats_file):
# TODO: add loading previous learning rate?
training_stats = json.load(open(training_stats_file))
else:
training_stats = {}
else:
# start over
training_stats = {}
show_model_summary = cp["TRAIN"].getboolean("show_model_summary")
# end parser config
# check output_dir, create it if not exists
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
running_flag_file = os.path.join(output_dir, ".training.lock")
if os.path.isfile(running_flag_file):
raise RuntimeError("A process is running in this directory!!!")
else:
open(running_flag_file, "a").close()
try:
print(f"backup config file to {output_dir}")
shutil.copy(config_file,
os.path.join(output_dir,
os.path.split(config_file)[1]))
datasets = ["train", "dev", "test"]
for dataset in datasets:
shutil.copy(os.path.join(dataset_csv_dir, f"{dataset}.csv"),
output_dir)
# get train/dev sample counts
train_counts, train_pos_counts = get_sample_counts(
output_dir, "train", class_names)
dev_counts, _ = get_sample_counts(output_dir, "dev", class_names)
# compute steps
if train_steps == "auto":
train_steps = int(train_counts / batch_size)
else:
try:
train_steps = int(train_steps)
except ValueError:
raise ValueError(f"""
train_steps: {train_steps} is invalid,
please use 'auto' or integer.
""")
print(f"** train_steps: {train_steps} **")
if validation_steps == "auto":
validation_steps = int(dev_counts / batch_size)
else:
try:
validation_steps = int(validation_steps)
except ValueError:
raise ValueError(f"""
validation_steps: {validation_steps} is invalid,
please use 'auto' or integer.
""")
print(f"** validation_steps: {validation_steps} **")
# compute class weights
print("** compute class weights from training data **")
class_weights = get_class_weights(
train_counts,
train_pos_counts,
multiply=positive_weights_multiply,
)
print("** class_weights **")
print(class_weights)
print("** load model **")
if use_trained_model_weights:
if use_best_weights:
model_weights_file = os.path.join(
output_dir, f"best_{output_weights_name}")
else:
model_weights_file = os.path.join(output_dir,
output_weights_name)
else:
model_weights_file = None
model_factory = ModelFactory()
model = model_factory.get_model(
class_names,
model_name=base_model_name,
use_base_weights=use_base_model_weights,
weights_path=model_weights_file,
input_shape=(image_dimension, image_dimension, 3))
if show_model_summary:
print(model.summary())
print("** create image generators **")
train_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(output_dir, "train.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=augmenter,
steps=train_steps,
)
validation_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(output_dir, "dev.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=augmenter,
steps=validation_steps,
shuffle_on_epoch_end=False,
)
output_weights_path = os.path.join(output_dir, output_weights_name)
print(f"** set output weights path to: {output_weights_path} **")
print("** check multiple gpu availability **")
gpus = len(os.getenv("CUDA_VISIBLE_DEVICES", "1").split(","))
if gpus > 1:
print(f"** multi_gpu_model is used! gpus={gpus} **")
model_train = multi_gpu_model(model, gpus)
# FIXME: currently (Keras 2.1.2) checkpoint doesn't work with multi_gpu_model
checkpoint = MultiGPUModelCheckpoint(
filepath=output_weights_path,
base_model=model,
)
else:
model_train = model
checkpoint = ModelCheckpoint(
output_weights_path,
save_weights_only=True,
save_best_only=True,
verbose=1,
)
print("** compile model with class weights **")
#model.compile(RAdam(), loss='mse')
#optimizer = Adam(lr=initial_learning_rate)
optimizer = RAdam(lr=initial_learning_rate)
model_train.compile(optimizer=optimizer, loss=[focal_loss])
lookahead = Lookahead(k=5, alpha=0.5) # Initialize Lookahead
lookahead.inject(model_train) # add into model
auroc = MultipleClassAUROC(
sequence=validation_sequence,
class_names=class_names,
weights_path=output_weights_path,
stats=training_stats,
workers=generator_workers,
)
callbacks = [
checkpoint,
TensorBoard(log_dir=os.path.join(output_dir, "logs"),
batch_size=batch_size),
ReduceLROnPlateau(monitor='val_loss',
factor=0.1,
patience=patience_reduce_lr,
verbose=1,
mode="min",
min_lr=min_lr),
auroc,
EarlyStopping(monitor='val_loss',
mode='min',
verbose=1,
patience=25),
]
print("** start training **")
history = model_train.fit_generator(
