def train():
with tf.Graph().as_default(), tf.device('/cpu:0'):
batch = tf.Variable(0, trainable=False)
learning_rate = tf.train.exponential_decay(
BASE_LEARNING_RATE, # base learning rate
batch * batch_size, # global_var indicating the number of steps
DECAY_STEP, # step size
DECAY_RATE, # decay rate
staircase=True # Stair-case or continuous decreasing
)
learning_rate = tf.maximum(learning_rate, LEARNING_RATE_CLIP)
bn_momentum = tf.train.exponential_decay(
BN_INIT_DECAY,
batch*batch_size,
BN_DECAY_DECAY_STEP,
BN_DECAY_DECAY_RATE,
staircase=True)
bn_decay = tf.minimum(BN_DECAY_CLIP, 1 - bn_momentum)
lr_op = tf.summary.scalar('learning_rate', learning_rate)
batch_op = tf.summary.scalar('batch_number', batch)
bn_decay_op = tf.summary.scalar('bn_decay', bn_decay)
trainer = tf.train.AdamOptimizer(learning_rate)
# store tensors for different gpus
tower_grads = []
pointclouds_phs = []
input_label_phs = []
seg_phs =[]
is_training_phs =[]
# 变量
with tf.variable_scope(tf.get_variable_scope()):
for i in range(FLAGS.num_gpu):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % (TOWER_NAME, i)) as scope:
pointclouds_phs.append(tf.placeholder(tf.float32, shape=(batch_size, point_num, 3))) # for points 4*2048*3
input_label_phs.append(tf.placeholder(tf.float32, shape=(batch_size, NUM_CATEGORIES))) # for one-hot category label # 4*16
seg_phs.append(tf.placeholder(tf.int32, shape=(batch_size, point_num))) # for part labels # labels 4*2048
is_training_phs.append(tf.placeholder(tf.bool, shape=()))
# 预测值
# seg_pred : B*N*part_num=4*2048*50
seg_pred = model.get_model(pointclouds_phs[-1], input_label_phs[-1], \
is_training=is_training_phs[-1], bn_decay=bn_decay, cat_num=NUM_CATEGORIES, \
part_num=NUM_PART_CATS, batch_size=batch_size, num_point=point_num, weight_decay=FLAGS.wd) # cat_num=16,part_num=50
# loss:这个batch的总的loss
# per_instance_loss:每个点云的loss,shape=4
# per_instance_seg_pred_res : 每个点云的分割结果，由seg_pred取max得到的，shape=4*2048
loss, per_instance_seg_loss, per_instance_seg_pred_res \
= model.get_loss(seg_pred, seg_phs[-1])
# placeholder
total_training_loss_ph = tf.placeholder(tf.float32, shape=())
total_testing_loss_ph = tf.placeholder(tf.float32, shape=())
seg_training_acc_ph = tf.placeholder(tf.float32, shape=())
seg_testing_acc_ph = tf.placeholder(tf.float32, shape=())
seg_testing_acc_avg_cat_ph = tf.placeholder(tf.float32, shape=())
# scalar
total_train_loss_sum_op = tf.summary.scalar('total_training_loss', total_training_loss_ph)
total_test_loss_sum_op = tf.summary.scalar('total_testing_loss', total_testing_loss_ph)
seg_train_acc_sum_op = tf.summary.scalar('seg_training_acc', seg_training_acc_ph)
seg_test_acc_sum_op = tf.summary.scalar('seg_testing_acc', seg_testing_acc_ph)
seg_test_acc_avg_cat_op = tf.summary.scalar('seg_testing_acc_avg_cat', seg_testing_acc_avg_cat_ph)
tf.get_variable_scope().reuse_variables()
grads = trainer.compute_gradients(loss)
tower_grads.append(grads)
grads = average_gradients(tower_grads) # 计算平均梯度
train_op = trainer.apply_gradients(grads, global_step=batch)
saver = tf.train.Saver(tf.global_variables(), sharded=True, max_to_keep=20) # 保存变量
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
sess = tf.Session(config=config)
init = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
sess.run(init)
train_writer = tf.summary.FileWriter(SUMMARIES_FOLDER + '/train', sess.graph) # 保存graph
test_writer = tf.summary.FileWriter(SUMMARIES_FOLDER + '/test')
train_file_list = provider.getDataFiles(TRAINING_FILE_LIST) # [train0.h5,train1.h5,...train5.h5]
num_train_file = len(train_file_list) # 6
test_file_list = provider.getDataFiles(TESTING_FILE_LIST) # [ply_data_val0.h5]
num_test_file = len(test_file_list) # 1
# 保存终端输入
fcmd = open(os.path.join(LOG_STORAGE_PATH, 'cmd.txt'), 'w')
fcmd.write(str(FLAGS))
fcmd.close()
# write logs to the disk
flog = open(os.path.join(LOG_STORAGE_PATH, 'log.txt'), 'w')
def train_one_epoch(train_file_idx, epoch_num): # 输入为打乱后的顺序
is_training = True
# 遍历每一个train文件
for i in range(num_train_file):
cur_train_filename = os.path.join(hdf5_data_dir, train_file_list[train_file_idx[i]]) # 获取当前的train的点云文件
printout(flog, 'Loading train file ' + cur_train_filename)
cur_data, cur_labels, cur_seg = provider.load_h5_data_label_seg(cur_train_filename)
cur_data, cur_labels, order = provider.shuffle_data(cur_data, np.squeeze(cur_labels))
cur_seg = cur_seg[order, ...]
