https://arxiv.org/abs/1911.11236
搭建训练环境
-
git clone https://github.com/QingyongHu/RandLA-Net.git
-
搭建 python 环境 , 这里我用的
3.9
shellconda create -n randlanet python=3.9 source activate randlanet pip install tensorflow==2.15.0 -i https://pypi.tuna.tsinghua.edu.cn/simple --timeout=120 pip install -r helper_requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple pip install Cython -i https://pypi.tuna.tsinghua.edu.cn/simple conda install -c conda-forge scikit-learn
-
cd
utils/cpp_wrappers/cpp_subsampling/
, 执行python setup.py build_ext --inplace
, 输出grid_subsampling.cpython-39-x86_64-linux-gnu.so
-
cd
nearest_neighbors
, 执行python setup.py build_ext --inplace
, 输出nearest_neighbors.cpython-39-x86_64-linux-gnu.so
制作数据集
-
这里我用
CloudCompare
标注的数据集 , 具体标注方法,上网找找. -
创建
make_train_dataset.py
, 开始生成训练数据集python# 写这段代码的时候,只有上帝和我知道它是干嘛的 # 现在,只有上帝知道 # @File : make_cloud_train_datasets.py # @Author : J. # @desc : 生成 RandLanet 训练数据集 from sklearn.neighbors import KDTree from os.path import join, exists, dirname, abspath import numpy as np import os, glob, pickle import sys BASE_DIR = dirname(abspath(__file__)) ROOT_DIR = dirname(BASE_DIR) sys.path.append(BASE_DIR) sys.path.append(ROOT_DIR) from helper_ply import write_ply from helper_tool import DataProcessing as DP grid_size = 0.01 dataset_path = './data/sample/original_data' original_pc_folder = join(dirname(dataset_path), 'original_ply') sub_pc_folder = join(dirname(dataset_path), 'input_{:.3f}'.format(grid_size)) os.mkdir(original_pc_folder) if not exists(original_pc_folder) else None os.mkdir(sub_pc_folder) if not exists(sub_pc_folder) else None railway_cnt = 0 backgroud_cnt = 0 for pc_path in glob.glob(join(dataset_path, '*.txt')): file_name = os.path.basename(pc_path)[:-4] if exists(join(sub_pc_folder, file_name + '_KDTree.pkl')): continue pc = np.loadtxt(pc_path) labels = pc[:, -1].astype(np.uint8) values , counts = np.unique(labels,return_counts = True) for i in range(len(values)): # 我标注2个类别(包含背景类别) # 统计每个类别点的数量 if values[i] == 0: backgroud_cnt = backgroud_cnt + counts[i] elif values[i] == 1: railway_cnt = railway_cnt + counts[i] full_ply_path = join(original_pc_folder, file_name + '.ply') # Subsample to save space sub_points, sub_colors, sub_labels = DP.grid_sub_sampling(pc[:, :3].astype(np.float32), pc[:, 3:6].astype(np.uint8), labels, 0.01) sub_labels = np.squeeze(sub_labels) write_ply(full_ply_path, (sub_points, sub_colors, sub_labels), ['x', 'y', 'z', 'red', 'green', 'blue', 'class']) # save sub_cloud and KDTree file sub_xyz, sub_colors, sub_labels = DP.grid_sub_sampling(sub_points, sub_colors, sub_labels, grid_size) sub_colors = sub_colors / 255.0 sub_labels = np.squeeze(sub_labels) sub_ply_file = join(sub_pc_folder, file_name + '.ply') write_ply(sub_ply_file, [sub_xyz, sub_colors, sub_labels], ['x', 'y', 'z', 'red', 'green', 'blue', 'class']) search_tree = KDTree(sub_xyz, leaf_size=50) kd_tree_file = join(sub_pc_folder, file_name + '_KDTree.pkl') with open(kd_tree_file, 'wb') as f: pickle.dump(search_tree, f) proj_idx = np.squeeze(search_tree.query(sub_points, return_distance=False)) proj_idx = proj_idx.astype(np.int32) proj_save = join(sub_pc_folder, file_name + '_proj.pkl') with open(proj_save, 'wb') as f: pickle.dump([proj_idx, labels], f) # 统计每个类别个数 print("----> backgroud_cnt: " + str(backgroud_cnt)) print("----> railway_cnt: " + str(railway_cnt))
-
修改
helper_tools.py
