import numpy as np
from geometry_processing.globals import MODEL_WEIGHTS
from geometry_processing.utils.helpers import load_weights
from geometry_processing.models.multiview_cnn import load_model, test
parser = argparse.ArgumentParser(description='Test MVCNN classification.')
parser.add_argument('--matrix_path',
required=True,
type=str,
help='Path to save the confusion matrix.')
args = parser.parse_args()
matrix_path = args.matrix_path
if __name__ == '__main__':
# Initialize model.
mvcnn = load_model()
load_weights(mvcnn, MODEL_WEIGHTS)
# Run through entire test dataset.
matrix = test(mvcnn)
print('Accuracy %.4f' % np.mean(np.diag(matrix) / np.sum(matrix, axis=1)))
# Save matrix to disk.
if matrix_path:
print('Saving to %s.' % matrix_path)
np.save(matrix_path, matrix)
import numpy as np
from geometry_processing.globals import SALIENCY_MODEL
from geometry_processing.utils.helpers import load_weights
from geometry_processing.models.saliency import build_model, test
parser = argparse.ArgumentParser(description='Test saliency classification.')
parser.add_argument('--matrix_path', required=True, type=str,
help='Path to save the confusion matrix.')
args = parser.parse_args()
matrix_path = args.matrix_path
if __name__ == '__main__':
# Initialize model.
saliency_cnn = build_model()
load_weights(saliency_cnn, SALIENCY_MODEL)
# Run through entire test dataset.
matrix = test(saliency_cnn)
print('Per Class Accuracy %s' % (np.diag(matrix) / np.sum(matrix, axis=1)))
print('MAP: %.4f' % np.mean(np.diag(matrix) / np.sum(matrix, axis=1)))
# Save matrix to disk.
if matrix_path:
print('Saving to %s.' % matrix_path)
np.save(matrix_path, matrix)
import argparse
from geometry_processing.globals import SALIENCY_MODEL, MODEL_WEIGHTS
from geometry_processing.utils.helpers import load_weights
from geometry_processing.models.saliency import build_model, train
parser = argparse.ArgumentParser(description='Train a saliency NN.')
parser.add_argument('--verbose',
required=False,
type=int,
default=1,
help='[1] for ncurses, [2] for per epoch.')
parser.add_argument('--log_file',
required=False,
type=str,
default='',
help='File to log training, validation loss and accuracy.')
args = parser.parse_args()
verbose = args.verbose
log_file = args.log_file
if __name__ == '__main__':
# Build and load cached weights.
saliency_cnn = build_model()
load_weights(saliency_cnn, MODEL_WEIGHTS)
# Update model.
train(saliency_cnn, save_path=SALIENCY_MODEL)
print(path_prediction[0], 0.0)
else:
for i in range(predictions.shape[0]):
if entropy(predictions[i]) <= confidence_threshold:
print(full_paths[i], 1.0)
else:
print(full_paths[i], 0.0)
if __name__ == '__main__':
# Data source and image normalization.
img_normalize = samplewise_normalize(IMAGE_MEAN, IMAGE_STD)
# Directory of images.
if generate_dataset == 'train':
datagen = FilenameImageDatagen(TRAIN_DIR, preprocess=img_normalize)
elif generate_dataset == 'test':
datagen = FilenameImageDatagen(VALID_DIR, preprocess=img_normalize)
else:
raise ValueError('Invalid input for --generate_dataset.')
# # Use the fc activations as features.
model = load_model()
load_weights(model, MODEL_WEIGHTS)
# Wrapper around Tensorflow run operation.
functor = K.function([model.layers[0].input, K.learning_phase()],
[model.get_layer('predictions').output])
generate(datagen, functor)