def test(model, dataset, weights_filepath="weights_current.h5"):
model.load_weights(weights_filepath)
train_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_test_batches,
flatten_y=False)
batch_x, batch_y = train_iterator.next()
results_dir = 'results'
if not os.path.exists(results_dir):
os.mkdir(results_dir)
pred = model._predict(batch_x)
pred = pred.reshape(batch_size, patch_size, 1, patch_size, patch_size)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
for i in range(batch_size):
v, t = mcubes.marching_cubes(pred_as_b012c[i, :, :, :, 0], 0.5)
mcubes.export_mesh(v, t, results_dir + '/drill_' + str(i) + '.dae',
'drill')
viz.visualize_batch_x(pred, i, str(i), results_dir + "/pred_" + str(i))
viz.visualize_batch_x(batch_x, i, str(i),
results_dir + "/input_" + str(i))
viz.visualize_batch_x(batch_y, i, str(i),
results_dir + "/expected_" + str(i))
def export_mesh(model, dataset, upsample, mcubes_threshold=0.005):
res = 3 * (upsample * opt.res, )
model.octant_size = model.octant_size * upsample
print('Export: calculating occupancy...')
mrc_fname = os.path.join(opt.logging_root, opt.experiment_name,
f"{opt.experiment_name}.mrc")
occupancy = utils.write_occupancy_multiscale_summary(res,
dataset,
model,
None,
None,
None,
None,
None,
output_mrc=mrc_fname,
oversample=upsample,
mode='hq')
print('Export: running marching cubes...')
vertices, faces = mcubes.marching_cubes(occupancy, mcubes_threshold)
print('Export: exporting mesh...')
out_fname = os.path.join(opt.logging_root, opt.experiment_name,
f"{opt.experiment_name}.dae")
mcubes.export_mesh(vertices, faces, out_fname)
def make_isomesh(self, val, name="", update=False):
"""makes a mesh based off the marching cubes algorithm, for given volume data
Arguments:
val {float} -- value between 0 and 1 that determines where the mesh is drawn. Mesh is
an isosurface based off volumetric data. 0 takes the minimum value in the volume and
tries to make a surface on that value, 1 takes the maximum.
Keyword Arguments:
name {str} -- given name for isomesh (default: {""})
update {bool} -- update isomesh or not? (default: {False})
"""
if not name:
name = self.name + '.dae'
elif not name.endswith('.dae'):
name = name + '.dae'
ipath = self.check_file(name, update)
if ipath is None:
return
print('making isosurface...')
start = time.time()
field_max = np.amax(self.field.field)
field_min = np.amin(self.field.field)
isoval = val * (field_max - field_min) + field_min
vertices, triangles = mcubes.marching_cubes(self.field.field, isoval)
mcubes.export_mesh(vertices, triangles, ipath, "Iso{}".format(val))
end = time.time()
print('mesh created, time elapsed = {}s'.format(end - start))
def test(model, dataset, weights_filepath="weights_current.h5"):
model.load_weights(weights_filepath)
train_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_test_batches,
flatten_y=False)
batch_x, batch_y = train_iterator.next()
results_dir = 'results'
if not os.path.exists(results_dir):
os.mkdir(results_dir)
pred = model._predict(batch_x)
pred = pred.reshape(batch_size, patch_size, 1, patch_size, patch_size)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
for i in range(batch_size):
v, t = mcubes.marching_cubes(pred_as_b012c[i, :, :, :, 0], 0.5)
mcubes.export_mesh(v, t, results_dir + '/drill_' + str(i) + '.dae', 'drill')
viz.visualize_batch_x(pred, i, str(i), results_dir + "/pred_" + str(i))
viz.visualize_batch_x(batch_x, i, str(i), results_dir + "/input_" + str(i))
viz.visualize_batch_x(batch_y, i, str(i), results_dir + "/expected_" + str(i))
def on_tri_d_run_clicked(self):
"""
Slot documentation goes here.
"""
thickness = 1
liver = self.liver
liver_recon = np.zeros([thickness * liver.shape[0], 512, 512])
for i in range(liver.shape[0]):
for s in range(thickness):
liver_recon[(s + 1) * i + s] = liver[i]
vertices, triangles = mcubes.marching_cubes(liver_recon, 0)
mcubes.export_mesh(vertices, triangles, "liver.dae", "liver")
tumor = self.tumor
tumor_recon = np.zeros([thickness * tumor.shape[0], 512, 512])
for i in range(tumor.shape[0]):
for s in range(thickness):
tumor_recon[(s + 1) * i + s] = tumor[i]
vertices_2, triangles_2 = mcubes.marching_cubes(tumor_recon, 0)
mcubes.export_mesh(vertices_2, triangles_2, "tumor.dae", "tumor")
QMessageBox.information(self, "Warning",
"3D model exported successfully")
def test_interp(self, config):
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
interp_size = 8
idx1 = 0
idx2 = 2
batch_voxels1 = self.data_voxels[idx1:idx1+1]
batch_voxels2 = self.data_voxels[idx2:idx2+1]
model_z1 = self.sess.run(self.sE,
feed_dict={
self.vox3d: batch_voxels1,
})
model_z2 = self.sess.run(self.sE,
feed_dict={
self.vox3d: batch_voxels2,
})
batch_z = np.zeros([interp_size,self.z_dim], np.float32)
for i in range(interp_size):
batch_z[i] = model_z2*i/(interp_size-1) + model_z1*(interp_size-1-i)/(interp_size-1)
dima = self.test_size
dim = self.real_size
multiplier = int(dim/dima)
multiplier2 = multiplier*multiplier
for t in range(interp_size):
model_float = np.zeros([self.real_size+2,self.real_size+2,self.real_size+2],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
minib = i*multiplier2+j*multiplier+k
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector: batch_z[t:t+1],
self.point_coord: self.coords[minib],
})
model_float[self.aux_x+i+1,self.aux_y+j+1,self.aux_z+k+1] = np.reshape(model_out, [self.test_size,self.test_size,self.test_size])
img1 = np.clip(np.amax(model_float, axis=0)*256, 0,255).astype(np.uint8)
img2 = np.clip(np.amax(model_float, axis=1)*256, 0,255).astype(np.uint8)
img3 = np.clip(np.amax(model_float, axis=2)*256, 0,255).astype(np.uint8)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_1t.png",img1)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_2t.png",img2)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_3t.png",img3)
thres = 0.5
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(vertices, triangles, config.sample_dir+"/"+"out"+str(t)+".dae", str(t))
print("[sample interpolation]")
def test_z(self, config, batch_z, dim):
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
dima = self.test_size
multiplier = int(dim/dima)
multiplier2 = multiplier*multiplier
multiplier3 = multiplier*multiplier*multiplier
#get coords 256
aux_x = np.zeros([dima,dima,dima],np.int32)
aux_y = np.zeros([dima,dima,dima],np.int32)
aux_z = np.zeros([dima,dima,dima],np.int32)
for i in range(dima):
for j in range(dima):
for k in range(dima):
aux_x[i,j,k] = i*multiplier
aux_y[i,j,k] = j*multiplier
aux_z[i,j,k] = k*multiplier
coords = np.zeros([multiplier3,dima,dima,dima,3],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
coords[i*multiplier2+j*multiplier+k,:,:,:,0] = aux_x+i
coords[i*multiplier2+j*multiplier+k,:,:,:,1] = aux_y+j
coords[i*multiplier2+j*multiplier+k,:,:,:,2] = aux_z+k
coords = (coords+0.5)/dim*2.0-1.0
coords = np.reshape(coords,[multiplier3,self.batch_size,3])
for t in range(batch_z.shape[0]):
model_float = np.zeros([dim+2,dim+2,dim+2],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
print(t,i,j,k)
minib = i*multiplier2+j*multiplier+k
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector: batch_z[t:t+1],
self.point_coord: coords[minib],
})
model_float[aux_x+i+1,aux_y+j+1,aux_z+k+1] = np.reshape(model_out, [dima,dima,dima])
img1 = np.clip(np.amax(model_float, axis=0)*256, 0,255).astype(np.uint8)
img2 = np.clip(np.amax(model_float, axis=1)*256, 0,255).astype(np.uint8)
img3 = np.clip(np.amax(model_float, axis=2)*256, 0,255).astype(np.uint8)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_1t.png",img1)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_2t.png",img2)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_3t.png",img3)
thres = 0.5
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(vertices, triangles, config.sample_dir+"/"+"out"+str(t)+".dae", str(t))
print("[sample GAN]")
def test_export():
u = np.zeros((10, 10, 10))
u[2:-2, 2:-2, 2:-2] = 1.0
