def gpu_prediction_sample(args):
in_files = args.input
net = UNet(n_channels=3, n_classes=1)
print("Loading model {}".format(args.model))
print("Using CUDA version of the net, prepare your GPU !")
net.cuda()
net.load_state_dict(torch.load(args.model))
print("Model loaded !")
for i, fn in enumerate(in_files):
print("\nPredicting image {} ...".format(fn))
img = Image.open(fn)
if img.size[0] < img.size[1]:
print("Error: image height larger than the width")
mask = predict_img(net=net,
full_img=img,
scale_factor=args.scale,
out_threshold=args.mask_threshold,
use_dense_crf=not args.no_crf,
use_gpu=not args.cpu)
print("Visualizing results for image {}, close to continue ...".format(
fn))
plot_img_and_mask(img, mask)
def main(raw_args):
args = get_args(raw_args)
args.model = '/home/zhaojin/data/TacomaBridge/segdata/train/checkpoint/logloss_softmax/CP12.pth'
in_files = ['/home/zhaojin/data/TacomaBridge/segdata/train/img/00034.png']
out_files = ['/home/zhaojin/my_path/dir/segdata/predict/00025.png']
net = UNet(n_channels=1, n_classes=4)
print("Loading model {}".format(args.model))
if not args.cpu:
print("Using CUDA version of the net, prepare your GPU !")
net.cuda()
net.load_state_dict(torch.load(args.model))
else:
net.cpu()
net.load_state_dict(torch.load(args.model, map_location='cpu'))
print("Using CPU version of the net, this may be very slow")
print("Model loaded !")
for i, fn in enumerate(in_files):
print("\nPredicting image {} ...".format(fn))
img = Image.open(fn)
if img.size[0] < img.size[1]:
print("Error: image height larger than the width")
mask = predict_img(net=net,
full_img=img,
scale_factor=args.scale,
out_threshold=args.mask_threshold,
use_dense_crf=not args.no_crf,
use_gpu=not args.cpu)
if args.viz:
print("Visualizing results for image {}, close to continue ...".
format(fn))
plot_img_and_mask(img, mask)
# if not args.no_save:
# out_fn = out_files[i]
# print('mask', mask)
# result = mask_to_image(mask)
#
# result.save(out_files[i])
#
# print("Mask saved to {}".format(out_files[i]))
return mask
def prediction(args):
in_files = args.input
out_files = get_output_filenames(args)
net = UNet(n_channels=3, n_classes=1)
print("Loading model {}".format(args.model))
if not args.cpu:
print("Using CUDA version of the net, prepare your GPU !")
net.cuda()
net.load_state_dict(torch.load(args.model))
else:
net.cpu()
net.load_state_dict(torch.load(args.model, map_location='cpu'))
print("Using CPU version of the net, this may be very slow")
print("Model loaded !")
for i, fn in enumerate(in_files):
print("\nPredicting image {} ...".format(fn))
img = Image.open(fn)
if img.size[0] < img.size[1]:
print("Error: image height larger than the width")
mask = predict_img(net=net,
full_img=img,
scale_factor=args.scale,
out_threshold=args.mask_threshold,
use_dense_crf=not args.no_crf,
use_gpu=not args.cpu)
if args.viz:
print("Visualizing results for image {}, close to continue ...".
format(fn))
plot_img_and_mask(img, mask)
if not args.no_save:
out_fn = out_files[i]
result = mask_to_image(mask)
result.save(out_files[i])
print("Mask saved to {}".format(out_files[i]))
def main(raw_args=None):
"""example: python predict.py --model '/home/zhaojin/data/TacomaBridge/segdata/train/checkpoint/weight_logloss_softmax/CP30.pth' --input '/home/zhaojin/data/TacomaBridge/segdata/train/img/00034.png' --viz"""
args = get_args(raw_args)
print('args', args)
# args.model = '/home/zhaojin/data/TacomaBridge/segdata/train/checkpoint/logloss_softmax/CP12.pth'
# in_files = ['/home/zhaojin/data/TacomaBridge/segdata/train/img/00034.png' ]
# out_files = ['/home/zhaojin/my_path/dir/segdata/predict/00025.png']
in_files = args.input
net = UNet(n_channels=1, n_classes=4)
print("Loading model {}".format(args.model))
if not args.cpu:
print("Using CUDA version of the net, prepare your GPU !")