generator=train_sequence,
steps_per_epoch=train_steps,
epochs=epochs,
validation_data=validation_sequence,
validation_steps=validation_steps,
callbacks=callbacks,
class_weight=class_weights,
workers=generator_workers,
shuffle=False,
)
# dump history
print("** dump history **")
with open(os.path.join(output_dir, "history.pkl"), "wb") as f:
pickle.dump({
"history": history.history,
"auroc": auroc.aurocs,
}, f)
print("** done! **")
finally:
os.remove(running_flag_file)
def main(fold,gender_train,gender_test):
# parser config
config_file = 'config_file.ini'
cp = ConfigParser()
cp.read(config_file)
root_output_dir= cp["DEFAULT"].get("output_dir")
# default config
print(root_output_dir,gender_train)
output_dir= root_output_dir + gender_train+'/Fold_'+str(fold)+'/output/'
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
# train config
image_dimension = cp["TRAIN"].getint("image_dimension")
# test config
batch_size = cp["TEST"].getint("batch_size")
test_steps = cp["TEST"].get("test_steps")
use_best_weights = cp["TEST"].getboolean("use_best_weights")
# parse weights file path
output_weights_name = cp["TRAIN"].get("output_weights_name")
weights_path = os.path.join(output_dir, output_weights_name)
best_weights_path = os.path.join(output_dir, f"best_{output_weights_name}")
# get test sample count
test_counts, _ = get_sample_counts(root_output_dir+gender_train+'/Fold_'+str(fold),str(gender_test), class_names)
# compute steps
if test_steps == "auto":
test_steps = int(test_counts / batch_size)
else:
try:
test_steps = int(test_steps)
except ValueError:
raise ValueError(f"""
test_steps: {test_steps} is invalid,
please use 'auto' or integer.
""")
print(f"** test_steps: {test_steps} **")
print("** load model **")
if use_best_weights:
print("** use best weights **")
model_weights_path = best_weights_path
else:
print("** use last weights **")
model_weights_path = weights_path
model_factory = ModelFactory()
model = model_factory.get_model(
class_names,
model_name=base_model_name,
use_base_weights=False,
weights_path=model_weights_path)
print("** load test generator **")
test_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(root_output_dir+gender_train+'/Fold_'+str(fold), str(gender_test)+".csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=None,
steps=test_steps,
shuffle_on_epoch_end=False,
)
print("** make prediction **")
y_hat = model.predict_generator(test_sequence, verbose=1)
y = test_sequence.get_y_true()
y_pred_dir = output_dir + "y_pred_run_" + str(fold)+"_train"+gender_train+"_"+gender_test+ ".csv"
y_true_dir = output_dir + "y_true_run_" + str(fold)+"_train"+gender_train+"_"+gender_test+ ".csv"
np.savetxt(y_pred_dir, y_hat, delimiter=",")
np.savetxt(y_true_dir, y, delimiter=",")
def main():
# parser config
print("### Input configuration file ### \n")
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
print("### Read default configurations ### \n")
output_dir = cp["DEFAULT"].get("output_dir")
image_train_source_dir = cp["DEFAULT"].get("image_train_source_dir")
image_valid_source_dir = cp["DEFAULT"].get("image_valid_source_dir")
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
# train config
print("### Reading training configurations ### \n")
use_base_model_weights = cp["TRAIN"].getboolean("use_base_model_weights")
use_trained_model_weights = cp["TRAIN"].getboolean(
"use_trained_model_weights")
use_best_weights = cp["TRAIN"].getboolean("use_best_weights")
output_weights_name = cp["TRAIN"].get("output_weights_name")
epochs = cp["TRAIN"].getint("epochs")
batch_size = cp["TRAIN"].getint("batch_size")
initial_learning_rate = cp["TRAIN"].getfloat("initial_learning_rate")
generator_workers = cp["TRAIN"].getint("generator_workers")
image_dimension = cp["TRAIN"].getint("image_dimension")
patience_reduce_lr = cp["TRAIN"].getint("patience_reduce_lr")
min_lr = cp["TRAIN"].getfloat("min_lr")
positive_weights_multiply = cp["TRAIN"].getfloat(
"positive_weights_multiply")
dataset_csv_dir = cp["TRAIN"].get("dataset_csv_dir")
# if previously trained weights is used, never re-split
if use_trained_model_weights:
# resuming mode
print("** use trained model weights **")
# load training status for resuming
training_stats_file = os.path.join(output_dir, ".training_stats.json")
if os.path.isfile(training_stats_file):
