def __getitem__(self, index):
"""Returns the item at index idx. """
data = dict()
attributes = dict()
synset_idx = self.synset_idxs[index]
obj_location = self.paths[index] / 'model.obj'
mesh = TriangleMesh.from_obj(str(obj_location))
data['vertices'] = mesh.vertices
data['faces'] = mesh.faces
attributes['name'] = self.names[index]
attributes['path'] = obj_location
attributes['synset'] = self.synsets[synset_idx]
attributes['label'] = self.labels[synset_idx]
return {'data': data, 'attributes': attributes}
def __getitem__(self, index):
data = dict()
attributes = dict()
img_name = self.img_names[index]
obj_name = self.obj_names[index]
view_num = random.randrange(0, self.views)
# load image and mesh
img = Image.open(os.path.join(img_name, 'rendering/{:02d}.png'.format(view_num)))
mesh = TriangleMesh.from_obj(os.path.join(obj_name, 'models/model_normalized.obj'))
# apply transformations to img
if self.transform is not None:
img = self.transform(img)
else:
img = torch.FloatTensor(np.array(img))
img = img.permute(2, 0, 1)
img = img / 255.
# load and process cam
param_location = os.path.join(img_name, 'rendering/rendering_metadata.txt')
azimuth, elevation, _, distance, _ = np.loadtxt(param_location)[view_num]
cam_params = kal.mathutils.geometry.transformations.compute_camera_params(azimuth, elevation, distance)
data['images'] = img
#data['vertices'] = mesh.vertices
#data['faces'] = mesh.faces
data['params'] = dict()
data['params']['cam_mat'] = cam_params[0]
data['params']['cam_pos'] = cam_params[1]
data['params']['azi'] = azimuth
data['params']['elevation'] = elevation
data['params']['distance'] = distance
attributes['img_name'] = img_name
attributes['obj_name'] = obj_name
attributes['synset'] = self.synsets[self.synset_idx[index]]
attributes['label'] = self.labels[self.synset_idx[index]]
return {'data': data, 'attributes': attributes}
def _get_data(self, index):
synset_idx = self.synset_idxs[index]
obj_location = self.paths[index] / 'model.obj'
mesh = TriangleMesh.from_obj(str(obj_location))
return (mesh, )