def plot_contours(roi_array: np.ndarray,
template: np.ndarray,
fig: plt.figure = None,
ax: plt.axis = None):
"""Plot contours of roi.
Args:
roi_array (numpy.ndarray): Array of roi masks.
template (numpy.ndarray): Template image.
fig (matplotlib.pyplot.figure, optional): Defaults to None. Figure to plot to.
ax (matplotlib.pyplot.axis, optional): Defaults to None. Axis to plot to.
"""
if fig is None and ax is None:
fig = plt.figure()
ax = fig.add_subplot(111)
elif ax is None and fig is not None:
ax = fig.add_subplot(111)
z, _, _ = roi_array.shape
np.random.seed(128)
colors = np.random.rand(3, z)
for idx, img_slice in enumerate(roi_array):
clean_border = segmentation.clear_border(img_slice).astype(np.int)
template = segmentation.mark_boundaries(template,
clean_border,
color=colors[:, idx],
mode='thick')
ax.imshow(template)
def display_overlay(rgb_image: np.ndarray, binary_mask: np.ndarray, ax: plt.axis, check_mask=False):
"""
Display version of RGB_image where `False` values in binary_mask are darkened.
:param rgb_image:
:param binary_mask:
:param ax:
:param check_mask:
:return:
"""
if check_mask and binary_mask.dtype is not bool:
warn("`binary_mask` is non-boolean, attempting conversion.")
binary_mask = binary_mask.astype(bool)
overlay = rgb_image.copy()
overlay[~binary_mask] = overlay[~binary_mask] // 2 # Darken the color of the original image where mask is False
ax.imshow(overlay)
def draw_model_prediction(fig: plt.figure,
ax: plt.axis,
model: nn.Module,
gw: int = 0,
min_point: (float, float) = (0, 0),
max_point: (float, float) = (500, 500),
resolution: float = 1,
apply_ploss: bool = True,
colorbar: bool = True,
detection_flag: bool = False,
detection_threshold: float = -140,
device='cpu',
*args,
**kwargs):
x_mesh, y_mesh = np.mgrid[min_point[0]:max_point[0]:resolution,
min_point[1]:max_point[1]:resolution]
x = x_mesh.ravel()
y = y_mesh.ravel()
data_x = np.stack([x, y], axis=1).astype(np.float32)
if detection_flag is False:
z = model(torch.from_numpy(data_x).to(device),
apply_ploss).detach()[:, gw, 0].cpu().numpy()
else:
#z = model(torch.from_numpy(data_x).to(device), apply_ploss).detach()[:, gw, 0].cpu().numpy()
z = model(torch.from_numpy(data_x).to(device),
apply_ploss).detach()[:, gw, :].cpu().numpy()
sub_z1 = z[:, 1]
sub_z = z[:, 0]
sub_z[sub_z1 < 0.9] = detection_threshold
z = z[:, 0]
z = z.reshape((int(max_point[0] - min_point[0]),
int(max_point[1] - min_point[1]))).transpose()
z[z < detection_threshold] = detection_threshold
im = ax.imshow(z, norm=colors.PowerNorm(gamma=2))
if colorbar:
divider = make_axes_locatable(ax)
cax = divider.append_axes('right', size='5%', pad=0.05)
fig.colorbar(im, cax=cax, orientation='vertical', label='dBm')
return im
