def main_UNet_II():
# TODO: Get through CLI arg
# Step 01: Get Input Resources and Model Configuration
parser = app_argparse()
args = parser.parse_args()
# print(args)
use_gpu = args.use_gpu
# tile_size = args.tile_size
tile_size = (200, 200)
INPUT_IMAGE_PATH = args.input_RGB
LABEL_IMAGE_PATH = args.input_GT
# WEIGHTS_FILE_PATH = args.output_model_path
WEIGHTS_FILE_PATH = "weights/Adam.UNet.weights.II.pt"
OUTPUT_IMAGE_PATH = args.output_images
# Step 02: Get Input Resources and Model Configuration
device = utils.device(use_gpu=use_gpu)
model = UNet()
# model = utils.load_weights_from_disk(model)
model = utils.load_entire_model(model, WEIGHTS_FILE_PATH, use_gpu)
print("use pretrained model!")
# print(model)
# summary(model, (3, tile_size[0], tile_size[1]))
# this is issue !!!
loader = dataset.full_image_loader(
INPUT_IMAGE_PATH, LABEL_IMAGE_PATH, tile_size=tile_size)
prediction = predict(model, loader, device=device,
class_label=ClassLabel.house)
# Step 03: save the output
input_image = utils.input_image(INPUT_IMAGE_PATH)
pred_image, mask_image = utils.overlay_class_prediction(
input_image, prediction)
pred_image_path = OUTPUT_IMAGE_PATH + "/prediction.png"
pred_image.save(pred_image_path)
pred_mask_path = OUTPUT_IMAGE_PATH + "/mask.png"
mask_image.save(pred_mask_path)
print("(i) Prediction and Mask image saved at {}".format(pred_image_path))
print("(ii) Mask image saved at {}".format(pred_mask_path))
# Step 04: Check the metrics
img_gt = np.array(Image.open(LABEL_IMAGE_PATH), dtype=np.int32)
img_mask = np.array(Image.open(pred_mask_path), dtype=np.int32)
metricComputation(img_gt, img_mask)
return torch.max(y_full, dim=1)[1]
if class_label == ClassLabel.house:
return torch.max(-y_full, dim=1)[1]
#TODO: Subclass error
raise ValueError('Unknown class label: {}'.format(class_label))
if __name__ == '__main__':
#TODO: Get through CLI arg
use_gpu = False
tile_size = (256, 256)
device = utils.device(use_gpu=use_gpu)
model = UNet()
model = utils.load_weights_from_disk(model)
input_image = utils.input_image()
loader = dataset.full_image_loader(tile_size=tile_size, img_path="images/img/train1.jpg")
prediction = predict(model, loader, device=device,
class_label=ClassLabel.house)
pred_image = utils.overlay_class_prediction(input_image, prediction)
pred_image_path = './images/output/prediction.png'
pred_image.save(pred_image_path)
print('(i) Prediction image saved at {}'.format(pred_image_path))
args = parser.parse_args()
print(args)
use_gpu = args.use_gpu
INPUT_IMAGE_PATH = args.input_RGB
LABEL_IMAGE_PATH = args.input_GT
WEIGHTS_FILE_PATH = args.output_model_path
# Step 1: TensorBoard setup
# default `log_dir` is "runs" - we'll be more specific here
writer = SummaryWriter("runs/aerial_image_segmentation")
# Step 2: Writing to TensorBoard
# get some random training images
tile_size = (250, 250)
loader = dataset.full_image_loader(INPUT_IMAGE_PATH,
LABEL_IMAGE_PATH,
tile_size=tile_size)
# dataiter = iter(loader)
# images, labels = dataiter.next()
images_RGB = torch.tensor(np.zeros((16, 3, 250, 250)))
images_GT = torch.tensor(np.zeros((16, 1, 250, 250)))
i = 0
for x, y in loader:
# print(x.shape, y.shape)
images_RGB[i, :, :, :] = x
images_GT[i, :, :, :] = y
i = i + 1
# # create grid of images
if class_label == ClassLabel.house:
return torch.max(-y_full, dim=1)[1]
#TODO: Subclass error
raise ValueError('Unknown class label: {}'.format(class_label))
if __name__ == '__main__':
#TODO: Get through CLI arg
use_gpu = False
tile_size = (256, 256)
device = utils.device(use_gpu=use_gpu)
model = FCNN()
model = utils.load_weights_from_disk(model)
loader = dataset.full_image_loader(tile_size=tile_size)
prediction = predict(model, loader, device=device,
class_label=ClassLabel.house)
input_image = utils.input_image()
pred_image = utils.overlay_class_prediction(input_image, prediction)
pred_image_path = './images/output/prediction.png'
pred_image.save(pred_image_path)
print('(i) Prediction image saved at {}'.format(pred_image_path))
def dev_predit(args):
use_gpu = args.use_gpu
tile_size = tile_size = (args.tile_size_height, args.tile_size_width)
INPUT_IMAGE_PATH = args.input_RGB
LABEL_IMAGE_PATH = args.input_GT
WEIGHTS_FILE_PATH = args.output_model_path
LOSS_PLOT_PATH = args.output_loss_plot
OUTPUT_IMAGE_PATH = args.output_images
# Step 02: Get Input Resources and Model Configuration
device = utils.device(use_gpu=use_gpu)
model = FCNN()
# model = utils.load_weights_from_disk(model)
model = utils.load_entire_model(model, WEIGHTS_FILE_PATH, use_gpu)
# print(model)
# summary(model, (3, tile_size[0], tile_size[1]))
# this is issue !!!
loader = dataset.full_image_loader(INPUT_IMAGE_PATH,
LABEL_IMAGE_PATH,
tile_size=tile_size)
prediction = predict(model,
loader,
device=device,
class_label=utils.ClassLabel.house)
# Step 03: save the output
input_image = utils.input_image(INPUT_IMAGE_PATH)
pred_image, mask_image = utils.overlay_class_prediction(
input_image, prediction)
pred_image_path = OUTPUT_IMAGE_PATH + "/prediction.png"
pred_image.save(pred_image_path)
pred_mask_path = OUTPUT_IMAGE_PATH + "/mask.png"
mask_image.save(pred_mask_path)
print("(i) Prediction and Mask image saved at {}".format(pred_image_path))
print("(ii) Prediction and Mask image saved at {}".format(pred_mask_path))
# Show Metrics Computation
img_gt = np.array(Image.open(LABEL_IMAGE_PATH), dtype=np.int32)
img_mask = np.array(Image.open(pred_mask_path), dtype=np.int32)
metricComputation(img_gt, img_mask)
# show images
img_rgb = cv.imread(INPUT_IMAGE_PATH)
img_gt = cv.imread(LABEL_IMAGE_PATH)
img_pred = cv.imread(pred_mask_path) # pred_image_path
img_lost = cv.imread(LOSS_PLOT_PATH)
images = [img_rgb, img_gt, img_pred, img_lost]
titles = ["RGB", "GT", "Prediction", "Training Loss"]
plt.figure(num=None, figsize=(7, 7), dpi=80, facecolor="w", edgecolor="k")
for i in range(4):
plt.subplot(2, 2, i + 1), plt.imshow(images[i],
"gray",
vmin=0,
vmax=255)
plt.title(titles[i])
plt.xticks([]), plt.yticks([])
plt.show()
return pred_image_path, pred_mask_path