def visualize_predictions_mesh(self,
prediction_data,
feature_data,
target=None):
image = feature_data['image']
dp = prediction_data['deformed_points']
probs = prediction_data['probs']
if not hasattr(self, '_mesh_fn') or self._mesh_fn is None:
self._mesh_fn = self._mesh_transformation()
image -= np.min(image)
image /= np.max(image)
plt.imshow(image)
plt.show()
mesh = self._mesh_fn(probs, dp)
vertices, faces, original_vertices = (mesh[k]
for k in ('vertices', 'faces',
'original_vertices'))
visualize_mesh(original_vertices, faces)
mlab.show()
visualize_mesh(vertices,
faces,
color=(1, 0, 0),
include_wireframe=False)
mlab.show()
visualize_point_cloud(vertices, color=(1, 0, 0), scale_factor=0.01)
mlab.show()
def visualize_data_pointcloud(self, feature_data, target):
image = feature_data['image']
image -= np.min(image)
image /= np.max(image)
plt.imshow(image)
plt.show()
visualize_point_cloud(target, color=(1, 0, 0), scale_factor=0.01)
mlab.show()
plt.close()
def visualize_predicted_pointclouds(self):
evaluation_ids = self.data_splitter.get_data(
tf.estimator.ModeKeys.PREDICT)
template_ids, bs, ps = zip(*self.get_ffd_data())
with tf.Graph().as_default():
dataset = get_dataset(self.preprocessed_data_path,
self.cat_id,
self.view_angles,
self.cloud_resamples,
evaluation_ids,
False,
False,
batch_size=len(evaluation_ids))
features, targets = dataset.make_one_shot_iterator().get_next()
predictions = self.build_estimator(
features, targets, tf.estimator.ModeKeys.PREDICT).predictions
saver = tf.train.Saver()
with tf.train.MonitoredSession() as sess:
saver.restore(sess, tf.train.latest_checkpoint(self.model_dir))
data = sess.run([features, predictions])
for prediction_tensor in nested_generator(data):
image = prediction_tensor[0]['image']
image -= np.min(image)
image /= np.max(image)
plt.imshow(image)
plt.show()
dp = prediction_tensor[1]['deformed_points']
probs = prediction_tensor[1]['probs']
i = np.argmax(probs)
predicted_vertices = np.matmul(bs[i], ps[i] + dp[i])
visualize_point_cloud(np.matmul(bs[i], ps[i]),
color=(0, 0, 1),
scale_factor=0.01)
mlab.show()
visualize_point_cloud(predicted_vertices,
color=(1, 0, 0),
scale_factor=0.01)
mlab.show()
ds = get_template_ffd("/media/saurabh/e56e40fb-030d-4f7f-9e63-42ed5f7f6c711/preprocessing_new", desc_to_id("pistol"),
edge_length_threshold=None, n_samples=16384)
key = "1f646ff59cabdddcd810dcd63f342aca"
with ds:
b = np.array(ds[key]['b'])
p = np.array(ds[key]['p'])
mesh_dataset = get_thresholded_template_mesh("/media/saurabh/e56e40fb-030d-4f7f-9e63-42ed5f7f6c711/preprocessing_new", desc_to_id("pistol"),
None)
with mesh_dataset:
f = np.array(mesh_dataset[key]['faces'])
v_orignal = np.array(mesh_dataset[key]['vertices'])
# print(b)
# visualize_mesh(v_orignal, f)
# mlab.show()
visualize_mesh(np.matmul(b, p), f)
mlab.show()
visualize_point_cloud(np.matmul(b, p))
mlab.show()
# from deformations.FFD import calculate_ffd
# b, p = calculate_ffd(v_orignal, f)
# isualize_mesh(np.matmul(b, p), f)
# mlab.show()
from graphicUtils.visualizer.mayaviVisualizer import visualize_point_cloud
from graphicUtils.visualizer.mayaviVisualizer import visualize_normals
from datasetReader.h5py.cloudReader import CloudReader
from mayavi import mlab
import numpy as np
reader = CloudReader("/media/saurabh/e56e40fb-030d-4f7f-9e63-42ed5f7f6c71/preprocessing_new/")
dataset = reader.get_dataset("03948459", "pointCloud")
with dataset:
visualize_point_cloud(
np.array(dataset['800cf19b2f7ce07e1ee14c0944aebb52']),
scale_factor=0.005, color=(0, 1, 0))
mlab.show()
#dataset = reader.get_dataset("03948459", "cloudNormal")
#with dataset:
# a = visualize_normals(
# np.array(dataset['139ecc9b5ec25ea77a9772e56db4cd44']['points']),
# np.array(dataset['139ecc9b5ec25ea77a9772e56db4cd44']['normals']),
# scale_factor=0.005, color=(1, 0, 1))
# mlab.show()