vertices, triangles = mcubes.marching_cubes(u, 0.5)
mcubes.export_obj(vertices, triangles, "output/test.obj")
mcubes.export_off(vertices, triangles, "output/test.off")
mcubes.export_mesh(vertices, triangles, "output/test.dae")
def sphere2():
# Create the volume
f = lambda x, y, z: x**2 + y**2 + z**2
# Extract the 16-isosurface
vertices, triangles = mcubes.marching_cubes_func((-10,-10,-10), (10,10,10),100, 100, 100, f, 16)
# Export the result to sphere2.dae
mcubes.export_mesh(vertices, triangles, "sphere2.dae", "MySphere")
def plotFromVoxels(voxels, title=''):
# print('plotfromvoxel')
voxel2obj(title + 'voxels.obj', voxels)
if len(voxels.shape) > 3:
x_d = voxels.shape[0]
y_d = voxels.shape[1]
z_d = voxels.shape[2]
v = voxels[:, :, :, 0]
v = np.reshape(v, (x_d, y_d, z_d))
else:
v = voxels
print(
"voxels_plot", v.shape
) ############################################### (32, 32, 32) ##################################
u = voxels
vertices, triangles = mcubes.marching_cubes(u, 0)
mcubes.export_mesh(vertices, triangles, title + "recon.dae",
"MySphere")
export_obj(vertices, triangles, title + 'recon.obj')
x, y, z = v.nonzero()
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(x, y, z, zdir='z', c='red')
ax.set_xlabel('X')
ax.set_ylabel('y')
ax.set_zlabel('z')
ax.set_aspect('equal')
ax.view_init(-90, 90)
max_range = np.array(
[x.max() - x.min(),
y.max() - y.min(),
z.max() - z.min()]).max()
print("max_range", max_range)
Xb = 0.5 * max_range * np.mgrid[
-1:2:2, -1:2:2, -1:2:2][0].flatten() + 0.5 * (x.max() + x.min())
Yb = 0.5 * max_range * np.mgrid[
-1:2:2, -1:2:2, -1:2:2][1].flatten() + 0.5 * (y.max() + y.min())
Zb = 0.5 * max_range * np.mgrid[
-1:2:2, -1:2:2, -1:2:2][2].flatten() + 0.5 * (z.max() + z.min())
# Comment or uncomment following both lines to test the fake bounding box:
for xb, yb, zb in zip(Xb, Yb, Zb):
ax.plot([xb], [yb], [zb], 'w')
plt.grid()
plt.show()
plt.title(title)
from matplotlib.pyplot import show
show(block=False)
def evaluate(dimX,dimY,dimZ):
vertices, triangles = mcubes.marching_cubes_func(
(boundingArea['minX'],boundingArea['minY'],boundingArea['minZ']),
(boundingArea['maxX'], boundingArea['maxY'], boundingArea['maxZ']), # Bounds
dimX, dimY, dimZ, # Number of samples in each dimension
implicit, # Implicit function
0) # Isosurface value
# Export the result to sphere2.dae
mcubes.export_mesh(vertices, triangles, "/Users/Emscape/Documents/Blender Projects/result.dae", "MLS result")
print("Done. Result saved in 'result.dae'.")
def export(vertices, triangles, object_name="MyShape", file_name="my_shape"):
t = time.time()
logging.info("exporting dae...")
# get untaken file_name
full_path = file_name + ".dae"
iterator = 2
while (os.path.isfile(full_path)):
full_path = file_name + str(iterator) + ".dae"
iterator += 1
mcubes.export_mesh(vertices, triangles, full_path, object_name)
logging.info("Done in %f seconds. Result saved in '%s'" % (time.time() - t, full_path))
def test(self, config):
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
dima = self.test_size
dim = self.real_size
multiplier = int(dim / dima)
multiplier2 = multiplier * multiplier
for t in range(self.data_voxels.shape[0]):
model_float = np.zeros(
[self.real_size + 2, self.real_size + 2, self.real_size + 2],
np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
minib = i * multiplier2 + j * multiplier + k
# batch_voxels = self.data_voxels[t:t+1]
batch_z_vector = self.z_vectors[t:t + 1]
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector:
batch_z_vector,
self.point_coord:
self.coords[minib],
})
model_float[self.aux_x + i + 1, self.aux_y + j + 1,
self.aux_z + k + 1] = np.reshape(
model_out, [
self.test_size, self.test_size,
self.test_size
])
img1 = np.clip(np.amax(model_float, axis=0) * 256, 0,
255).astype(np.uint8)
img2 = np.clip(np.amax(model_float, axis=1) * 256, 0,
255).astype(np.uint8)
img3 = np.clip(np.amax(model_float, axis=2) * 256, 0,
255).astype(np.uint8)
cv2.imwrite(config.sample_dir + "/" + str(t) + "_1t.png", img1)
cv2.imwrite(config.sample_dir + "/" + str(t) + "_2t.png", img2)
cv2.imwrite(config.sample_dir + "/" + str(t) + "_3t.png", img3)
thres = 0.5
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(
vertices, triangles,
config.sample_dir + "/" + "out" + str(t) + ".dae", str(t))
print("[sample]")
def ros_mesh_msg_to_daefile(mesh, dae_filepath):
import mcubes
vs = []
for vert in mesh.vertices:
vs.append((vert.x, vert.y, vert.z))
vertices = np.array(vs)
ts = []
for tri in mesh.triangles:
ts.append(tri.vertex_indices)
triangles = np.array(ts)
mcubes.export_mesh(vertices, triangles, dae_filepath, "model")
def torus():
size = 100
X, Y, Z = np.mgrid[:size, :size, :size]
r = size / 8
R = r * 2
u = ( (X-size/2)**2 + (Y-size/2)**2 + (Z-size/2)**2 + R**2 -r**2)**2 - 4*(R**2)*((X-size/2)**2 + (Y-size/2)**2)
# Extract the 0-isosurface
vertices, triangles = mcubes.marching_cubes(u, 0)
# Export the result to sphere.dae
mcubes.export_mesh(vertices, triangles, "torus1.dae", "MyTorus")
def __init__(self,segmentation, mtype="DAE"):
self.segmentation = segmentation
self.image = segmentation.dicomimage
threshold=segmentation.getThreshold()
if mtype.lower() == "collada" or mtype.lower() == "dae":
self.extention=".dae"
self.name = segmentation.name +"_" + mtype+ "_Tresh-" + threshold
self.vertices, self.triangles = mcubes.marching_cubes(self.segmentation.image_Threshold, 0)
mcubes.export_mesh(self.vertices, self.triangles, GlobalData.ModelPath + "/" +self.name + self.extention, self.name)
if mtype.lower() == "stl":
self.extention=".stl"
self.name = segmentation.name + "_" + mtype +"_Tresh-" + threshold
self.vertices, self.triangles = mcubes.marching_cubes(self.segmentation.image_Threshold, 0)
mcubes.export_mesh(self.vertices, self.triangles, GlobalData.ModelPath + "/" +self.name + self.extention, self.name)
daepath = GlobalData.ModelPath + "/" + self.name
self.name = daepath
def marching_cube(resolution, bounding_box, number_fo_anim):
u = np.load('leabels.npy')
print(u.shape)
# Extract the 0-isosurface
vertices, triangles = mcubes.marching_cubes(u, 0.1)
print(np.max(vertices[:, 2]))
print(bounding_box, resolution)
for i in range(vertices.shape[0]):
for j in range(3):
vertices[i, j] = vertices[i, j] / resolution * (bounding_box[
2 * j + 1] - bounding_box[2 * j]) + bounding_box[2 * j]
print(np.max(vertices[:, 1]))
mcubes.export_mesh(vertices, triangles,
"sphere_" + str(number_fo_anim) + ".dae", "MySphere")
return vertices
def execute_cb(self, goal):
rospy.loginfo("received new goal")
points = []
gen = pc2.read_points(goal.partial_cloud,
skip_nans=True,
field_names=("x", "y", "z"))
for p in gen:
points.append(p)
pc = np.array(points)
patch_size = 120
vox_resolution = get_voxel_resolution(pc, patch_size)
center = get_center(pc)
pc_center_in_voxel_grid = (patch_size * PERCENT_X,
patch_size * PERCENT_Y,
patch_size * PERCENT_Z)
voxel_grid = create_voxel_grid_around_point_scaled(
pc, center, vox_resolution, patch_size, pc_center_in_voxel_grid)
rospy.loginfo("about to run mcubes")
v, t = mcubes.marching_cubes(voxel_grid[:, :, :, 0], 0.5)
v = rescale_mesh(v, center, vox_resolution, pc_center_in_voxel_grid)
unsmoothed_handle, unsmoothed_filename = tempfile.mkstemp(
suffix=".dae")
smoothed_handle, smoothed_filename = tempfile.mkstemp(suffix=".ply")
mcubes.export_mesh(v, t, unsmoothed_filename, "model")
cmd_str = "meshlabserver -i " + unsmoothed_filename + " -o " + smoothed_filename + " -s " + str(
self.mlx_script_filepath)
subprocess.call(cmd_str.split())
mesh = mesh_conversions.read_mesh_msg_from_ply_filepath(
smoothed_filename)
if os.path.exists(unsmoothed_filename):
os.remove(unsmoothed_filename)
if os.path.exists(smoothed_filename):
os.remove(smoothed_filename)
self._result.mesh = mesh
rospy.loginfo('Succeeded')
self._as.set_succeeded(self._result)
def export_dae(filename, cutout, level=0):
"""
Converts a dense annotation to a DAE, using Marching Cubes (PyMCubes).