# TODO: add loading previous learning rate?
training_stats = json.load(open(training_stats_file))
else:
training_stats = {}
else:
# start over
training_stats = {}
print("### Show model summary ### \n")
show_model_summary = cp["TRAIN"].getboolean("show_model_summary")
# end parser config
print("### Check output directory ### \n")
# check output_dir, create it if not exists
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
running_flag_file = os.path.join(output_dir, ".training.lock")
if os.path.isfile(running_flag_file):
raise RuntimeError("A process is running in this directory!!!")
else:
open(running_flag_file, "a").close()
try:
print("### Backup config file to {} \n".format(output_dir))
shutil.copy(config_file,
os.path.join(output_dir,
os.path.split(config_file)[1]))
datasets = ["train", "valid"]
for dataset in datasets:
shutil.copy(os.path.join(dataset_csv_dir, dataset + '.csv'),
output_dir)
# get train/dev sample counts
print("### Get class frequencies ### \n")
train_counts, train_pos_counts = get_sample_counts(
output_dir, "train", class_names)
dev_counts, _ = get_sample_counts(output_dir, "valid", class_names)
# compute steps
print("### Compute step size ### \n")
train_steps = int(train_counts / batch_size)
validation_steps = int(dev_counts / batch_size)
# compute class weights
print("### Class weights ### \n")
class_weights = get_class_weights(
train_counts,
train_pos_counts,
multiply=positive_weights_multiply,
)
print("### Class_weights ### \n")
print(class_weights)
print("\n")
print("### Loading model ### \n")
if use_trained_model_weights:
if use_best_weights:
model_weights_file = os.path.join(
output_dir, "best_" + output_weights_name)
else:
model_weights_file = os.path.join(output_dir,
output_weights_name)
else:
model_weights_file = None
model_factory = ModelFactory()
print("### Get model ### \n")
model = model_factory.get_model(
class_names,
model_name=base_model_name,
use_base_weights=use_base_model_weights,
weights_path=model_weights_file,
input_shape=(image_dimension, image_dimension, 3))
print("Show model summary? {}".format(show_model_summary))
if show_model_summary:
print(model.summary())
print("\n ### Create image generators ### \n")
train_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(output_dir, "train.csv"),
class_names=class_names,
source_image_dir=image_train_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=augmenter,
steps=train_steps,
)
validation_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(output_dir, "valid.csv"),
class_names=class_names,
source_image_dir=image_valid_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=augmenter,
steps=validation_steps,
shuffle_on_epoch_end=False,
)
output_weights_path = os.path.join(output_dir, output_weights_name)
print("### Set output weights path to {} ### \n".format(
output_weights_path))
print("### Check multiple gpu availability ### \n")
#gpus = len(os.getenv("CUDA_VISIBLE_DEVICES").split(","))
if False: ## Turn off multiple gpu model
print("### Multi_gpu_model is used! gpus={} ###".format(gpus))
model_train = multi_gpu_model(model, gpus)
# FIXME: currently (Keras 2.1.2) checkpoint doesn't work with multi_gpu_model
checkpoint = MultiGPUModelCheckpoint(
filepath=output_weights_path,
base_model=model,
)
else:
model_train = model
checkpoint = ModelCheckpoint(
output_weights_path,
save_weights_only=True,
save_best_only=True,
verbose=1,
)
print("### Compile model with class weights ### \n")
optimizer = Adam(lr=initial_learning_rate)
model_train.compile(optimizer=optimizer, loss="binary_crossentropy")
auroc = MultipleClassAUROC(
sequence=validation_sequence,
class_names=class_names,
weights_path=output_weights_path,
stats=training_stats,
workers=generator_workers,
)
callbacks = [
checkpoint,
TensorBoard(log_dir=os.path.join(output_dir, "logs")),
ReduceLROnPlateau(monitor='val_loss',
factor=0.1,
