def preprocess():
WIDTH = 484
HEIGHT = 240
ENSEMBLE_N = 3
# GET COLOR ENCODING AND ITS INDEX MAPPING
colors = loadmat('../data/color150.mat')['colors']
root = '..'
names = {}
with open('../data/object150_info.csv') as f:
reader = csv.reader(f)
next(reader)
for row in reader:
names[int(row[0])] = row[5].split(";")[0]
idx_map = create_idx_group()
colors, names = edit_colors_names_group(colors, names)
# SETUP MODEL
cfg_path = os.path.join('..', 'config',
'ade20k-mobilenetv2dilated-c1_deepsup.yaml')
#cfg_path="config/ade20k-resnet18dilated-ppm_deepsup.yaml"
model = setup_model(cfg_path, root, gpu=0)
model.eval()
# GET DATA AND PROCESS IMAGE
data = np.load(os.path.join('..', 'test_set', 'cls1_rgb.npy'))
data = data[:, :, ::-1]
img = ImageLoad_cv2(data, WIDTH, HEIGHT, ENSEMBLE_N, True)
# MODEL FEED
predictions = predict(model, img, ENSEMBLE_N, gpu=0, is_silent=False)
return predictions, colors, names, idx_map
def prepare_idx_map(self):
self.idx_map = create_idx_group()
if __name__ == '__main__':
#Define the color dict
import matplotlib.pyplot as plt
WIDTH = 484
HEIGHT = 240
RESIZE_N = 2
IS_SILENT = True
colors = loadmat('data/color150.mat')['colors']
root = ''
names = {}
with open('data/object150_info.csv') as f:
reader = csv.reader(f)
next(reader)
for row in reader:
names[int(row[0])] = row[5].split(";")[0]
idx_map = create_idx_group()
colors, names = edit_colors_names_group(colors, names)
#take cls.npy as an example
data = np.load(os.path.join('test_set', 'cls1_rgb.npy'))
data = data[:, :, ::-1]
cfg_path = os.path.join('config',
'ade20k-mobilenetv2dilated-c1_deepsup.yaml')
#cfg_path="config/ade20k-resnet18dilated-ppm_deepsup.yaml"
model = setup_model(cfg_path, root, gpu=0)
model.eval()
for i in range(5):
torch.cuda.synchronize()
start = time.time()
img = ImageLoad_cv2(data, WIDTH, HEIGHT, RESIZE_N, is_silent=IS_SILENT)
predictions = predict(model, img, RESIZE_N, gpu=0, is_silent=IS_SILENT)