Arguments:
filename (str): The filename to write out to
cutout (numpy.ndarray): The dense annotation
level (int): The level at which to run mcubes
Returns:
boolean success
"""
if ".dae" not in filename:
filename = filename + ".dae"
vs, fs = mcubes.marching_cubes(cutout, level)
mcubes.export_mesh(vs, fs, filename, "ndioexport")
def plan():
# Create a data volume (30 x 30 x 30)
X, Y, Z = np.mgrid[:50, :50, :50]
u = (3*X) + (2*Y) + (1*Z)
# Extract the 0-isosurface
vertices, triangles = mcubes.marching_cubes(u, 0)
print vertices.shape
print triangles.shape
#for t in vertices:
# print t
# Export the result to sphere.dae
mcubes.export_mesh(vertices, triangles, "plan.dae", "MyPlane")
def sphere1():
# Create a data volume (30 x 30 x 30)
X, Y, Z = np.mgrid[:50, :50, :50]
u = (X-25)**2 + (Y-25)**2 + (Z-25)**2 - 20**2
# Extract the 0-isosurface
vertices, triangles = mcubes.marching_cubes(u, 0)
print vertices.shape
print triangles.shape
#for t in vertices:
# print t
# Export the result to sphere.dae
mcubes.export_mesh(vertices, triangles, "sphere3.dae", "MySphere")
def remesh_binvox_model(model_dir, model_name, results_dir):
with open(model_dir + model_name + '.binvox', 'rb') as f:
model = binvox_rw.read_as_3d_array(f)
points = model.data
binvox_scale = model.scale
binvox_offset = model.translate
dims = model.dims
binvox_offset = np.array(binvox_offset).reshape(1, 3)
num_voxels_per_dim = max(dims)
voxel_grid = np.zeros((num_voxels_per_dim + 2, num_voxels_per_dim + 2,
num_voxels_per_dim + 2))
voxel_grid[1:num_voxels_per_dim + 1, 1:num_voxels_per_dim + 1,
1:num_voxels_per_dim + 1] = points
v, t = mcubes.marching_cubes(voxel_grid, 0.5)
v = v * binvox_scale / num_voxels_per_dim + binvox_offset
mcubes.export_mesh(v, t, results_dir + model_name + '.dae', model_name)
def test(model, dataset, weights_filepath=BEST_WEIGHT_FILE):
abs_weights_filepath = '/home/jvarley/3d_conv/keras/examples/' + weights_filepath
model.load_weights(abs_weights_filepath)
train_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_test_batches,
flatten_y=False)
batch_x, batch_y = train_iterator.next()
results_dir = DATA_DIR + 'results'
if not os.path.exists(results_dir):
os.makedirs(results_dir)
pred = model._predict(batch_x)
pred = pred.reshape(batch_size, patch_size, 1, patch_size, patch_size)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
for i in range(batch_size):
v, t = mcubes.marching_cubes(pred_as_b012c[i, :, :, :, 0], 0.5)
mcubes.export_mesh(v, t, results_dir + '/toilet_' + str(i) + '.dae', 'drill')
viz.visualize_batch_x(pred, i, str(i), results_dir + "/pred_" + str(i))
viz.visualize_batch_x(batch_x, i, str(i), results_dir + "/input_" + str(i))
viz.visualize_batch_x(batch_y, i, str(i), results_dir + "/expected_" + str(i))
# for i in range(batch_size):
# viz.visualize_batch_x_y_overlay(batch_x, batch_y, pred, i=i, title=str(i))
# viz.visualize_batch_x(pred, i, 'pred_' + str(i), )
# viz.visualize_batch_x(batch_x, i,'batch_x_' + str(i), )
# viz.visualize_batch_x(batch_y, i, 'batch_y_' + str(i), )
import IPython
IPython.embed()
#!/usr/bin/env python import numpy as np import mcubes from generate_voxels import voxelize_mesh # Shows simple marching cubes using PyMCubes mesh_file = '/home/markvandermerwe/YCB/ycb_meshes/002_master_chef_can.stl' voxels = voxelize_mesh(mesh_file, np.eye(4), 0.1, True) vertices, triangles = mcubes.marching_cubes(voxels, 0) mcubes.export_mesh(vertices, triangles, 'test.dae', 'test')
def main(context):
#1. Dimension of bounding box of object (USED TO SAMPLE 3D GRID) #
################################################## #
#1. HERE THE BOUNDARIES OF THE OBJECT ARE COMPUTED ---
name = context.active_object.data.name
xDimensionsHalve = bpy.data.objects[name].dimensions.x/2
xMin = 0 - xDimensionsHalve
xMax = 0 + xDimensionsHalve
yDimensionsHalve = bpy.data.objects[name].dimensions.y/2
yMin = 0 - yDimensionsHalve
yMax = 0 + yDimensionsHalve
zDimensionsHalve = bpy.data.objects[name].dimensions.z/2
zMin = 0 - zDimensionsHalve
zMax = 0 + zDimensionsHalve
#2. COMPUTE MLS FUNCTION ########################## #
################################################## #
#0. Define Help functions:
#
#Wendland weight function
def Wendland ( r , h ):
return (1 - r/h)**4*(4*r/h+1)
#b^T for degree 0, 1 or 2.
def ChooseB (degree, point):
x = point[0]
y = point[1]
z = point[2]
if degree == 0:
A = np.matrix([[1]])
elif degree == 1:
A = np.matrix([[1], [x], [y], [z], [x*y], [x*z], [y*z], [x*y*z]])
elif degree == 2:
A = np.matrix([[1], [x], [y], [z], [x**2], [y**2], [z**2], [x*y], [x*z], [y*z], [x**2*y], [x**2*z], [x*y**2], [x*z**2], [y**2*z], [y*z**2], [x*y*z], [x**2*y*z], [x*y**2*z], [x*y*z**2], [x**2*y**2], [x**2*z**2], [y**2*z**2], [x**2*y**2*z], [x**2*y*z**2], [x*y**2*z**2], [x**2*y**2*z**2]])
return np.transpose(A)
#Checks whether a point P is within a range of the given point C
#which in 3D means is within the sphere with C as its center and the specified
#, range as its radius
def insideSphere(C, R, P):
return ( P[0]- C[0] ) ** 2 + (P[1]- C[1]) ** 2 + (P[2]-C[2]) ** 2 < R**2
#Gets the appropriate length that matches to a degree k
def matchingLengthofDegreeK(k):
if k == 0:
l = 1
elif k == 1:
l = 8
elif k == 2:
l = 27
return l
#Can be used for visualization purposes
def makeMaterial(name, diffuse, specular, alpha):
mat = bpy.data.materials.new(name)
mat.diffuse_color = diffuse
mat.diffuse_shader = 'LAMBERT'
mat.diffuse_intensity = 1.0
return mat
def setMaterial(ob, mat):
me = ob.data
me.materials.append(mat)
#1. SETUP EPSILON, POINTCLOUD POINTS (FIRST n POINTS), POINTCLOUD POINT NORMALS and N (NECESSARY VARIABLES FOR COMPUTING CONSTRAINT POINTS), POINTCLOUD CENTER ---
#
#Computes N (amount of points in pointCloud)
PointCloud_points = []
PointCloud_points = context.active_object.data.vertices
N = len(PointCloud_points )
#Computes Normals of point cloud points
PointCloud_point_normals = []
for n in context.active_object['vertex_normal_list']:
PointCloud_point_normals.append(np.array([n[0], n[1], n[2]]))
#Fixes an ε value, for instance ε = 0.01 times the diagonal of the bounding box to the object. EXPERIMENTABLE PARAMETER
v1 = np.array((xMin, yMin,zMax))
v2 = np.array((xMax, yMax,zMin))
diagonalOfBoundingBox = np.linalg.norm(v1-v2)
epsilon = 0.01 * diagonalOfBoundingBox
#2. IMPLEMENT SPATIAL INDEX: KD-TREE ---
#
#Computes a Spatial Index: KD-TREE from the PointCloud_points
#(for faster nearest neighborhood calculations)
kd = mathutils.kdtree.KDTree(N)
for index, point in enumerate(PointCloud_points):
kd.insert(point.co, index)
#Must have been called before using any of the kd.find methods.
