def test_model(self):
inputs = []
images = []
file_paths = list_files_in_directory('test_resources/*.jpg')
for file_path in file_paths:
image_array = load_image(file_path, False, target_size=(300, 300))
images.append(imread(file_path))
inputs.append(image_array)
inputs = np.asarray(inputs, dtype='float32')
inputs = preprocess_input(inputs)
predictions = self.model.predict(inputs, batch_size=1, verbose=1)
prior_box_manager = PriorBoxManager(self.prior_boxes,
box_scale_factors=[.1, .1, .2, .2])
results = prior_box_manager.detection_out(predictions)
for i, img in enumerate(images):
# Parse the outputs.
det_label = results[i][:, 0]
det_conf = results[i][:, 1]
det_xmin = results[i][:, 2]
det_ymin = results[i][:, 3]
det_xmax = results[i][:, 4]
det_ymax = results[i][:, 5]
# Get detections with confidence higher than 0.6.
top_indices = [i for i, conf in enumerate(det_conf) if conf >= 0.8]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin = det_xmin[top_indices]
top_ymin = det_ymin[top_indices]
top_xmax = det_xmax[top_indices]
top_ymax = det_ymax[top_indices]
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()
plt.imshow(img / 255.)
currentAxis = plt.gca()
for i in range(top_conf.shape[0]):
xmin = int(round(top_xmin[i] * img.shape[1]))
ymin = int(round(top_ymin[i] * img.shape[0]))
xmax = int(round(top_xmax[i] * img.shape[1]))
ymax = int(round(top_ymax[i] * img.shape[0]))
score = top_conf[i]
label = int(top_label_indices[i])
#label_name = voc_classes[label - 1]
#label_name = self.class_names[label - 1]
label_name = self.class_names[label]
display_txt = '{:0.2f}, {}'.format(score, label_name)
coords = (xmin, ymin), xmax-xmin+1, ymax-ymin+1
color = colors[label]
currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2))
currentAxis.text(xmin, ymin, display_txt, bbox={'facecolor':color, 'alpha':0.5})
plt.show()
multibox_loss = MultiboxLoss(num_classes, neg_pos_ratio=2.0).compute_loss
model.compile(optimizer=Adam(lr=3e-4),
loss=multibox_loss,
metrics=[class_accuracy])
box_creator = PriorBoxCreator(model)
prior_boxes = box_creator.create_boxes()
ground_truth_manager = XMLParser(ground_data_prefix,
background_id=None,
class_names=classes)
ground_truth_data = ground_truth_manager.get_data()
print('Number of ground truth samples:', len(ground_truth_data.keys()))
train_keys, validation_keys = split_data(ground_truth_data, training_ratio=.8)
prior_box_manager = PriorBoxManager(prior_boxes,
box_scale_factors=[.1, .1, .2, .2],
num_classes=num_classes)
image_generator = ImageGenerator(ground_truth_data,
prior_box_manager,
batch_size,
image_shape[0:2],
train_keys,
validation_keys,
image_prefix,
vertical_flip_probability=0,
horizontal_flip_probability=0.5)
model_names = ('../trained_models/model_checkpoints/' +
'weights.{epoch:02d}-{val_loss:.2f}.hdf5')
model_checkpoint = ModelCheckpoint(model_names,
# parameters root_prefix = '../datasets/VOCdevkit/VOC2007/' image_prefix = root_prefix + 'JPEGImages/' ground_data_prefix = root_prefix + 'Annotations/' model = my_SSD(num_classes=21) image_shape = model.input_shape[1:] background_id = 0 ground_truth_manager = XMLParser(ground_data_prefix, background_id) ground_truth_data = ground_truth_manager.get_data() VOC2007_decoder = ground_truth_manager.arg_to_class box_creator = PriorBoxCreator(model) prior_boxes = box_creator.create_boxes() vis = BoxVisualizer(image_prefix, image_shape[0:2], VOC2007_decoder) prior_boxes = flatten_prior_boxes(prior_boxes) selected_key = random.choice(list(ground_truth_data.keys())) selected_data = ground_truth_data[selected_key] selected_box_coordinates = selected_data[:, 0:4] prior_box_manager = PriorBoxManager(prior_boxes, background_id,box_scale_factors=[.1,.1,.2,.2]) encoded_boxes = prior_box_manager.assign_boxes(selected_data) positive_mask = encoded_boxes[:, 4 + background_id] != 1 vis.draw_normalized_box(encoded_boxes[positive_mask], selected_key) decoded_boxes = prior_box_manager.decode_boxes(encoded_boxes) vis.draw_normalized_box(decoded_boxes[positive_mask], selected_key) vis.draw_normalized_box(prior_boxes[positive_mask], selected_key)
from utils.utils import flatten_prior_boxes
from utils.utils import split_data
# parameters
root_prefix = '../datasets/VOCdevkit/VOC2007/'
image_prefix = root_prefix + 'JPEGImages/'
ground_data_prefix = root_prefix + 'Annotations/'
model = my_SSD(num_classes=21)
image_shape = model.input_shape[1:]
background_id = 0
ground_truth_manager = XMLParser(ground_data_prefix, background_id)