python#import cpp_wrappers.cpp_subsampling.grid_subsampling as cpp_subsampling #import nearest_neighbors.lib.python.nearest_neighbors as nearest_neighbors # 修改成 import utils.cpp_wrappers.cpp_subsampling.grid_subsampling as cpp_subsampling import utils.nearest_neighbors.nearest_neighbors as nearest_neighbors ... # 复制一个 起个自己名字 class ConfigSample: k_n = 16 # KNN num_layers = 5 # Number of layers num_points = 16000 # Number of input points # 包含背景类别,如果想排除背景类别, 修改 ignored_labels num_classes = 2 # Number of valid classes sub_grid_size = 0.01 # preprocess_parameter # Todo batch_size = 4 # batch_size during training val_batch_size = 2 # batch_size during validation and test train_steps = 500 # Number of steps per epochs val_steps = 3 # Number of validation steps per epoch sub_sampling_ratio = [4, 4, 4, 4, 2] # sampling ratio of random sampling at each layer d_out = [16, 64, 128, 256, 512] # feature dimension noise_init = 3.5 # noise initial parameter max_epoch = 100 # maximum epoch during training learning_rate = 1e-2 # initial learning rate lr_decays = {i: 0.95 for i in range(0, 500)} # decay rate of learning rate train_sum_dir = 'train_log' saving = True saving_path = None augment_scale_anisotropic = True augment_symmetries = [True, False, False] augment_rotation = 'vertical' augment_scale_min = 0.8 augment_scale_max = 1.2 augment_noise = 0.001 augment_occlusion = 'none' augment_color = 0.8 @staticmethod def get_class_weights(dataset_name): # pre-calculate the number of points in each category num_per_class = [] if dataset_name is 'S3DIS': num_per_class = np.array([3370714, 2856755, 4919229, 318158, 375640, 478001, 974733, 650464, 791496, 88727, 1284130, 229758, 2272837], dtype=np.int32) elif dataset_name is 'Semantic3D': num_per_class = np.array([5181602, 5012952, 6830086, 1311528, 10476365, 946982, 334860, 269353], dtype=np.int32) elif dataset_name is 'SemanticKITTI': num_per_class = np.array([55437630, 320797, 541736, 2578735, 3274484, 552662, 184064, 78858, 240942562, 17294618, 170599734, 6369672, 230413074, 101130274, 476491114, 9833174, 129609852, 4506626, 1168181]) # TODO 增加一个自己的类别 elif dataset_name is 'Sample': # 每一个类别点的数量 num_per_class = np.array([4401119, 148313]) weight = num_per_class / float(sum(num_per_class)) ce_label_weight = 1 / (weight + 0.02) return np.expand_dims(ce_label_weight, axis=0) ...
训练
- main_Sample.py (拷贝 main_S3DIS.py)
python
from os.path import join, exists
from RandLANet import Network
from tester_Railway import ModelTester
from helper_ply import read_ply
from helper_tool import Plot
from helper_tool import DataProcessing as DP
from helper_tool import ConfigRailway as cfg
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import numpy as np
import pickle, argparse, os
class Railway:
def __init__(self):
self.name = 'Sample'
# 最好给绝对路径
self.path = '/home/ab/workspace/train/randla-net-tf2-main/data/sample'
self.label_to_names = {0: 'background', 1: 'sample'}
self.num_classes = len(self.label_to_names)
self.label_values = np.sort([k for k, v in self.label_to_names.items()])
self.label_to_idx = {l: i for i, l in enumerate(self.label_values)}
# 如果想忽略背景类别 np.sort([0])
#self.ignored_labels = np.sort([0]) # TODO
self.ignored_labels = np.sort([]) # TODO
self.original_folder = join(self.path, 'original_data')
self.full_pc_folder = join(self.path, 'original_ply')
self.sub_pc_folder = join(self.path, 'input_{:.3f}'.format(cfg.sub_grid_size))
#训练、验证、测试数据都在original_data数据集中,需要做划分
self.val_split = ["20240430205457370","20240430205527591"]
self.test_split= ["20240430205530638"]
# Initial training-validation-testing files
self.train_files = []
self.val_files = []
self.test_files = []
cloud_names = [file_name[:-4] for file_name in os.listdir(self.original_folder) if file_name[-4:] == '.txt']
#根据文件名划分训练、验证、测试数据集
for pc_name in cloud_names:
pc_file=join(self.sub_pc_folder, pc_name + '.ply')
if pc_name in self.val_split:
self.val_files.append(pc_file)
elif pc_name in self.test_split:
self.test_files.append(pc_file)