kd.balance()
#Compute the origin of the axis aligned bounding box
origin = mathutils.Vector((0,0,0))
for index, point in enumerate(PointCloud_points):
origin += point.co
origin /= N
polyDegree = 0
def MLS(x , y ,z):
P = np.array([x , y, z])
#Get closest points Pi within wendland radius from P. EXPERIMENTABLE PARAMETER
wendlandRadius = diagonalOfBoundingBox/20
pointsWithinRange = kd.find_range(P, wendlandRadius)
numpyPointsWithinRange = []
redPoints = []
redPointsEpsilonValues = []
greenPoints = []
greenPointsEpsilonValues = []
for (co,index, dist) in pointsWithinRange:
Ni = PointCloud_point_normals[index]
pos = co
PiNumpy = np.array((pos[0], pos[1], pos[2]))
epsilonBackup = epsilon
result = PiNumpy + epsilonBackup*Ni
#Range to look for closest points from Pi+N. EXPERIMENTABLE PARAMETER
Range = diagonalOfBoundingBox/20
Pi_Not_Closest = True
#Change datatype of Pi, to make computations easier
Pi = pos
#Check whether Pi is the closest point to Pi+N
while Pi_Not_Closest :
#Calculates distances between Pi+N = result and the points that are within a range distance from Pi+N
dist, closestPos = min([(np.linalg.norm(result - co), co) for (co,index, dist) in kd.find_range(result, Range)])
#If Pi is not the closest point to Pi+N,
# divide ε by 2 and recompute pi+N until this is the case
if closestPos != Pi:
epsilonBackup /= 2
result = Pi + epsilonBackup * Ni
else:
Pi_Not_Closest = False
break
#check whether the green and red point are within wendlandRadius of P
if insideSphere(C = P, R = wendlandRadius, P = result - 2*(epsilonBackup * Ni)):
greenPoints.append(result - 2*(epsilonBackup * Ni))
greenPointsEpsilonValues.append(- epsilonBackup)
if insideSphere(C = P, R = wendlandRadius ,P = result):
redPoints.append((result))
redPointsEpsilonValues.append(epsilonBackup)
numpyPointsWithinRange.append(PiNumpy)
#Create lists of the Pi's and Di's belonging to P
PointsPi = numpyPointsWithinRange + redPoints + greenPoints
PointsDi = [0]*len(pointsWithinRange) + redPointsEpsilonValues + greenPointsEpsilonValues
#sqrt(ti) = sqrt(theta(|P-Pi|)) (see MLS reference sheet: http://www.cs.uu.nl/docs/vakken/ddm/MLS%20Reference%20Sheet.pdf)
sqrtTiValues = []
#smoothing value for wendland weight function. EXPERIMENTABLE PARAMETER
h = 1
for Pi in PointsPi:
value = np.sqrt(Wendland(np.linalg.norm(P-Pi), h))
sqrtTiValues.append(value)
# A is a one-column matrix filled by sqrtTi multiplied with b^T
A = np.empty((0,matchingLengthofDegreeK(polyDegree)))
for index, sqrtTi in enumerate(sqrtTiValues):
#Here we choose B for a degree 0, 1 or 2. EXPERIMENTABLE PARAMETER
bT = ChooseB(polyDegree, PointsPi[index])
value = sqrtTi*bT
A = np.insert(A, index, value, 0)
# r = sqrtTi_x_Di
r = np.empty((0, len(sqrtTiValues)))
for index, sqrtTi in enumerate(sqrtTiValues):
r = np.insert(r, index, sqrtTi * PointsDi[index])
if(len(A) != 0):
A_T = np.transpose(A)
A_T_x_A = np.dot(A_T, A)
A_T_x_r = np.dot(A_T, r)
#a = (A^T*A)^-1 * A^T*r
a = np.dot(np.linalg.inv(A_T_x_A), A_T_x_r)
#Finally add a to the samples
return np.dot(ChooseB(polyDegree, [x,y,z]), a)
else:
return 10000
def f(x, y, z):
return MLS(x, y, z)
#4. INPUTS SAMPLED GRID TO MARCHING CUBES PLUGIN ---
#
lowerLeft = origin - mathutils.Vector((diagonalOfBoundingBox/2*0.9, diagonalOfBoundingBox/2*0.9, diagonalOfBoundingBox/2*0.9))
upperRight = origin + mathutils.Vector((diagonalOfBoundingBox/2*1.1, diagonalOfBoundingBox/2*1.1, diagonalOfBoundingBox/2*1.1))
vertices, triangles = mcubes.marching_cubes_func((lowerLeft[0], lowerLeft[1], lowerLeft[2]),(upperRight[0], upperRight[1], upperRight[2]), 100, 100, 100, f, 0)
# Export the result
mcubes.export_mesh(vertices, triangles, "C:\\Users\\jaswir\\Documents\\GameTechnology\\3DM\\3DM_Practical1\\DAE_Files\\Bunnyk1.dae", "Bunny_k1")
import numpy as np
import mcubes
print("Example 1: Isosurface in NumPy volume...")
# Create a data volume (30 x 30 x 30)
X, Y, Z = np.mgrid[:100, :100, :100]
u = (X-50)**2 + (Y-50)**2 + (Z-50)**2 - 25**2
# Extract the 0-isosurface
vertices1, triangles1 = mcubes.marching_cubes(u, 0)
# Export the result to sphere.dae
mcubes.export_mesh(vertices1, triangles1, "sphere1.dae", "MySphere")
print("Done. Result saved in 'sphere1.dae'.")
print("Example 2: Isosurface in Python function...")
print("(this might take a while...)")
# Create the volume
def f(x, y, z):
return x**2 + y**2 + z**2
# Extract the 16-isosurface
vertices2, triangles2 = mcubes.marching_cubes_func(
(-10,-10,-10), (10,10,10), # Bounds
100, 100, 100, # Number of samples in each dimension
f, # Implicit function
16) # Isosurface value
def test_z_pc(self, config, batch_z, dim):
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
dima = self.test_size
multiplier = int(dim/dima)
multiplier2 = multiplier*multiplier
multiplier3 = multiplier*multiplier*multiplier
#get coords 256
aux_x = np.zeros([dima,dima,dima],np.int32)
aux_y = np.zeros([dima,dima,dima],np.int32)
aux_z = np.zeros([dima,dima,dima],np.int32)
for i in range(dima):
for j in range(dima):
for k in range(dima):
aux_x[i,j,k] = i*multiplier
aux_y[i,j,k] = j*multiplier
aux_z[i,j,k] = k*multiplier
coords = np.zeros([multiplier3,dima,dima,dima,3],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
coords[i*multiplier2+j*multiplier+k,:,:,:,0] = aux_x+i
coords[i*multiplier2+j*multiplier+k,:,:,:,1] = aux_y+j
coords[i*multiplier2+j*multiplier+k,:,:,:,2] = aux_z+k
coords = (coords+0.5)/dim*2.0-1.0
coords = np.reshape(coords,[multiplier3,self.batch_size,3])
n_pc_points = 2048
thres = 0.5
hdf5_file = h5py.File(self.dataset_name + "_im_gan_sample.hdf5", 'w')
hdf5_file.create_dataset("points", [batch_z.shape[0],n_pc_points,3], np.float32)
for t in range(batch_z.shape[0]):
print(t)
model_float = np.zeros([dim+2,dim+2,dim+2],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
minib = i*multiplier2+j*multiplier+k
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector: batch_z[t:t+1],
self.point_coord: coords[minib],
})
model_float[aux_x+i+1,aux_y+j+1,aux_z+k+1] = np.reshape(model_out, [dima,dima,dima])
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(vertices, triangles, config.sample_dir+"/"+"out"+str(t)+".dae", str(t))
np.random.shuffle(vertices)
vertices = (vertices - dim/2 - 0.5)/dim
vertices_out = np.zeros([n_pc_points,3], np.float32)
vertices_len = vertices.shape[0]
for i in range(n_pc_points):
vertices_out[i] = vertices[i%vertices_len]
hdf5_file["points"][t,:,:] = vertices_out
hdf5_file.close()
def test(model, dataset, epoch=-1):
train_iterator = dataset.train_iterator(batch_size=args.BATCH_SIZE,
flatten_y=False)
holdout_view_iterator = dataset.holdout_view_iterator(batch_size=args.BATCH_SIZE,
flatten_y=False)
holdout_model_iterator = dataset.holdout_model_iterator(batch_size=args.BATCH_SIZE,
flatten_y=False)
if epoch == -1:
base_dir = 'final/'
else:
base_dir = 'epoch_' + str(epoch) + '/'
sub_dir = base_dir + 'trained_views/'
os.makedirs(args.TEST_OUTPUT_DIR + sub_dir)
batch_x, batch_y = train_iterator.next()
pred = model._predict(batch_x)
# Prediction comes in format [batch number, z-axis, patch number, x-axis,
# y-axis].
pred = pred.reshape(args.BATCH_SIZE, args.PATCH_SIZE, 1, args.PATCH_SIZE, args.PATCH_SIZE)
