def generate_3d_example():
n_gaussians = 1
variance = np.square(1.0 / n_gaussians)
gmm = utils.get_grid_gmm(
subdivisions=[n_gaussians, n_gaussians, n_gaussians],
variance=variance)
# points = np.array([[[0, 0, 0]]])
points = get_3d_spiral()
fig_images = []
for i, point in enumerate(points):
if point.ndim == 1:
point = np.expand_dims(point, axis=0)
pc_3dmfv = utils.get_3DmFV(point,
gmm.weights_,
gmm.means_,
gmm.covariances_,
normalize=True)
fig_image = visualization.visualzie_3dmfv_gaussian_and_points(
gmm,
point,
pc_3dmfv[0, :, :],
display=False,
export=False,
export_path=OUTPUT_PATH + '/fv_3d' + str(i) + '.png')
fig_images.append(fig_image)
imageio.mimsave(OUTPUT_PATH + '/3d_fv.gif', fig_images)
def generate_3d_example_2():
n_gaussians = 2
variance = np.square(1.0/n_gaussians)
gmm = utils.get_grid_gmm(subdivisions=[n_gaussians, n_gaussians, n_gaussians], variance=variance)
points = utils.load_point_cloud_from_txt('car_130.txt')
points = np.expand_dims(points, axis=0)
pc_3dmfv = utils.get_3DmFV(points, gmm.weights_, gmm.means_, gmm.covariances_, normalize=True)
fig_image = visualization.visualize_3dmfv_gaussian_and_points(gmm, np.squeeze(points), pc_3dmfv[0, :, :], display=False,
export=True,
export_path=OUTPUT_PATH + '/fv_3d_model' + '.png')
def main():
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.append(BASE_DIR + '/visualization')
log_dir = 'log_fisher_grid5_nonlinear'
#Load gaussians
# gmm_filename = os.path.join(log_dir,'gmm.p')
# gmm = pickle.load(open(gmm_filename, "rb"))
# parameters_filename = os.path.join(log_dir,'parameters.p')
# PARAMETERS = pickle.load(open(parameters_filename, "rb"))
#Create new gaussian
subdev = 10
variance = 0.01
gmm = utils.get_grid_gmm(subdivisions=[subdev, subdev, subdev],
variance=variance)
class helper_struct():
def __init__(self):
self.num_gaussians = subdev
self.gmm_type = 'grid'
PARAMETERS = helper_struct()
gaussian_index = 740
num_points = 1024
model_idx = 0
n_gaussians = np.power(
PARAMETERS.num_gaussians,
3) if PARAMETERS.gmm_type == 'grid' else PARAMETERS.num_gaussians
points, _ = provider.load_single_model(model_idx=model_idx,
test_train='train',
file_idxs=0,
num_points=num_points)
g_pts, g_probs = utils.get_gaussian_points(points,
gmm,
idx=gaussian_index,
thresh=0.01)
#draw_gaussian_points(points, g_pts, gmm, idx=gaussian_index, ax=None, display=True, color_val=g_probs)
#fv = utils.fisher_vector(points, gmm, normalization=True)
# d_pi = fv[0:n_gaussians]
# mean_d_pi = 0.02
# ax=draw_point_cloud(points)
# draw_gaussians(gmm, ax=ax, display=True, mappables=d_pi, thresh=mean_d_pi)
per_point_dpi, per_point_d_mu, per_point_d_sigma = utils.fisher_vector_per_point(
points, gmm)
visualize_derivatives(points, gmm, gaussian_index, per_point_dpi,
per_point_d_mu, per_point_d_sigma)
def visualize_fv_pc_clas():
num_points = 1024
n_classes = 40
clas = 'person'
#Create new gaussian
subdev = 5
variance = 0.04
export = False
display = True
exp_path = '/home/itzikbs/PycharmProjects/fisherpointnet/paper_images/'
shape_names = provider.getDataFiles( \
os.path.join(BASE_DIR, 'data/modelnet' + str(n_classes) + '_ply_hdf5_2048/shape_names.txt'))
shape_dict = {shape_names[i]: i for i in range(len(shape_names))}
gmm = utils.get_grid_gmm(subdivisions=[subdev, subdev, subdev], variance=variance)
# compute fv
w = tf.constant(gmm.weights_, dtype=tf.float32)
mu = tf.constant(gmm.means_, dtype=tf.float32)
sigma = tf.constant(gmm.covariances_, dtype=tf.float32)
for clas in shape_dict:
points = provider.load_single_model_class(clas=clas, ind=0, test_train='train', file_idxs=0, num_points=1024,
n_classes=n_classes)
points = np.expand_dims(points,0)
points_tensor = tf.constant(points, dtype=tf.float32) # convert points into a tensor
fv_tensor = tf_util.get_fv_minmax(points_tensor, w, mu, sigma, flatten=False)
sess = tf_util.get_session(2)
with sess:
fv = fv_tensor.eval()
#
# visualize_single_fv_with_pc(fv_train, points, label_title=clas,
# fig_title='fv_pc', type='paper', pos=[750, 800, 0, 0], export=export,
# filename=BASE_DIR + '/paper_images/fv_pc_' + clas)
visualize_fv(fv, gmm, label_title=[clas], max_n_images=5, normalization=True, export=export, display=display,
filename=exp_path + clas+'_fv', n_scales=1, type='none', fig_title='Figure')
visualize_pc(points, label_title=clas, fig_title='figure', export=export, filename=exp_path +clas+'_pc')
plt.close('all')