else:
self.train_files.append(pc_file)
# Initiate containers
self.val_proj = []
self.val_labels = []
self.test_proj = []
self.test_labels = []
self.possibility = {}
self.min_possibility = {}
self.class_weight = {}
self.input_trees = {'training': [], 'validation': [], 'test': []}
self.input_colors = {'training': [], 'validation': [], 'test': []}
self.input_labels = {'training': [], 'validation': []}
# Ascii files dict for testing
self.ascii_files = {
'20240430205530638.ply': '20240430205530638-reduced.labels'}
self.load_sub_sampled_clouds(cfg.sub_grid_size)
def load_sub_sampled_clouds(self, sub_grid_size):
tree_path = join(self.path, 'input_{:.3f}'.format(sub_grid_size))
files = np.hstack((self.train_files, self.val_files, self.test_files))
for i, file_path in enumerate(files):
cloud_name = file_path.split('/')[-1][:-4]
print('Load_pc_' + str(i) + ': ' + cloud_name)
if file_path in self.val_files:
cloud_split = 'validation'
elif file_path in self.train_files:
cloud_split = 'training'
else:
cloud_split = 'test'
# Name of the input files
kd_tree_file = join(tree_path, '{:s}_KDTree.pkl'.format(cloud_name))
sub_ply_file = join(tree_path, '{:s}.ply'.format(cloud_name))
# read ply with data
data = read_ply(sub_ply_file)
sub_colors = np.vstack((data['red'], data['green'], data['blue'])).T
if cloud_split == 'test':
sub_labels = None
else:
sub_labels = data['class']
# Read pkl with search tree
with open(kd_tree_file, 'rb') as f:
search_tree = pickle.load(f)
self.input_trees[cloud_split] += [search_tree]
self.input_colors[cloud_split] += [sub_colors]
if cloud_split in ['training', 'validation']:
self.input_labels[cloud_split] += [sub_labels]
# Get validation and test re_projection indices
print('\nPreparing reprojection indices for validation and test')
for i, file_path in enumerate(files):
# get cloud name and split
cloud_name = file_path.split('/')[-1][:-4]
# Validation projection and labels
if file_path in self.val_files:
proj_file = join(tree_path, '{:s}_proj.pkl'.format(cloud_name))
with open(proj_file, 'rb') as f:
proj_idx, labels = pickle.load(f)
self.val_proj += [proj_idx]
self.val_labels += [labels]
# Test projection
if file_path in self.test_files:
proj_file = join(tree_path, '{:s}_proj.pkl'.format(cloud_name))
with open(proj_file, 'rb') as f:
proj_idx, labels = pickle.load(f)
self.test_proj += [proj_idx]
self.test_labels += [labels]
print('finished')
return
# Generate the input data flow
def get_batch_gen(self, split):
if split == 'training':
num_per_epoch = cfg.train_steps * cfg.batch_size
elif split == 'validation':
num_per_epoch = cfg.val_steps * cfg.val_batch_size
elif split == 'test':
num_per_epoch = cfg.val_steps * cfg.val_batch_size
# Reset possibility
self.possibility[split] = []
self.min_possibility[split] = []
self.class_weight[split] = []
# Random initialize
for i, tree in enumerate(self.input_trees[split]):
self.possibility[split] += [np.random.rand(tree.data.shape[0]) * 1e-3]
self.min_possibility[split] += [float(np.min(self.possibility[split][-1]))]
if split != 'test':
_, num_class_total = np.unique(np.hstack(self.input_labels[split]), return_counts=True)
self.class_weight[split] += [np.squeeze([num_class_total / np.sum(num_class_total)], axis=0)]
def spatially_regular_gen():
# Generator loop
for i in range(num_per_epoch): # num_per_epoch
# Choose the cloud with the lowest probability
cloud_idx = int(np.argmin(self.min_possibility[split]))
# choose the point with the minimum of possibility in the cloud as query point
point_ind = np.argmin(self.possibility[split][cloud_idx])
# Get all points within the cloud from tree structure
points = np.array(self.input_trees[split][cloud_idx].data, copy=False)