# Convert prediction to format [batch number, x-axis, y-axis, z-axis,
# patch number].
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
for i in range(args.BATCH_SIZE):
v, t = mcubes.marching_cubes(pred_as_b012c[i, :, :, :, 0], 0.5)
# Save predicted object mesh.
mcubes.export_mesh(v, t, args.TEST_OUTPUT_DIR + sub_dir + 'model_' + str(i) + '.dae',
'model')
# Save visualizations of the predicted, input, and expected occupancy
# grids.
viz.visualize_batch_x(pred, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "pred_" + str(i))
viz.visualize_batch_x(batch_x, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "input_" + str(i))
viz.visualize_batch_x(batch_y, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "expected_" + str(i))
sub_dir = base_dir + 'holdout_views/'
os.makedirs(args.TEST_OUTPUT_DIR + sub_dir)
batch_x, batch_y = holdout_view_iterator.next()
pred = model._predict(batch_x)
pred = pred.reshape(args.BATCH_SIZE, args.PATCH_SIZE, 1, args.PATCH_SIZE, args.PATCH_SIZE)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
for i in range(args.BATCH_SIZE):
v, t = mcubes.marching_cubes(pred_as_b012c[i, :, :, :, 0], 0.5)
mcubes.export_mesh(v, t, args.TEST_OUTPUT_DIR + sub_dir + 'model_' + str(i) + '.dae',
'model')
# Save visualizations of the predicted, input, and expected occupancy
# grids.
viz.visualize_batch_x(pred, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "pred_" + str(i))
viz.visualize_batch_x(batch_x, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "input_" + str(i))
viz.visualize_batch_x(batch_y, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "expected_" + str(i))
sub_dir = base_dir + 'holdout_models/'
os.makedirs(args.TEST_OUTPUT_DIR + sub_dir)
batch_x, batch_y = holdout_model_iterator.next()
pred = model._predict(batch_x)
pred = pred.reshape(args.BATCH_SIZE, args.PATCH_SIZE, 1, args.PATCH_SIZE, args.PATCH_SIZE)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
for i in range(args.BATCH_SIZE):
v, t = mcubes.marching_cubes(pred_as_b012c[i, :, :, :, 0], 0.5)
mcubes.export_mesh(v, t, args.TEST_OUTPUT_DIR + sub_dir + 'model_' + str(i) + '.dae',
'model')
# Save visualizations of the predicted, input, and expected occupancy
# grids.
viz.visualize_batch_x(pred, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "pred_" + str(i))
viz.visualize_batch_x(batch_x, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "input_" + str(i))
viz.visualize_batch_x(batch_y, i, str(i),
args.TEST_OUTPUT_DIR + sub_dir + "expected_" + str(i))
def main():
# Use NumPy to create a 2D array of complex numbers on [-2,2]x[-2,2]
Y, X = np.mgrid[-1.3:1.3:0.005, -2:1:0.005]
print 'Y shape: ', Y.shape
print 'X shape: ', X.shape
Z = X+1j*Y
xs = tf.constant(Z.astype("complex64"))
zs = tf.Variable(xs)
ns = tf.Variable(tf.zeros_like(xs, "float32"))
not_diverged = tf.Variable(np.ones(Z.shape, dtype=np.bool))
Z_mod_at_div = tf.Variable(2 * tf.ones_like(xs, "float32"))
for i in range(MAX_ITERS):
# Compute the new values of z: z^2 + x
zs_ = zs*zs + xs
# Have we diverged with this new value?
cur_mod = tf.complex_abs(zs_)
not_diverged_ = cur_mod < 4
# Operation to update the zs and the iteration count.
# Note: We keep computing zs after they diverge! This
# is very wasteful! There are better, if a little
# less simple, ways to do this.
ns_ = ns + tf.cast(not_diverged_, "float32")
diverged_this_step = tf.logical_and(tf.logical_not(not_diverged_), not_diverged)
Z_mod_at_div = tf.select(diverged_this_step, cur_mod, Z_mod_at_div)
zs = zs_
ns = ns_
not_diverged = not_diverged_
mus = tf.select(not_diverged, ns, ns + 1 - tf.log(tf.log(Z_mod_at_div)) / np.log(2))
with tf.Session() as sess:
tf.initialize_all_variables().run()
print 'running!'
ns_evaled, Z_mod_at_div_evaled, mus_evaled = sess.run([ns, Z_mod_at_div, mus])
print 'done running!'
print Z_mod_at_div_evaled
non_zeros_z_mod = np.where(np.abs(Z_mod_at_div_evaled) > 0.01)
print non_zeros_z_mod
print 'max mod: %f, min mod: %f' % (np.max(Z_mod_at_div_evaled), np.min(Z_mod_at_div_evaled[non_zeros_z_mod]))
print 'diff between mus and ns: '
diff = mus_evaled - ns_evaled
print diff
print 'max: %f, min: %f' % (np.max(diff), np.min(diff))
DisplayFractal(mus_evaled, 'mandelbrot.png')
DisplayFractal(ns_evaled, 'mandelbrot_notfrac.png')
img_int_ext = interior_exterior_map(ns_evaled)
print "img_int_ext.max, %f, img_int_ext.min: %f" % \
(img_int_ext.max(), img_int_ext.min())
location = (X.shape[0] / 2, (4 * X.shape[1]) / 5)
radius = (X.shape[0] / 10)
ext_radius = (X.shape[0] / 70)
img_int_ext_pendant = add_pendant(img_int_ext, location, radius, ext_radius)
DisplayFractal(img_int_ext_pendant, "mandelbrot_int_ext_pendant.png")
img_int_ext_pendant_noend = np.copy(img_int_ext_pendant)
for i in xrange(X.shape[1] / 5):
for j in xrange(X.shape[0]):
img_int_ext_pendant_noend[j, i] = 1
DisplayFractal(img_int_ext_pendant_noend, "mandelbrot_int_ext_pendant_noend.png")
img_int_ext_pendant_noend_bigmiddle = np.copy(img_int_ext_pendant_noend)
location_bigmiddle = np.array((X.shape[0] / 2, int(X.shape[1] / 2.5)))
radius_bigmiddle = X.shape[1] / 25
for i in xrange(X.shape[1]):
for j in xrange(X.shape[0]):
dist = norm(np.array((j, i)) - location_bigmiddle)
if dist < radius_bigmiddle:
img_int_ext_pendant_noend_bigmiddle[j, i] = -1
DisplayFractal(img_int_ext_pendant_noend_bigmiddle, "mandelbrot_int_ext_pendant_noend_bigmiddle.png")
print "img_int_ext: "
print img_int_ext
DisplayFractal(img_int_ext, "mandelbrot_int_ext.png")
contours = measure.find_contours(img_int_ext_pendant_noend_bigmiddle, 0.0)
len_contours = [len(contour_i) for contour_i in contours]
print len_contours
contours_sorted_by_size = sorted(contours, key=len)
len_contours = [len(contour_i) for contour_i in contours]
print len_contours
bigcontour = contours_sorted_by_size[0]
#embed()
#bigcontour_int_ext = contour_to_int_ext_map(bigcontour, X, Y)
#embed()
#fig, ax = plt.subplots()
#ax.imshow(img_int_ext, interpolation='nearest', cmap=plt.cm.gray)
#for n, contour in enumerate(contours):
#ax.plot(contour[:, 1], contour[:, 0], linewidth=2)
#ax.plot(bigcontour[:, 1], bigcontour[:, 0], linewidth=2)
#ax.axis('image')
#ax.set_xticks([])
#ax.set_yticks([])
dwg = svgwrite.Drawing('mandelbrot.svg', profile='tiny')
for j in [-1, -2]:
contour = contours_sorted_by_size[j]
for i in xrange(contour.shape[0] - 1):
#print tuple(bigcontour[i])
dwg.add(dwg.line(tuple(contour[i]), tuple(contour[i + 1]), \
stroke=svgwrite.rgb(10, 10, 16, '%')))
#dwg.add(dwg.text('Test', insert=(0, 0.2), fill='red'))
dwg.save()
#plt.show()
#error = 100 * np.abs(mus_evaled - ns_evaled)
#print error.shape
#error = error.reshape(list(error.shape)+[1])
#print error.shape
#error_img = np.concatenate([error, error, error], 2)
#error_img = np.uint8(np.clip(error_img, 0, 255))
#scipy.misc.imsave('mandelbrot_errors.png', error_img)
