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)
ckpt_manager = tf.train.CheckpointManager(ckpt, checkpoint_path, max_to_keep=5)
start_epoch = 0
if ckpt_manager.latest_checkpoint and continue_from_last_ckpt:
start_epoch = int(ckpt_manager.latest_checkpoint.split('-')[-1])
ckpt.restore(ckpt_manager.latest_checkpoint)
print("Restored from checkpoint: {}".format(
ckpt_manager.latest_checkpoint))
for epoch in range(start_epoch, EPOCHS):
start = time.time()
total_loss = 0
for batch in range(data_generator.steps):
img, target, _ = data_generator.__getitem__(batch)
# print( target.max())
with graph_mode():
img_tensor = chexnet.get_visual_features(img)
print("batch: {}".format(batch))
# img_tensor=np.random.randint(low=-1,high=1,size=(1,1024))
# img_tensor=np.float32(img_tensor)
batch_loss, t_loss = train_step(img_tensor, target)
total_loss += t_loss
if batch % 5 == 0:
print('Epoch {} Batch {} Loss {:.4f}'.format(
epoch + 1, batch,
batch_loss.numpy() / int(target.shape[1])))
# storing the epoch end loss value to plot later
fig = plt.figure(figsize=(7.20, 10.80))
fig.add_axes((.0, .5, .9, .7))
fig.text(.1, .3, caption, wrap=True, fontsize=20)
plt.xticks([])
plt.yticks([])
plt.imshow(img)
plt.savefig(output_images_folder + "/{}".format(img_name))
plt.close(fig)
hypothesis = []
references = []
for batch in range(data_generator.steps):
print("Batch: {}".format(batch))
img, target, img_path = data_generator.__getitem__(batch)
with graph_mode():
img_tensor = chexnet.get_visual_features(img)
result, attention_plot = evaluate(img_tensor)
target_word_list = tokenizer_wrapper.get_sentence_from_tokens(target)
references.append([target_word_list])
hypothesis.append(result)
target_sentence = tokenizer_wrapper.get_string_from_word_list(
target_word_list)
predicted_sentence = tokenizer_wrapper.get_string_from_word_list(result)
# save_output_prediction(img_path[0], target_sentence, predicted_sentence)
print(get_bleu_scores(hypothesis, references))
# # captions on the validation set
# rid = np.random.randint(0, len(img_name_val))