# print("points........." + str(points.shape))
# Center point of input region
center_point = points[point_ind, :].reshape(1, -1)
# Add noise to the center point
noise = np.random.normal(scale=cfg.noise_init / 10, size=center_point.shape)
pick_point = center_point + noise.astype(center_point.dtype)
query_idx = self.input_trees[split][cloud_idx].query(pick_point, k=cfg.num_points)[1][0]
# Shuffle index
query_idx = DP.shuffle_idx(query_idx)
# Get corresponding points and colors based on the index
queried_pc_xyz = points[query_idx]
queried_pc_xyz[:, 0:2] = queried_pc_xyz[:, 0:2] - pick_point[:, 0:2]
queried_pc_colors = self.input_colors[split][cloud_idx][query_idx]
if split == 'test':
queried_pc_labels = np.zeros(queried_pc_xyz.shape[0])
queried_pt_weight = 1
else:
queried_pc_labels = self.input_labels[split][cloud_idx][query_idx]
queried_pc_labels = np.array([self.label_to_idx[l] for l in queried_pc_labels])
queried_pt_weight = np.array([self.class_weight[split][0][n] for n in queried_pc_labels])
# Update the possibility of the selected points
dists = np.sum(np.square((points[query_idx] - pick_point).astype(np.float32)), axis=1)
delta = np.square(1 - dists / np.max(dists)) * queried_pt_weight
self.possibility[split][cloud_idx][query_idx] += delta
self.min_possibility[split][cloud_idx] = float(np.min(self.possibility[split][cloud_idx]))
if True:
yield (queried_pc_xyz,
queried_pc_colors.astype(np.float32),
queried_pc_labels,
query_idx.astype(np.int32),
np.array([cloud_idx], dtype=np.int32))
gen_func = spatially_regular_gen
gen_types = (tf.float32, tf.float32, tf.int32, tf.int32, tf.int32)
gen_shapes = ([None, 3], [None, 3], [None], [None], [None])
return gen_func, gen_types, gen_shapes
def get_tf_mapping(self):
# Collect flat inputs
def tf_map(batch_xyz, batch_features, batch_labels, batch_pc_idx, batch_cloud_idx):
batch_features = tf.map_fn(self.tf_augment_input, [batch_xyz, batch_features], dtype=tf.float32)
input_points = []
input_neighbors = []
input_pools = []
input_up_samples = []
for i in range(cfg.num_layers):
neigh_idx = tf.py_func(DP.knn_search, [batch_xyz, batch_xyz, cfg.k_n], tf.int32)
sub_points = batch_xyz[:, :tf.shape(batch_xyz)[1] // cfg.sub_sampling_ratio[i], :]
pool_i = neigh_idx[:, :tf.shape(batch_xyz)[1] // cfg.sub_sampling_ratio[i], :]
up_i = tf.py_func(DP.knn_search, [sub_points, batch_xyz, 1], tf.int32)
input_points.append(batch_xyz)
input_neighbors.append(neigh_idx)
input_pools.append(pool_i)
input_up_samples.append(up_i)
batch_xyz = sub_points
input_list = input_points + input_neighbors + input_pools + input_up_samples
input_list += [batch_features, batch_labels, batch_pc_idx, batch_cloud_idx]
return input_list
return tf_map
# data augmentation
@staticmethod
def tf_augment_input(inputs):
xyz = inputs[0]
features = inputs[1]
theta = tf.random_uniform((1,), minval=0, maxval=2 * np.pi)
# Rotation matrices
c, s = tf.cos(theta), tf.sin(theta)
cs0 = tf.zeros_like(c)
cs1 = tf.ones_like(c)
R = tf.stack([c, -s, cs0, s, c, cs0, cs0, cs0, cs1], axis=1)
stacked_rots = tf.reshape(R, (3, 3))
# Apply rotations
transformed_xyz = tf.reshape(tf.matmul(xyz, stacked_rots), [-1, 3])
# Choose random scales for each example
min_s = cfg.augment_scale_min
max_s = cfg.augment_scale_max
if cfg.augment_scale_anisotropic:
s = tf.random_uniform((1, 3), minval=min_s, maxval=max_s)
else:
s = tf.random_uniform((1, 1), minval=min_s, maxval=max_s)
symmetries = []
for i in range(3):
if cfg.augment_symmetries[i]:
symmetries.append(tf.round(tf.random_uniform((1, 1))) * 2 - 1)
else:
symmetries.append(tf.ones([1, 1], dtype=tf.float32))
s *= tf.concat(symmetries, 1)