net.cuda()
net.load_state_dict(torch.load(args.model))
else:
net.cpu()
net.load_state_dict(torch.load(args.model, map_location='cpu'))
print("Using CPU version of the net, this may be very slow")
print("Model loaded !")
for i, fn in enumerate(in_files):
print("\nPredicting image {} ...".format(fn))
img = Image.open(fn)
if img.size[0] < img.size[1]:
print("Error: image height larger than the width")
mask = predict_img(net=net,
full_img=img,
scale_factor=args.scale,
out_threshold=args.mask_threshold,
use_dense_crf=not args.no_crf,
use_gpu=not args.cpu)
if args.viz:
print("Visualizing results for image {}, close to continue ...".
format(fn))
mask = np.transpose(mask, axes=[1, 2, 0])
plot_img_and_mask(img, mask)
print("Model loaded !")
for i, fn in enumerate(in_files):
print("\nPredicting image {} ...".format(fn))
images, patient_number, frame_indices, rotated, true_masks = load_patient_images(fn)
# if img.size[0] < img.size[1]:
# print("Error: image height larger than the width")
predictions = []
for i, image in enumerate(images):
image = torch.FloatTensor(image)
image = image.cuda()
mask_pred = net(image[None, :, :, :]) # feed one at a time
predictions.append((image[:, :, 0], mask_pred[0, :, :, 1]))
# mask = predict_img(net=net,
# full_img=img,
# scale_factor=args.scale,
# out_threshold=args.mask_threshold,
# use_dense_crf=not args.no_crf,
# use_gpu=not args.cpu)
if args.viz:
print("Visualizing results for image {}, close to continue ...".format(fn))
image = image[0]
mask_pred = mask_pred[0][0]
plot_img_and_mask(image, mask_pred, true_masks[i])
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
logging.info(f'Using device {device}')
net.to(device=device)
net.load_state_dict(torch.load(args.model, map_location=device))
logging.info("Model loaded !")
for i, fn in enumerate(in_files):
logging.info("\nPredicting image {} ...".format(fn))
img = Image.open(fn)
mask = predict_img(net=net,
full_img=img,
scale_factor=args.scale,
out_threshold=args.mask_threshold,
use_dense_crf=False,
device=device)
if not args.no_save:
out_fn = out_files[i]
result = mask_to_image(mask)
result.save(out_files[i])
logging.info("Mask saved to {}".format(out_files[i]))
if args.viz:
logging.info("Visualizing results for image {}, close to continue ...".format(fn))
plot_img_and_mask(img, mask)
default=True)
parser.add_argument('--no-save',
'-n',
action='store_true',
help="Do not save the output masks",
default=True)
return parser.parse_args()
if __name__ == "__main__":
args = get_args()
in_files = args.input
out_files = args.output
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
input_img = Image.open(in_files[0])
# print(input_img)
net = ResUNetA(3, 1)
net.to(device=device)
# print(args.model)
load = torch.load(args.model, map_location=device)
# print(load.keys())
net.load_state_dict(load['netG'])
mask = predict_mask(net, input_img, device)
plot_img_and_mask(input_img, mask)
print("Model loaded !")
for i, fn in enumerate(in_files):
print("\nPredicting image {} ...".format(fn))
#img = Image.open(fn)
img = cv2.imread(fn)
img = Image.fromarray(img)
mask_v, mask_h = predict_img(net=net,
full_img=img,
use_gpu=not args.cpu)
if args.viz:
print("Visualizing results for image {}, close to continue ...".
format(fn))
plot_img_and_mask(img, mask_v)
if not args.no_save:
mask_v = mask_v.numpy()
# mask_v=np.where(mask_v==1,mask_v, 0)
# print(mask_v)
result_v = mask_to_image(mask_v)
result_v.save(out_files_v[i])
mask_h = mask_h.numpy()
# mask_h=np.where(mask_h==1,mask_h,0)
result_h = mask_to_image(mask_h)
result_h.save(out_files_h[i])
print("Mask saved to {}".format(out_files_v[i]))
print("Mask saved to {}".format(out_files_h[i]))