cur_labels_one_hot = convert_label_to_one_hot(cur_labels)
num_data = len(cur_labels)
num_batch = num_data // (FLAGS.num_gpu * batch_size) # For all working gpus num——batch代表这个train文件分几个batch
total_loss = 0.0
total_seg_acc = 0.0
# 对每一个batch
for j in range(num_batch):
begidx_0 = j * batch_size # 第一个gpu
endidx_0 = (j + 1) * batch_size
begidx_1 = (j + 1) * batch_size # 第二个gpu
endidx_1 = (j + 2) * batch_size
feed_dict = {
# For the first gpu
pointclouds_phs[0]: cur_data[begidx_0: endidx_0, ...], # 4*2048*3
input_label_phs[0]: cur_labels_one_hot[begidx_0: endidx_0, ...], # 4*16
seg_phs[0]: cur_seg[begidx_0: endidx_0, ...], # 4*2048 ，每一个数都在0-49之间
is_training_phs[0]: is_training,
# # For the second gpu
# pointclouds_phs[1]: cur_data[begidx_1: endidx_1, ...],
# input_label_phs[1]: cur_labels_one_hot[begidx_1: endidx_1, ...],
# seg_phs[1]: cur_seg[begidx_1: endidx_1, ...],
# is_training_phs[1]: is_training,
}
# train_op is for both gpus, and the others are for gpu_1
# 每一个batch的平均损失、每一个点云的损失、分割预测值
_, loss_val, per_instance_seg_loss_val, seg_pred_val, pred_seg_res \
= sess.run([train_op, loss, per_instance_seg_loss, seg_pred, per_instance_seg_pred_res], \
feed_dict=feed_dict)
# per_instance_part_acc = np.mean(pred_seg_res == cur_seg[begidx_1: endidx_1, ...], axis=1)
per_instance_part_acc = np.mean(pred_seg_res == cur_seg[begidx_0: endidx_0, ...], axis=1) # 每一个点云的分割精度
average_part_acc = np.mean(per_instance_part_acc) # 当前batch的平均精度
total_loss += loss_val
total_seg_acc += average_part_acc
# 至此，一个train文件遍历完成
total_loss = total_loss * 1.0 / num_batch # 每一个train文件都得到一个loss和seg_acc
total_seg_acc = total_seg_acc * 1.0 / num_batch
# 绘制图
lr_sum, bn_decay_sum, batch_sum, train_loss_sum, train_seg_acc_sum = sess.run(\
[lr_op, bn_decay_op, batch_op, total_train_loss_sum_op, seg_train_acc_sum_op], \
feed_dict={total_training_loss_ph: total_loss, seg_training_acc_ph: total_seg_acc})
train_writer.add_summary(train_loss_sum, i + epoch_num * num_train_file) # epoch_num是一个不断变化的值
train_writer.add_summary(lr_sum, i + epoch_num * num_train_file)
train_writer.add_summary(bn_decay_sum, i + epoch_num * num_train_file)
train_writer.add_summary(train_seg_acc_sum, i + epoch_num * num_train_file)
train_writer.add_summary(batch_sum, i + epoch_num * num_train_file)
printout(flog, '\tTanin_file: {},Training Total Mean_loss: {}'.format(i,total_loss)) # 每一个train文件的loss和acc
printout(flog, '\t\tTanin_file: {} ,Training Seg Accuracy: {}'.format(i,total_seg_acc))
def eval_one_epoch(epoch_num):
is_training = False
total_loss = 0.0
total_seg_acc = 0.0
total_seen = 0
total_seg_acc_per_cat = np.zeros((NUM_CATEGORIES)).astype(np.float32) # [0. 0. ....0.] 16个0
total_seen_per_cat = np.zeros((NUM_CATEGORIES)).astype(np.int32) # [0 0 0 0 ...0]
for i in range(num_test_file): # i= 0 num_test_file=1
cur_test_filename = os.path.join(hdf5_data_dir, test_file_list[i]) # ply_data_val0.h5
printout(flog, 'Loading test file ' + cur_test_filename) # ply_data_val0.h5