# Create N x 3 vector of scales to multiply with stacked_points
stacked_scales = tf.tile(s, [tf.shape(transformed_xyz)[0], 1])
# Apply scales
transformed_xyz = transformed_xyz * stacked_scales
noise = tf.random_normal(tf.shape(transformed_xyz), stddev=cfg.augment_noise)
transformed_xyz = transformed_xyz + noise
# rgb = features[:, :3]
# stacked_features = tf.concat([transformed_xyz, rgb], axis=-1)
return transformed_xyz
def init_input_pipeline(self):
print('Initiating input pipelines')
cfg.ignored_label_inds = [self.label_to_idx[ign_label] for ign_label in self.ignored_labels]
gen_function, gen_types, gen_shapes = self.get_batch_gen('training')
gen_function_val, _, _ = self.get_batch_gen('validation')
gen_function_test, _, _ = self.get_batch_gen('test')
self.train_data = tf.data.Dataset.from_generator(gen_function, gen_types, gen_shapes)
self.val_data = tf.data.Dataset.from_generator(gen_function_val, gen_types, gen_shapes)
self.test_data = tf.data.Dataset.from_generator(gen_function_test, gen_types, gen_shapes)
self.batch_train_data = self.train_data.batch(cfg.batch_size)
self.batch_val_data = self.val_data.batch(cfg.val_batch_size)
self.batch_test_data = self.test_data.batch(cfg.val_batch_size)
map_func = self.get_tf_mapping()
self.batch_train_data = self.batch_train_data.map(map_func=map_func)
self.batch_val_data = self.batch_val_data.map(map_func=map_func)
self.batch_test_data = self.batch_test_data.map(map_func=map_func)
self.batch_train_data = self.batch_train_data.prefetch(cfg.batch_size)
self.batch_val_data = self.batch_val_data.prefetch(cfg.val_batch_size)
self.batch_test_data = self.batch_test_data.prefetch(cfg.val_batch_size)
iter = tf.data.Iterator.from_structure(self.batch_train_data.output_types, self.batch_train_data.output_shapes)
self.flat_inputs = iter.get_next()
self.train_init_op = iter.make_initializer(self.batch_train_data)
self.val_init_op = iter.make_initializer(self.batch_val_data)
self.test_init_op = iter.make_initializer(self.batch_test_data)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=0, help='the number of GPUs to use [default: 0]')
parser.add_argument('--mode', type=str, default='train', help='options: train, test, vis')
parser.add_argument('--model_path', type=str, default='None', help='pretrained model path')
FLAGS = parser.parse_args()
GPU_ID = FLAGS.gpu
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = str(GPU_ID)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
Mode = FLAGS.mode
dataset = Railway()
dataset.init_input_pipeline()
if Mode == 'train':
model = Network(dataset, cfg)
model.train(dataset)
elif Mode == 'test':
cfg.saving = False
model = Network(dataset, cfg)
if FLAGS.model_path is not 'None':
chosen_snap = FLAGS.model_path
else:
chosen_snapshot = -1
logs = np.sort([os.path.join('results', f) for f in os.listdir('results') if f.startswith('Log')])
chosen_folder = logs[-1]
snap_path = join(chosen_folder, 'snapshots')
snap_steps = [int(f[:-5].split('-')[-1]) for f in os.listdir(snap_path) if f[-5:] == '.meta']
chosen_step = np.sort(snap_steps)[-1]
chosen_snap = os.path.join(snap_path, 'snap-{:d}'.format(chosen_step))
print(".............. chosen_snap:" + chosen_snap)
tester = ModelTester(model, dataset, restore_snap=chosen_snap)
tester.test(model, dataset)
else:
##################
# Visualize data #
##################
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
sess.run(dataset.train_init_op)
while True:
flat_inputs = sess.run(dataset.flat_inputs)
pc_xyz = flat_inputs[0]
sub_pc_xyz = flat_inputs[1]
labels = flat_inputs[21]
Plot.draw_pc_sem_ins(pc_xyz[0, :, :], labels[0, :])
Plot.draw_pc_sem_ins(sub_pc_xyz[0, :, :], labels[0, 0:np.shape(sub_pc_xyz)[1]])
- 开始训练
python main_Sample.py --mode train --gpu 0