ground_truth_data = ground_truth_manager.get_data()
box_creator = PriorBoxCreator(model)
prior_boxes = box_creator.create_boxes()
prior_box_manager = PriorBoxManager(prior_boxes, background_id)
prior_boxes = flatten_prior_boxes(prior_boxes)
train_keys, validation_keys = split_data(ground_truth_data, training_ratio=.8)
batch_size = 10
image_generator = ImageGenerator(ground_truth_data,
prior_box_manager,
batch_size,
image_shape[0:2],
train_keys,
validation_keys,
image_prefix,
vertical_flip_probability=0,
horizontal_flip_probability=0.5)
branch_3 = Reshape((-1, 4 + num_classes))(branch_3)
local_3 = Lambda(lambda x: x[:, :, :4])(branch_3)
class_3 = Lambda(lambda x: K.softmax(x[:, :, 4:]))(branch_3)
classification_tensor = merge([class_1, class_2, class_3],
mode='concat',
concat_axis=1)
localization_tensor = merge([local_1, local_2, local_3],
mode='concat',
concat_axis=1)
output_tensor = merge([localization_tensor, classification_tensor],
mode='concat',
concat_axis=-1)
model = Model(input_tensor, output_tensor)
return model
if __name__ == '__main__':
input_shape = (100, 100, 3)
model = mini_SSD(input_shape)
model.compile(optimizer='adam', loss='categorical_crossentropy')
print(model.summary())
plot(model, 'mini_SSD.png')
from utils.prior_box_creator import PriorBoxCreator
from utils.prior_box_manager import PriorBoxManager
prior_box_creator = PriorBoxCreator(model)
prior_boxes = prior_box_creator.create_boxes()
prior_box_manager = PriorBoxManager(prior_boxes)
print(prior_box_manager.prior_boxes.shape)
if layer.name in freeze:
layer.trainable = False
multibox_loss = MultiboxLoss(num_classes, neg_pos_ratio=2.0).compute_loss
model.compile(optimizer=Adam(lr=3e-4), loss=multibox_loss, metrics=['acc'])
box_creator = PriorBoxCreator(model)
prior_boxes = box_creator.create_boxes()
#prior_boxes = pickle.load(open('prior_boxes_ssd300.pkl', 'rb'))
ground_truth_manager = XMLParser(ground_data_prefix, background_id=None)
ground_truth_data = ground_truth_manager.get_data()
train_keys, validation_keys = split_data(ground_truth_data, training_ratio=.8)
prior_box_manager = PriorBoxManager(prior_boxes,
box_scale_factors=[.1, .1, .2, .2])
image_generator = ImageGenerator(ground_truth_data,
prior_box_manager,
batch_size,
image_shape[0:2],
train_keys,
validation_keys,
image_prefix,
vertical_flip_probability=0,
horizontal_flip_probability=0.5)
model_names = ('../trained_models/model_checkpoints/' +
'weights.{epoch:02d}-{val_loss:.2f}.hdf5')
model_checkpoint = ModelCheckpoint(model_names,
monitor='val_loss',
layer_scale, box_arg = 0, 780
box_coordinates = prior_boxes[layer_scale][box_arg, :, :]
#box_visualizer.draw_normalized_box(box_coordinates)
ground_data_prefix = root_prefix + 'Annotations/'
ground_truth_data = XMLParser(ground_data_prefix).get_data()
random_key = random.choice(list(ground_truth_data.keys()))
selected_data = ground_truth_data[random_key]
selected_box_coordinates = selected_data[:, 0:4]
#box_visualizer.draw_normalized_box(selected_box_coordinates, random_key)
train_keys, validation_keys = split_data(ground_truth_data,
training_ratio=.8)
prior_box_manager = PriorBoxManager(prior_boxes)
assigned_encoded_boxes = prior_box_manager.assign_boxes(selected_data)
positive_mask = assigned_encoded_boxes[:, -8] > 0
assigned_decoded_boxes = prior_box_manager.decode_boxes(
assigned_encoded_boxes)
decoded_positive_boxes = assigned_decoded_boxes[positive_mask, 0:4]
#box_visualizer.draw_normalized_box(decoded_positive_boxes, random_key)
batch_size = 10
image_generator = ImageGenerator(ground_truth_data,
prior_box_manager,
batch_size,
image_shape[0:2],
train_keys,
validation_keys,
image_prefix,
from models import SSD300
from utils.prior_box_manager import PriorBoxManager
from utils.prior_box_creator import PriorBoxCreator
from utils.XML_parser import XMLParser
image_shape = (300, 300, 3)
overlap_threshold = .5
model = SSD300(image_shape)
box_creator = PriorBoxCreator(model)
prior_boxes = box_creator.create_boxes()
data_path = '../datasets/VOCdevkit/VOC2007/'
ground_truths = XMLParser(data_path + 'Annotations/').get_data()
prior_box_manager = PriorBoxManager(prior_boxes,
overlap_threshold,
background_id=0)
a = prior_box_manager.assign_boxes(ground_truths['000009.jpg'])
encoded_boxes = prior_box_manager.encoded_boxes
best_iou_indices = prior_box_manager.best_iou_indices
num_assigned_boxes = prior_box_manager.num_assigned_boxes
best_iou_mask = prior_box_manager.best_iou_mask