# 3d mandelbrot!
max_dist = 10
#tsdf = gen_tsdf(img_int_ext_pendant_noend_bigmiddle, max_dist)
tsdf = np.load("tsdf_10.npy")
#np.save("tsdf_10", tsdf)
#plt.imshow(tsdf)
#plt.show()
# a = -3 / 20
# b = 53 / 20
# c = -1
# for 10.5 at 10, 8.5 at 5, and 1.5 at 1
# with a * x**2 + b * x + c formula for height
int_ext_3d_map = gen_int_ext_3d_map_from_tsdf(tsdf, max_dist)
#embed()
vertices, triangles = mcubes.marching_cubes(int_ext_3d_map, 0)
mcubes.export_mesh(vertices, triangles, "mandelbrot_smoothed.dae", "Mandelbrot_pendant")
#embed()
from mayavi import mlab
mlab.triangular_mesh(
vertices[:, 0], vertices[:, 1], vertices[:, 2],
triangles)
mlab.show()
# for i in range(1501, 1735):
# image = Image.open('./hola/1/'+str(i)+'.png').convert('RGBA')
# pixeldata = list(image.getdata())
# for j,pixel in enumerate(pixeldata):
# if pixel[:3] == (255,255,255):
# pixeldata[j] = (255,255,255,0)
# image.putdata(pixeldata)
# image.save('./hola/1/'+str(i)+'.png')
# PATIENTS_FOLDER = './hola/1/'
# patients = os.listdir(PATIENTS_FOLDER) #listing all directories and files within
# patients.sort()
#------------------------Running marching cubes on the images with ROI---------------------
X_data = []
files = glob.glob ("./Head/roi_images/*.png")
for myFile in files:
#print(myFile)
image = cv2.imread (myFile)
X_data.append (image)
print('X_data shape:', np.array(X_data).shape)
patient_scans = np.array(X_data)[:,:,:,0]
print patient_scans.shape
print type(patient_scans)
# verts, faces, normals, values = measure.marching_cubes_lewiner(patient_scans, 1)
vertices, triangles = mcubes.marching_cubes(patient_scans, 0)
mcubes.export_mesh(vertices, triangles, "final_image.dae", "MyROI")
def test_interp(self, config):
self.saver = tf.train.Saver()
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
interp_size = 8
idx1 = 0
idx2 = 1
thres = 0.6
add_out = "./out/"
dim = 128
dima = self.test_size
multiplier = int(dim/dima)
multiplier2 = multiplier*multiplier
multiplier3 = multiplier*multiplier*multiplier
#get coords 64
aux_x = np.zeros([dima,dima,dima],np.int32)
aux_y = np.zeros([dima,dima,dima],np.int32)
aux_z = np.zeros([dima,dima,dima],np.int32)
for i in range(dima):
for j in range(dima):
for k in range(dima):
aux_x[i,j,k] = i*multiplier
aux_y[i,j,k] = j*multiplier
aux_z[i,j,k] = k*multiplier
coords = np.zeros([multiplier3,dima,dima,dima,3],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
coords[i*multiplier2+j*multiplier+k,:,:,:,0] = aux_x+i
coords[i*multiplier2+j*multiplier+k,:,:,:,1] = aux_y+j
coords[i*multiplier2+j*multiplier+k,:,:,:,2] = aux_z+k
coords = (coords+0.5)/dim*2.0-1.0
coords = np.reshape(coords,[multiplier3,self.batch_size,3])
offset_x = int(self.crop_edge/2)
offset_y = int(self.crop_edge/2)
batch_view1 = self.data_pixel[idx1,0]
batch_view1 = batch_view1[offset_y:offset_y+self.crop_size, offset_x:offset_x+self.crop_size]
batch_view1 = np.reshape(batch_view1/255.0, [1,self.crop_size,self.crop_size,1])
batch_view2 = self.data_pixel[idx2,0]
batch_view2 = batch_view2[offset_y:offset_y+self.crop_size, offset_x:offset_x+self.crop_size]
batch_view2 = np.reshape(batch_view2/255.0, [1,self.crop_size,self.crop_size,1])
model_z1 = self.sess.run(self.sE,
feed_dict={
self.view_test: batch_view1,
})
model_z2 = self.sess.run(self.sE,
feed_dict={
self.view_test: batch_view2,
})
batch_z = np.zeros([interp_size,self.z_dim], np.float32)
for i in range(interp_size):
batch_z[i] = model_z2*i/(interp_size-1) + model_z1*(interp_size-1-i)/(interp_size-1)
for t in range(interp_size):
model_float = np.zeros([dim+2,dim+2,dim+2],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
minib = i*multiplier2+j*multiplier+k
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector_test: batch_z[t],
self.point_coord: coords[minib],
})
model_float[aux_x+i+1,aux_y+j+1,aux_z+k+1] = np.reshape(model_out, [dima,dima,dima])
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(vertices, triangles, add_out+str(t)+".dae", str(t))
print("[sample]")
data_dict = h5py.File('02691156_vox.hdf5', 'r')
i = 0
shape = 'airplane'
vox = data_dict['voxels'][:]
batch_vox = vox[i:i+1]
batch_vox = np.reshape(batch_vox,[64,64,64])
img1 = np.clip(np.amax(batch_vox, axis=0)*256, 0,255).astype(np.uint8)
cv2.imwrite(shape + '_' + str(i)+"_vox_1.png",img1)
img2 = np.clip(np.amax(batch_vox, axis=1)*256, 0,255).astype(np.uint8)
cv2.imwrite(shape + '_' + str(i)+"_vox_2.png",img2)
img3 = np.clip(np.amax(batch_vox, axis=2)*256, 0,255).astype(np.uint8)
cv2.imwrite(shape + '_' + str(i)+"_vox_3.png",img3)
vertices, triangles = mcubes.marching_cubes(batch_vox, 0.5)
mcubes.export_mesh(vertices, triangles, shape + '_' + str(i)+"_vox.dae", str(i))
points16 = data_dict['points_16'][:]
data_values16 = data_dict['values_16'][:]
batch_points = points16[i,:]
batch_values = data_values16[i,:]
real_model = np.zeros([16,16,16],np.uint8)
real_model[batch_points[:,0],batch_points[:,1],batch_points[:,2]] = np.reshape(batch_values, [-1])
img1 = np.clip(np.amax(real_model, axis=0)*256, 0,255).astype(np.uint8)
cv2.imwrite(shape + '_' + str(i)+"_16_1.png",img1)
img2 = np.clip(np.amax(real_model, axis=1)*256, 0,255).astype(np.uint8)
cv2.imwrite(shape + '_' + str(i)+ "_16_2.png",img2)
img3 = np.clip(np.amax(real_model, axis=2)*256, 0,255).astype(np.uint8)
cv2.imwrite(shape + '_' + str(i)+"_16_3.png",img3)
def test(self, config):
self.saver = tf.train.Saver()
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
thres = 0.6
add_out = "./out/"
add_image = "./image/"
dim = 128
dima = self.test_size
multiplier = int(dim/dima)
multiplier2 = multiplier*multiplier
multiplier3 = multiplier*multiplier*multiplier
#get coords 64
aux_x = np.zeros([dima,dima,dima],np.int32)
aux_y = np.zeros([dima,dima,dima],np.int32)
aux_z = np.zeros([dima,dima,dima],np.int32)
for i in range(dima):
for j in range(dima):
for k in range(dima):
aux_x[i,j,k] = i*multiplier
aux_y[i,j,k] = j*multiplier
aux_z[i,j,k] = k*multiplier
coords = np.zeros([multiplier3,dima,dima,dima,3],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
coords[i*multiplier2+j*multiplier+k,:,:,:,0] = aux_x+i
coords[i*multiplier2+j*multiplier+k,:,:,:,1] = aux_y+j
coords[i*multiplier2+j*multiplier+k,:,:,:,2] = aux_z+k
coords = (coords+0.5)/dim*2.0-1.0
coords = np.reshape(coords,[multiplier3,self.batch_size,3])