# 读取数据
# data = f['data'][:] # (1870, 2048, 3)
# label = f['label'][:] # (1870，1) 1870个点云的类别0-15
# seg = f['pid'][:] # (1870, 2048) ，表示每一个点属于的类别0-49，一共50类点
cur_data, cur_labels, cur_seg = provider.load_h5_data_label_seg(cur_test_filename)
cur_labels = np.squeeze(cur_labels) # shape:(1870,)
cur_labels_one_hot = convert_label_to_one_hot(cur_labels) # 1870*16
num_data = len(cur_labels) # 1870个点云
num_batch = num_data // batch_size # 467个batch
# Run on gpu_1, since the tensors used for evaluation are defined on gpu_1
for j in range(num_batch): # 0-466
begidx = j * batch_size
endidx = (j + 1) * batch_size
# feed_dict = {
# pointclouds_phs[1]: cur_data[begidx: endidx, ...],
# input_label_phs[1]: cur_labels_one_hot[begidx: endidx, ...],
# seg_phs[1]: cur_seg[begidx: endidx, ...],
# is_training_phs[1]: is_training}
feed_dict = {
pointclouds_phs[0]: cur_data[begidx: endidx, ...], # 4*2048*3
input_label_phs[0]: cur_labels_one_hot[begidx: endidx, ...], # 4*16
seg_phs[0]: cur_seg[begidx: endidx, ...], # 4*2048
is_training_phs[0]: is_training}
# pred_seg_res：每个点的分割结果 shape:4*2048
# seg_pred_val:分割结果，概率编码 shape:4*2048*50
# per_instance_seg_loss_val: 每一个点云的损失 shape:(4,)
# loss_val：当前batch的平均损失 shape:()
loss_val, per_instance_seg_loss_val, seg_pred_val, pred_seg_res \
= sess.run([loss, per_instance_seg_loss, seg_pred, per_instance_seg_pred_res], \
feed_dict=feed_dict)
per_instance_part_acc = np.mean(pred_seg_res == cur_seg[begidx: endidx, ...], axis=1) # 4个点云的每一个的分割精度 shape:(4,)
average_part_acc = np.mean(per_instance_part_acc) # 4个点云的平均分割精度
total_seen += 1 # 以batch为单位
total_loss += loss_val
total_seg_acc += average_part_acc # average_part_acc：当前batch的分割精度
for shape_idx in range(begidx, endidx): # 对当前batch中的每一个点云
total_seen_per_cat[cur_labels[shape_idx]] += 1 # 统计看过的每一类点云的数量
total_seg_acc_per_cat[cur_labels[shape_idx]] += per_instance_part_acc[shape_idx - begidx] # 统计每一类点云的精度
total_loss = total_loss * 1.0 / total_seen # 总的分割损失
total_seg_acc = total_seg_acc * 1.0 / total_seen # 总的平均分割精度，以batch为单位
# 绘制图
test_loss_sum, test_seg_acc_sum = sess.run(\
[total_test_loss_sum_op, seg_test_acc_sum_op], \
feed_dict={total_testing_loss_ph: total_loss, \
seg_testing_acc_ph: total_seg_acc})
test_writer.add_summary(test_loss_sum, (epoch_num+1) * num_train_file-1)
test_writer.add_summary(test_seg_acc_sum, (epoch_num+1) * num_train_file-1)
printout(flog, '\t\tTesting Total Mean_loss: %f' % total_loss)
printout(flog, '\t\tTesting Seg Accuracy: %f' % total_seg_acc)
for cat_idx in range(NUM_CATEGORIES): # 0-15
if total_seen_per_cat[cat_idx] > 0: # 如果看过这类物体，就打印看得数量
printout(flog, '\n\t\tCategory %s Object Number: %d' % (all_obj_cats[cat_idx][0], total_seen_per_cat[cat_idx]))
printout(flog, '\t\tCategory %s Seg Accuracy: %f' % (all_obj_cats[cat_idx][0], total_seg_acc_per_cat[cat_idx]/total_seen_per_cat[cat_idx]))
if not os.path.exists(MODEL_STORAGE_PATH):
os.mkdir(MODEL_STORAGE_PATH)
for epoch in range(TRAINING_EPOCHES):
printout(flog, '\n<<< Testing on the test dataset ...')