patience=patience_reduce_lr,
verbose=1,
mode="min",
min_lr=min_lr),
auroc,
]
print("### Start training ### \n")
history = model_train.fit(
train_sequence,
steps_per_epoch=train_steps,
epochs=epochs,
validation_data=validation_sequence,
validation_steps=validation_steps,
callbacks=callbacks,
class_weight=class_weights,
workers=generator_workers,
shuffle=False,
)
# dump history
print("### Dump history ### \n")
with open(os.path.join(output_dir, "history.pkl"), "wb") as f:
pickle.dump({
"history": history.history,
"auroc": auroc.aurocs,
}, f)
print("** done! **")
finally:
os.remove(running_flag_file)
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
output_dir = cp["DEFAULT"].get("output_dir")
if not os.path.exists(output_dir):
os.mkdir(output_dir)
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
image_dimension = cp["TRAIN"].getint("image_dimension")
batch_size = cp["TEST"].getint("batch_size")
test_steps = cp["TEST"].get("test_steps")
# parse weights file path
output_weights_name = cp["TRAIN"].get("output_weights_name")
weights_path = os.path.join(output_dir, output_weights_name)
data_set_dir = cp["TRAIN"].get("dataset_csv_dir")
input_weights_name = cp["TRAIN"].get("input_weights_name")
best_weights_path = os.path.join(data_set_dir,
f"best_{input_weights_name}")
# get test sample count
test_counts, _ = get_sample_counts(data_set_dir, "test", class_names)
# compute steps
if test_steps == "auto":
test_steps = int(test_counts / batch_size)
else:
try:
test_steps = int(test_steps)
except ValueError:
raise ValueError(f"""
test_steps: {test_steps} is invalid,
please use 'auto' or integer.
""")
# CAM config
bbox_list_file = cp["CAM"].get("bbox_list_file")
use_best_weights = cp["CAM"].getboolean("use_best_weights")
print("** load model **")
if use_best_weights:
print("** use best weights **")
model_weights_path = best_weights_path
else:
print("** use last weights **")
model_weights_path = weights_path
model_factory = ModelFactory()
model = model_factory.get_model(class_names,
model_name=base_model_name,
use_base_weights=False,
weights_path=model_weights_path)
print("read bbox list file")
df_images = pd.read_csv(bbox_list_file, header=None, skiprows=1)
df_images.columns = ["file_name", "label", "x", "y", "w", "h"]
print("create a generator for loading transformed images")
cam_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(data_set_dir, "test.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=None,
steps=test_steps,
shuffle_on_epoch_end=False,
)
image_output_dir = os.path.join(output_dir, "cam")
if not os.path.isdir(image_output_dir):
os.makedirs(image_output_dir)
print("create CAM")
df_images.apply(
lambda g: create_cam(
df_g=g,
output_dir=image_output_dir,
image_source_dir=image_source_dir,
model=model,
generator=cam_sequence,
class_names=class_names,
),
axis=1,
)
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
weights_dir = cp["DEFAULT"].get("weights_dir")
base_model_name = cp["DEFAULT"].get("base_model_name")
chexnet_class_names = cp["DEFAULT"].get("chexnet_class_names").split(",")
class_names = cp["DEFAULT"].get("class_names").split(",")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
data_dir = cp["DEFAULT"].get("data_dir")
# train config
image_dimension = cp["TRAIN"].getint("image_dimension")
# test config
batch_size = cp["TEST"].getint("batch_size")
test_steps = cp["TEST"].get("test_steps")
# parse weights file path
output_weights_name = cp["TRAIN"].get("output_weights_name")
weights_path = os.path.join(weights_dir, output_weights_name)
# get test sample count
test_counts = get_sample_counts(data_dir, "all_data", class_names)
# compute steps
if test_steps == "auto":
test_steps = int(test_counts / batch_size)
else:
try:
test_steps = int(test_steps)
except ValueError:
raise ValueError(f"""
test_steps: {test_steps} is invalid,
please use 'auto' or integer.