offset_x = int(self.crop_edge/2)
offset_y = int(self.crop_edge/2)
#test_num = self.data_pixel.shape[0]
test_num = 16
for t in range(test_num):
print(t,test_num)
batch_view = self.data_pixel[t,0]
batch_view = batch_view[offset_y:offset_y+self.crop_size, offset_x:offset_x+self.crop_size]
batch_view = np.reshape(batch_view/255.0, [1,self.crop_size,self.crop_size,1])
model_z = self.sess.run(self.sE,
feed_dict={
self.view_test: batch_view,
})
model_float = np.zeros([dim+2,dim+2,dim+2],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
minib = i*multiplier2+j*multiplier+k
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector_test: model_z,
self.point_coord: coords[minib],
})
model_float[aux_x+i+1,aux_y+j+1,aux_z+k+1] = np.reshape(model_out, [dima,dima,dima])
'''
img1 = np.clip(np.amax(model_float, axis=0)*256, 0,255).astype(np.uint8)
img2 = np.clip(np.amax(model_float, axis=1)*256, 0,255).astype(np.uint8)
img3 = np.clip(np.amax(model_float, axis=2)*256, 0,255).astype(np.uint8)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_1t.png",img1)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_2t.png",img2)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_3t.png",img3)
img1 = (np.reshape(batch_view, [self.crop_size,self.crop_size])*255).astype(np.uint8)
cv2.imwrite(config.sample_dir+"/"+str(t)+"_v.png",img1)
'''
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(vertices, triangles, add_out+str(t)+".dae", str(t))
cv2.imwrite(add_image+str(t)+".png", self.data_pixel[t,0])
print("[sample]")
def test_image(self, config):
self.saver = tf.train.Saver()
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
return
thres = 0.6
add_out = "./out/"
add_image = "./image/"
dim = 128
dima = self.test_size
multiplier = int(dim/dima)
multiplier2 = multiplier*multiplier
multiplier3 = multiplier*multiplier*multiplier
#get coords 64
aux_x = np.zeros([dima,dima,dima],np.int32)
aux_y = np.zeros([dima,dima,dima],np.int32)
aux_z = np.zeros([dima,dima,dima],np.int32)
for i in range(dima):
for j in range(dima):
for k in range(dima):
aux_x[i,j,k] = i*multiplier
aux_y[i,j,k] = j*multiplier
aux_z[i,j,k] = k*multiplier
coords = np.zeros([multiplier3,dima,dima,dima,3],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
coords[i*multiplier2+j*multiplier+k,:,:,:,0] = aux_x+i
coords[i*multiplier2+j*multiplier+k,:,:,:,1] = aux_y+j
coords[i*multiplier2+j*multiplier+k,:,:,:,2] = aux_z+k
coords = (coords+0.5)/dim*2.0-1.0
coords = np.reshape(coords,[multiplier3,self.batch_size,3])
offset_x = int(self.crop_edge/2)
offset_y = int(self.crop_edge/2)
for t in range(16):
img_add = add_image+str(t)+".png"
print(img_add)
imgo_ = cv2.imread(img_add, cv2.IMREAD_GRAYSCALE)
img = cv2.resize(imgo_, (self.view_size,self.view_size))
batch_view = np.reshape(img,(1,self.view_size,self.view_size,1))
batch_view = batch_view[:, offset_y:offset_y+self.crop_size, offset_x:offset_x+self.crop_size, :]
batch_view = batch_view/255.0
model_z = self.sess.run(self.sE,
feed_dict={
self.view_test: batch_view,
})
model_float = np.zeros([dim+2,dim+2,dim+2],np.float32)
for i in range(multiplier):
for j in range(multiplier):
for k in range(multiplier):
minib = i*multiplier2+j*multiplier+k
model_out = self.sess.run(self.zG,
feed_dict={
self.z_vector_test: model_z,
self.point_coord: coords[minib],
})
model_float[aux_x+i+1,aux_y+j+1,aux_z+k+1] = np.reshape(model_out, [dima,dima,dima])
vertices, triangles = mcubes.marching_cubes(model_float, thres)
mcubes.export_mesh(vertices, triangles, add_out+str(t)+".dae", str(t))
print("[sample]")
def extract_voxel(get_model, model_path, loss_function, train_path,
validation_path, mesh):
# Read in training and validation files.
validation_files = [
os.path.join(validation_path, filename)
for filename in os.listdir(validation_path) if ".tfrecord" in filename
]
sdf_count_ = 2048
voxel_resolution = 32
# Fetch the data.
validation_dataset = get_sdf_dataset(validation_files,
batch_size=1,
sdf_count=sdf_count_)
# Setup iterators.
val_iterator = validation_dataset.make_initializable_iterator()
val_next_point_cloud, val_next_xyz, val_next_label = val_iterator.get_next(
)
# Setup model operations.
points = tf.placeholder(tf.float32)
xyz_in = tf.placeholder(tf.float32)
sdf_labels = tf.placeholder(tf.float32)
is_training = tf.placeholder(tf.bool)
sdf_prediction, loss, _ = get_model(points,
xyz_in,
sdf_labels,
is_training,
None,
batch_size=1,
alpha=0.5,
loss_function=loss_function,
sdf_count=sdf_count_)
# Generate points to sample.
pts = []
for x in range(voxel_resolution):
for y in range(voxel_resolution):
for z in range(voxel_resolution):
x_ = -0.5 + ((1.0 / float(voxel_resolution - 1)) * x)
y_ = -0.5 + ((1.0 / float(voxel_resolution - 1)) * y)
z_ = -0.5 + ((1.0 / float(voxel_resolution - 1)) * z)
pts.append([x_, y_, z_])
pts = np.array(pts)
pt_splits = np.split(pts, pts.shape[0] // sdf_count_)
# Save/Restore model.
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, os.path.join(model_path, 'model.ckpt'))
# Setup function that predicts SDF for (x,y,z) given a point cloud.
def get_sdf(point_cloud, pts):
prediction = sess.run(sdf_prediction,
feed_dict={
points: point_cloud,
xyz_in: pts,
sdf_labels: None,
is_training: False,
})
# print(xyz)
# print(prediction)
return prediction
sess.run(val_iterator.initializer)
for i in range(20):
point_clouds_, xyzs_, labels_ = sess.run(
(val_next_point_cloud, val_next_xyz, val_next_label))
# Setup a voxelization based on the SDF.
voxelized = np.zeros(
(voxel_resolution, voxel_resolution, voxel_resolution),
dtype=np.float32)
filled_pts = []
# For all points sample SDF given the point cloud and include points inside the object to a point cloud.
for pts_ in pt_splits:
sdf_ = get_sdf(point_clouds_,
np.reshape(pts_, (1, sdf_count_, 3)))
for pt_, sdf in zip(np.reshape(pts_, (sdf_count_, 3)),
np.reshape(sdf_, (sdf_count_, ))):
if sdf <= 0.0 and sdf >= -0.05:
filled_pts.append(pt_)
x_ = int(
round(
(pt_[0] + 0.5) * float(voxel_resolution - 1)))
y_ = int(
round(
(pt_[1] + 0.5) * float(voxel_resolution - 1)))
z_ = int(
round(
(pt_[2] + 0.5) * float(voxel_resolution - 1)))
voxelized[x_, y_, z_] = 1.0
# Plot.
plot_3d_points(point_clouds_[0])
plot_3d_points(np.reshape(filled_pts, (-1, 3)))
if mesh:
# Mesh w/ mcubes.
#plot_voxel(convert_to_sparse_voxel_grid(voxelized), voxel_res=(voxel_resolution, voxel_resolution, voxel_resolution))
vertices, triangles = mcubes.marching_cubes(voxelized, 0)
mcubes.export_mesh(vertices, triangles, 'test.dae', 'test')
meshed_object = trimesh.load('test.dae')
meshed_object.show()
def execute_cb(self, goal):
start_time = time.time()
self._feedback = graspit_shape_completion.msg.CompleteMeshFeedback()
self._result = graspit_shape_completion.msg.CompleteMeshResult()
rospy.loginfo('Received Msg')
single_view_pointcloud_filepath = '/srv/data/shape_completion_data/test_1/pcd_8_310_143723.pcd'
point_array = np.asarray(goal.partial_mesh.vertices)
pc = np.zeros((len(point_array), 3), np.float32)
for i in range(len(point_array)):
pc[i][0] = point_array[i].x
pc[i][1] = point_array[i].y
pc[i][2] = point_array[i].z
batch_x = np.zeros((1, self.patch_size, self.patch_size, self.patch_size, 1), dtype=np.float32)
batch_x[0, :, :, :, :], voxel_resolution, offset = reconstruction_utils.build_test_from_pc_scaled(pc, self.patch_size)
#make batch B2C01 rather than B012C
batch_x = batch_x.transpose(0, 3, 4, 1, 2)
pred = self.model._predict(batch_x)
pred = pred.reshape(1, self.patch_size, 1, self.patch_size, self.patch_size)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
batch_x = batch_x.transpose(0, 3, 4, 1, 2)
mask = reconstruction_utils.get_occluded_voxel_grid(batch_x[0, :, :, :, 0])
completed_region = pred_as_b012c[0, :, :, :, 0] * mask
scale = 4
high_res_voxel_grid, voxel_resolution, offset = reconstruction_utils.build_high_res_voxel_grid(pc, scale, self.patch_size)
indices = np.mgrid[0:scale*self.patch_size:1, 0:scale*self.patch_size:1, 0:scale*self.patch_size:1]
scaled_completed_region = map_coordinates(completed_region, indices/scale, order = 0, mode = 'constant', cval=0.0)
output = high_res_voxel_grid[:, :, :, 0] + scaled_completed_region
#output = batch_x[0, :, :, :, 0] + completed_region
v, t = mcubes.marching_cubes(output, 0.25)
if self.smooth_mesh:
coarse_mesh = '/srv/data/temp/' + 'coarse.dae'
smooth_mesh = '/srv/data/temp/' + 'smooth.off'
script_file = '/srv/data/temp/' + 'poisson_remesh.mlx'
mcubes.export_mesh(v, t, coarse_mesh, 'model')
cmd_string = 'meshlabserver -i ' + coarse_mesh
cmd_string = cmd_string + ' -o ' + smooth_mesh
cmd_string = cmd_string + ' -s ' + script_file
process = subprocess.call(cmd_string, shell=True)
off = off_handler.OffHandler()
off.read(smooth_mesh)
v = off.vertices
t = off.faces
#viz.visualize_batch_x(pred, 0, str(1), 'results/' + "pred_" + str(1))
#viz.visualize_batch_x(batch_x, 0, str(1), 'results/' + "input_" + str(1))
v *= voxel_resolution
v += offset
for i in range(len(v)):
self._result.completed_mesh.vertices.append(geometry_msgs.msg.Point(v[i, 0], v[i, 1], v[i, 2]))
for i in range(len(t)):
self._result.completed_mesh.triangles.append(shape_msgs.msg.MeshTriangle((t[i, 0], t[i, 1], t[i, 2])))
end_time = time.time()
self._result.completion_time = int(1000*(end_time - start_time))
self._as.set_succeeded(self._result)
import numpy as np
import pandas as pd
from pyntcloud import PyntCloud
import mcubes
cloud = PyntCloud.from_file("../data/points.xyz", sep=" ")
# k_neighbors = cloud.get_neighbors(k=10)
# cloud.add_scalar_field("normals", k_neighbors=k_neighbors)
voxelgrid_id = cloud.add_structure("voxelgrid", n_x=32, n_y=32, n_z=32)
voxelgrid = cloud.structures[voxelgrid_id]
x_cords = voxelgrid.voxel_x
y_cords = voxelgrid.voxel_y
z_cords = voxelgrid.voxel_z
voxel = np.zeros((32, 32, 32))
for x, y, z in zip(x_cords, y_cords, z_cords):
voxel[x][y][z] = 1
# smooth = mcubes.smooth(voxel)
vertices, triangles = mcubes.marching_cubes(voxel, 0)
mcubes.export_mesh(vertices, triangles, "../outputs/scene.dae", "MyScene")
def execute_cb(self, goal):
start_time = time.time()
self._feedback = graspit_shape_completion.msg.CompleteMeshFeedback()
self._result = graspit_shape_completion.msg.CompleteMeshResult()
rospy.loginfo('Received Msg')
single_view_pointcloud_filepath = '/srv/data/shape_completion_data/test_1/pcd_8_310_143723.pcd'
point_array = np.asarray(goal.partial_mesh.vertices)
pc = np.zeros((len(point_array), 3), np.float32)
for i in range(len(point_array)):
pc[i][0] = point_array[i].x
pc[i][1] = point_array[i].y
pc[i][2] = point_array[i].z
batch_x = np.zeros(
(1, self.patch_size, self.patch_size, self.patch_size, 1),
dtype=np.float32)
batch_x[
0, :, :, :, :], voxel_resolution, offset = reconstruction_utils.build_test_from_pc_scaled(
pc, self.patch_size)
#make batch B2C01 rather than B012C
batch_x = batch_x.transpose(0, 3, 4, 1, 2)
pred = self.model._predict(batch_x)
pred = pred.reshape(1, self.patch_size, 1, self.patch_size,
self.patch_size)
pred_as_b012c = pred.transpose(0, 3, 4, 1, 2)
batch_x = batch_x.transpose(0, 3, 4, 1, 2)
mask = reconstruction_utils.get_occluded_voxel_grid(batch_x[0, :, :, :,
0])
completed_region = pred_as_b012c[0, :, :, :, 0] * mask
scale = 4
high_res_voxel_grid, voxel_resolution, offset = reconstruction_utils.build_high_res_voxel_grid(
pc, scale, self.patch_size)
indices = np.mgrid[0:scale * self.patch_size:1,
0:scale * self.patch_size:1,
0:scale * self.patch_size:1]
scaled_completed_region = map_coordinates(completed_region,
indices / scale,
order=0,
mode='constant',
cval=0.0)
output = high_res_voxel_grid[:, :, :, 0] + scaled_completed_region
#output = batch_x[0, :, :, :, 0] + completed_region
v, t = mcubes.marching_cubes(output, 0.25)
if self.smooth_mesh:
coarse_mesh = '/srv/data/temp/' + 'coarse.dae'
smooth_mesh = '/srv/data/temp/' + 'smooth.off'
script_file = '/srv/data/temp/' + 'poisson_remesh.mlx'
mcubes.export_mesh(v, t, coarse_mesh, 'model')
cmd_string = 'meshlabserver -i ' + coarse_mesh
cmd_string = cmd_string + ' -o ' + smooth_mesh
cmd_string = cmd_string + ' -s ' + script_file
process = subprocess.call(cmd_string, shell=True)
off = off_handler.OffHandler()
off.read(smooth_mesh)
v = off.vertices
t = off.faces
#viz.visualize_batch_x(pred, 0, str(1), 'results/' + "pred_" + str(1))
#viz.visualize_batch_x(batch_x, 0, str(1), 'results/' + "input_" + str(1))
v *= voxel_resolution
v += offset
for i in range(len(v)):
self._result.completed_mesh.vertices.append(
geometry_msgs.msg.Point(v[i, 0], v[i, 1], v[i, 2]))
for i in range(len(t)):
self._result.completed_mesh.triangles.append(
shape_msgs.msg.MeshTriangle((t[i, 0], t[i, 1], t[i, 2])))
end_time = time.time()
self._result.completion_time = int(1000 * (end_time - start_time))
self._as.set_succeeded(self._result)
# @Last Modified time: 2020-10-22 16:49:55
import numpy as np
import mcubes
print("Example 1: Isosurface in NumPy volume...")
# Create a data volume (30 x 30 x 30)
X, Y, Z = np.mgrid[:100, :100, :100]
u = (X - 50)**2 + (Y - 50)**2 + (Z - 50)**2 - 25**2
# Extract the 0-isosurface
vertices1, triangles1 = mcubes.marching_cubes(u, 0)
print(vertices1.shape, triangles1.shape)
# Export the result to sphere.dae
mcubes.export_mesh(vertices1, triangles1, "sphere1.dae", "MySphere")
print("Done. Result saved in 'sphere1.dae'.")
print("Example 2: Isosurface in Python function...")
print("(this might take a while...)")
# Create the volume
def f(x, y, z):
return x**2 + y**2 + z**2
# Extract the 16-isosurface
vertices2, triangles2 = mcubes.marching_cubes_func(
data_points64 = data_dict['points_64'][:]
data_values64 = data_dict['values_64'][:]
data_voxels = data_dict['voxels'][:]
dxb = 0
batch_voxels = data_voxels[dxb:dxb + 1]
batch_voxels = np.reshape(batch_voxels, [64, 64, 64])
img1 = np.clip(np.amax(batch_voxels, axis=0) * 256, 0, 255).astype(np.uint8)
img2 = np.clip(np.amax(batch_voxels, axis=1) * 256, 0, 255).astype(np.uint8)
img3 = np.clip(np.amax(batch_voxels, axis=2) * 256, 0, 255).astype(np.uint8)
cv2.imwrite(str(dxb) + "_vox_1.png", img1)
cv2.imwrite(str(dxb) + "_vox_2.png", img2)
cv2.imwrite(str(dxb) + "_vox_3.png", img3)
vertices, triangles = mcubes.marching_cubes(batch_voxels, 0.5)
mcubes.export_mesh(vertices, triangles, str(dxb) + "_vox.dae", str(dxb))
batch_points_int = data_points16[dxb, :]
batch_values = data_values16[dxb, :]
real_model = np.zeros([16, 16, 16], np.uint8)
real_model[batch_points_int[:, 0], batch_points_int[:, 1],
batch_points_int[:, 2]] = np.reshape(batch_values, [-1])
img1 = np.clip(np.amax(real_model, axis=0) * 256, 0, 255).astype(np.uint8)
img2 = np.clip(np.amax(real_model, axis=1) * 256, 0, 255).astype(np.uint8)
img3 = np.clip(np.amax(real_model, axis=2) * 256, 0, 255).astype(np.uint8)
cv2.imwrite(str(dxb) + "_16_1.png", img1)
cv2.imwrite(str(dxb) + "_16_2.png", img2)
cv2.imwrite(str(dxb) + "_16_3.png", img3)
vertices, triangles = mcubes.marching_cubes(batch_voxels, 0.5)
mcubes.export_mesh(vertices, triangles, str(dxb) + "_16.dae", str(dxb))