eval_one_epoch(epoch) # 评估
printout(flog, '\n>>> Training for the epoch %d/%d ...' % (epoch, TRAINING_EPOCHES))
train_file_idx = np.arange(0, len(train_file_list))
np.random.shuffle(train_file_idx)
train_one_epoch(train_file_idx, epoch) # 训练
if epoch % 5 == 0:
cp_filename = saver.save(sess, os.path.join(MODEL_STORAGE_PATH, 'epoch_' + str(epoch)+'.ckpt'))
printout(flog, 'Successfully store the checkpoint model into ' + cp_filename)
flog.flush()
flog.close()
def predict():
is_training = False
with tf.device('/gpu:' + str(gpu_to_use)):
pointclouds_ph, input_label_ph = placeholder_inputs()
is_training_ph = tf.placeholder(tf.bool, shape=())
seg_pred = model.get_model(pointclouds_ph, input_label_ph, \
cat_num=NUM_OBJ_CATS, part_num=NUM_PART_CATS, is_training=is_training_ph, \
batch_size=batch_size, num_point=point_num, weight_decay=0.0, bn_decay=None)
saver = tf.train.Saver()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
with tf.Session(config=config) as sess:
if not os.path.exists(output_dir):
os.mkdir(output_dir)
flog = open(os.path.join(output_dir, 'log.txt'), 'a+')
printout(flog, 'Loading model %s' % pretrained_model_path)
saver.restore(sess, pretrained_model_path)
printout(flog, 'Model restored.')
batch_data = np.zeros([batch_size, point_num, 3]).astype(np.float32)
total_acc = 0.0
total_seen = 0
total_acc_iou = 0.0
total_per_cat_acc = np.zeros((NUM_OBJ_CATS)).astype(np.float32)
total_per_cat_iou = np.zeros((NUM_OBJ_CATS)).astype(np.float32)
total_per_cat_seen = np.zeros((NUM_OBJ_CATS)).astype(np.int32)
ffiles = open(test_file_list, 'r')
lines = [line.rstrip() for line in ffiles.readlines()]
pts_files = [line.split()[0] for line in lines]
seg_files = [line.split()[1] for line in lines]
labels = [line.split()[2] for line in lines]
ffiles.close()
len_pts_files = len(pts_files)
for shape_idx in range(len_pts_files):
if shape_idx % 100 == 0:
printout(flog, '%d/%d ...' % (shape_idx, len_pts_files))
cur_gt_label = on2oid[labels[shape_idx]] # 0/1/.../15
cur_label_one_hot = np.zeros((1, NUM_OBJ_CATS), dtype=np.float32)
cur_label_one_hot[0, cur_gt_label] = 1
pts_file_to_load = os.path.join(ply_data_dir, pts_files[shape_idx])
seg_file_to_load = os.path.join(ply_data_dir, seg_files[shape_idx])
pts, seg = load_pts_seg_files(pts_file_to_load, seg_file_to_load,
objcats[cur_gt_label])
ori_point_num = len(seg)
batch_data[0,
...] = pc_augment_to_point_num(pc_normalize(pts),
point_num)
seg_pred_res = sess.run(seg_pred,
feed_dict={
pointclouds_ph: batch_data,
input_label_ph: cur_label_one_hot,
is_training_ph: is_training
})
seg_pred_res = seg_pred_res[0, ...]