""")
print(f"** test_steps: {test_steps} **")
print("** load model **")
model_weights_path = weights_path
model_factory = ModelFactory()
model = model_factory.get_model(chexnet_class_names,
model_name=base_model_name,
use_base_weights=False,
weights_path=model_weights_path,
pop_last_layer=True)
model.summary()
print("** load test generator **")
test_sequence = AugmentedImageSequence(
dataset_csv_file=os.path.join(data_dir, "all_data.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=None,
steps=test_steps,
shuffle_on_epoch_end=False,
)
print("** make prediction **")
image, y = test_sequence.__getitem__(4)
y_hat = model.predict(image)
# y_hat = model.predict_generator(test_sequence, verbose=1)
# y = test_sequence.get_y_true()
print(y_hat.shape)
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
output_dir = cp["DEFAULT"].get("output_dir")
if not os.path.exists(output_dir):
os.mkdir(output_dir)
base_model_name = cp["DEFAULT"].get("base_model_name")
class_names = cp["DEFAULT"].get("class_names").split(",")
image_source_dir = cp["DEFAULT"].get("image_source_dir")
data_set_dir = cp["TRAIN"].get("dataset_csv_dir")
# train config
image_dimension = cp["TRAIN"].getint("image_dimension")
# test config
batch_size = cp["TEST"].getint("batch_size")
test_steps = cp["TEST"].get("test_steps")
use_best_weights = cp["TEST"].getboolean("use_best_weights")
# parse weights file path
input_weights_name = cp["TRAIN"].get("input_weights_name")
weights_path = os.path.join(data_set_dir, input_weights_name)
best_weights_path = os.path.join(data_set_dir,
"best_{}".format(input_weights_name))
# get test sample count
test_counts, _ = get_sample_counts(data_set_dir, "test", class_names)
# compute steps
if test_steps == "auto":
test_steps = int(test_counts / batch_size)
else:
try:
test_steps = int(test_steps)
except ValueError:
raise ValueError("""
test_steps: {} is invalid,
please use 'auto' or integer.
""".format(test_steps))
print("** test_steps: {} **".format(test_steps))
print("** load model **")
if use_best_weights:
print("** use best weights **")
model_weights_path = best_weights_path
else:
print("** use last weights **")
model_weights_path = weights_path
model_factory = ModelFactory()
model = model_factory.get_model(class_names,
model_name=base_model_name,
use_base_weights=False,
weights_path=model_weights_path)
print("** load test generator **")
test_sequence = AugmentedImageSequence(
# dataset_csv_file=os.path.join(output_dir, "dev.csv"),
dataset_csv_file=os.path.join(data_set_dir, "test.csv"),
# dataset_csv_file=os.path.join(data_set_dir, "MIMIC_dataset.csv"),
class_names=class_names,
source_image_dir=image_source_dir,
batch_size=batch_size,
target_size=(image_dimension, image_dimension),
augmenter=None,
steps=test_steps,
shuffle_on_epoch_end=False,
)
# test_sequence.dataset_df.to_csv(os.path.join(output_dir, 'test_data_frame.csv'))
print("** make prediction **")
y_hat = model.predict_generator(test_sequence, verbose=1)
y = test_sequence.get_y_true()
# np.savetxt(os.path.join(output_dir, 'y_hat_1205_default_weight.txt'), y_hat)
np.savetxt(os.path.join(output_dir, 'y_0430.txt'), y)
test_log_path = os.path.join(output_dir, "test.log")
print("** write log to {} **".format(test_log_path))
aurocs = []
with open(test_log_path, "w") as f:
for i in range(len(class_names)):
try:
score = roc_auc_score(y[:, i], y_hat[:, i])
aurocs.append(score)
except ValueError:
score = 0
f.write("{}: {}\n".format(class_names[i], score))
mean_auroc = np.mean(aurocs)
f.write("-------------------------\n")
f.write("mean auroc: {}\n".format(mean_auroc))
print("mean auroc: {}".format(mean_auroc))