def main():
args = get_parser()
# Getting data to predict on
if os.path.isfile(args.images_path):
data = load_image(args.images_path, args.image_size)
image_names = [args.images_path]
data = data.reshape(-1, args.image_size, args.image_size, 1)
else:
data, image_names = load_images(args.images_path, args.image_size)
# Creating model
model = create_model(image_size=args.image_size,
weights_path=args.weights_path)
# Predicting
head_root, head_vowel, head_consonant = model.predict(data, verbose=1)
head_root = np.argmax(head_root, axis=1)
head_vowel = np.argmax(head_vowel, axis=1)
head_consonant = np.argmax(head_consonant, axis=1)
# Creating and saving resulting DataFrame
result_df = pd.DataFrame()
result_df['image_name'] = image_names
result_df['head_root'] = head_root
result_df['head_vowel'] = head_vowel
result_df['head_consonant'] = head_consonant
result_df.to_csv('result.csv', index=False)
def main(_):
# Retrieve parameters
config = get_parameters()
#prepare data
word_table, data = dataset.prepare_data(config)
# Preprocess all images
test_data = pre.load_image('data/laska.png', (224, 224))
test_data = np.array([test_data])
# Build model.
model = ImageCaptioner(config, word_table)
# model.train(train_data)
model.test(test_data)
def get_batch_from_txt_files_(self):
self.index += 1
#for i, f in enumerate(fs):
img = load_image(osp.join('/home/ubuntu/3d-testing/InterHand2.6M/main/', self.fs[self.index]).strip())
box = self.bs[self.index].split(",")
bbox = []
for b in box:
bbox.append(float(b.replace("\n", "")))
img, inv_trans = augmentation(img, np.array(bbox), None, None, None, 'test', None)
img = self.transform(img.astype(np.float32))/255.
# image = cv2.imread(osp.join('/home/ubuntu/3d-testing/InterHand2.6M/main/', self.fs[self.index]).strip())
# image = cv2.rectangle(image, (int(bbox[0]), int(bbox[1])), (int(bbox[0])+int(bbox[2]), int(bbox[0]) + int(bbox[3])), (255,0,0), 3)
# print(cv2.imwrite("bbox_testing/" + str(self.index)+".jpg", image))
return img, osp.join('/home/ubuntu/3d-testing/InterHand2.6M/main/', self.fs[self.index]).strip(), inv_trans
from data_augmentation import SSDAugmentation
from utils.datasets import DataManager
from utils.preprocessing import load_image
from utils.datasets import get_arg_to_class
from utils.visualizer import draw_image_boxes
import cv2
# import numpy as np
size = 300
dataset_name = 'VOC2007'
class_names = ['background', 'aeroplane']
class_to_arg = get_arg_to_class(class_names)
# transformer = SSDAugmentation(size, mean=(104, 117, 123))
transformer = SSDAugmentation(size, mean=(0, 0, 0))
data_manager = DataManager(dataset_name, class_names)
data = data_manager.load_data()
for image_key in data.keys():
image_path = data_manager.image_prefix + image_key
print(cv2.imread(image_path))
image_array = load_image(image_path, (size, size))[0]
original_image_array = load_image(image_path, None)[0]
ground_truth_data = data[image_key]
boxes = ground_truth_data[:, :4]
labels = ground_truth_data[:, 4:]
transformed_data = transformer(image_array, boxes, labels)
image_array, boxes, labels = transformed_data
# image_array = image_array[:, :, ::-1]
image_array = image_array.astype('uint8')
draw_image_boxes(boxes, image_array, class_to_arg, normalized=True)
from utils.data_augmentation import HorizontalFlip
from utils.data_augmentation import ToPercentCoords
from utils.data_augmentation import Resize
from utils.data_augmentation import SubtractMeans
from utils.preprocessing import load_image
from utils.preprocessing import B_MEAN, G_MEAN, R_MEAN
from datasets import DataManager
import matplotlib.pyplot as plt
data_manager = DataManager('VOC2007', 'train')
class_names = data_manager.class_names
train_data = data_manager.load_data()
image_path = sorted(list(train_data.keys()))[7]
box_data = train_data[image_path]
image_array = load_image(image_path, RGB=False).copy()
data = (image_array, box_data[:, :4], box_data[:, 4:])
convert_from_ints = ConvertFromInts()
to_absolute_coords = ToAbsoluteCoords()
photometric_distort = PhotometricDistort2()
expand = Expand((B_MEAN, G_MEAN, R_MEAN))
random_sample_crop = RandomSampleCrop()
horizontal_flip = HorizontalFlip()
to_percent_coords = ToPercentCoords()
resize = Resize(300)
subtract_means = SubtractMeans((B_MEAN, G_MEAN, R_MEAN))
plt.imshow(image_array[..., ::-1])
plt.show()
data = convert_from_ints(*data)
selected_classes = [class_names[0]] + [class_names[ground_truth_class_arg]]
num_ground_truth_boxes = 0
class_decoder = get_arg_to_class(class_names)
num_classes = len(class_names)
data_manager = DataManager(dataset_name, selected_classes, data_prefix,
image_prefix)
ground_truth_data = data_manager.load_data()
difficult_data_flags = data_manager.parser.difficult_objects
image_names = sorted(list(ground_truth_data.keys()))
# print('Number of images found:', len(image_names))
for image_name in image_names:
ground_truth_sample = ground_truth_data[image_name]
image_prefix = data_manager.image_prefix
image_path = image_prefix + image_name
image_array, original_image_size = load_image(image_path, input_shape)
image_array = preprocess_images(image_array)
predicted_data = predict(model, image_array, prior_boxes,
original_image_size, 21, class_threshold,
iou_threshold)
ground_truth_sample = denormalize_box(ground_truth_sample,
original_image_size)
ground_truth_boxes_in_image = len(ground_truth_sample)
difficult_objects = difficult_data_flags[image_name]
difficult_objects = np.asarray(difficult_objects, dtype=bool)
num_ground_truth_boxes += np.sum(np.logical_not(difficult_objects))
if predicted_data is None:
# print('Zero predictions given for image:', image_name)
continue
#plt.imshow(original_image_array.astype('uint8'))
#plt.show()
ground_truth_data = dataset_manager.load_data()
class_names = dataset_manager.class_names
print('Found:', len(ground_truth_data), 'images')
print('Class names: \n', class_names)
# prior boxes
# ------------------------------------------------------------------
# model = SSD300()
prior_boxes = create_prior_boxes()
print('Prior boxes shape:', prior_boxes.shape)
print('Prior box example:', prior_boxes[777])
image_path = '../images/fish-bike.jpg'
# input_shape = model.input_shape[1:3]
input_shape = (300, 300)
image_array = load_image(image_path, input_shape)
prior_boxes = to_point_form(prior_boxes)
box_coordinates = prior_boxes[7010:7015, :]
plot_box_data(box_coordinates, image_array)
plt.imshow(image_array)
plt.show()
# ground truth
# ------------------------------------------------------------------
image_name, box_data = random.sample(ground_truth_data.items(), 1)[0]
print('Data sample: \n', box_data)
# image_path = dataset_manager.images_path + image_name
image_path = image_name
arg_to_class = dataset_manager.arg_to_class
colors = get_colors(len(class_names))
image_array = load_image(image_path, input_shape)