iou_oids = object2setofoid[objcats[cur_gt_label]]
non_cat_labels = list(
set(np.arange(NUM_PART_CATS)).difference(set(iou_oids)))
mini = np.min(seg_pred_res)
seg_pred_res[:, non_cat_labels] = mini - 1000
seg_pred_val = np.argmax(seg_pred_res, axis=1)[:ori_point_num]
seg_acc = np.mean(seg_pred_val == seg)
total_acc += seg_acc
total_seen += 1
total_per_cat_seen[cur_gt_label] += 1
total_per_cat_acc[cur_gt_label] += seg_acc
mask = np.int32(seg_pred_val == seg)
total_iou = 0.0
iou_log = ''
for oid in iou_oids:
n_pred = np.sum(seg_pred_val == oid)
n_gt = np.sum(seg == oid)
n_intersect = np.sum(np.int32(seg == oid) * mask)
n_union = n_pred + n_gt - n_intersect
iou_log += '_' + str(n_pred) + '_' + str(n_gt) + '_' + str(
n_intersect) + '_' + str(n_union) + '_'
if n_union == 0:
total_iou += 1
iou_log += '_1\n'
else:
total_iou += n_intersect * 1.0 / n_union
iou_log += '_' + str(n_intersect * 1.0 / n_union) + '\n'
avg_iou = total_iou / len(iou_oids)
total_acc_iou += avg_iou
total_per_cat_iou[cur_gt_label] += avg_iou
if output_verbose:
output_color_point_cloud(
pts, seg,
os.path.join(output_dir,
str(shape_idx) + '_gt.obj'))
output_color_point_cloud(
pts, seg_pred_val,
os.path.join(output_dir,
str(shape_idx) + '_pred.obj'))
output_color_point_cloud_red_blue(
pts, np.int32(seg == seg_pred_val),
os.path.join(output_dir,
str(shape_idx) + '_diff.obj'))
with open(os.path.join(output_dir,
str(shape_idx) + '.log'), 'w') as fout:
fout.write('Total Point: %d\n\n' % ori_point_num)
fout.write('Ground Truth: %s\n' % objnames[cur_gt_label])
fout.write('Accuracy: %f\n' % seg_acc)
fout.write('IoU: %f\n\n' % avg_iou)
fout.write('IoU details: %s\n' % iou_log)
printout(flog, pretrained_model_path)
printout(flog, 'Accuracy: %f' % (total_acc / total_seen))
printout(flog, 'IoU: %f' % (total_acc_iou / total_seen))
for cat_idx in range(NUM_OBJ_CATS):
printout(
flog, '\t ' + objcats[cat_idx] + ' Total Number: ' +
str(total_per_cat_seen[cat_idx]))
if total_per_cat_seen[cat_idx] > 0:
printout(flog, '\t ' + objcats[cat_idx] + ' Accuracy: ' + \
str(total_per_cat_acc[cat_idx] / total_per_cat_seen[cat_idx]))
printout(flog, '\t ' + objcats[cat_idx] + ' IoU: '+ \
str(total_per_cat_iou[cat_idx] / total_per_cat_seen[cat_idx]))
def train():
with tf.Graph().as_default(), tf.device('/cpu:0'):
batch = tf.Variable(0, trainable=False)
learning_rate = tf.train.exponential_decay(
BASE_LEARNING_RATE, # base learning rate
batch * batch_size, # global_var indicating the number of steps
DECAY_STEP, # step size
DECAY_RATE, # decay rate
staircase=True # Stair-case or continuous decreasing
)
learning_rate = tf.maximum(learning_rate, LEARNING_RATE_CLIP)
bn_momentum = tf.train.exponential_decay(BN_INIT_DECAY,
batch * batch_size,
BN_DECAY_DECAY_STEP,
BN_DECAY_DECAY_RATE,
staircase=True)
bn_decay = tf.minimum(BN_DECAY_CLIP, 1 - bn_momentum)
lr_op = tf.summary.scalar('learning_rate', learning_rate)
batch_op = tf.summary.scalar('batch_number', batch)
bn_decay_op = tf.summary.scalar('bn_decay', bn_decay)
trainer = tf.train.AdamOptimizer(learning_rate)
# store tensors for different gpus
tower_grads = []
pointclouds_phs = []
input_label_phs = []
seg_phs = []
is_training_phs = []
with tf.variable_scope(tf.get_variable_scope()):
for i in range(FLAGS.num_gpu):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % (TOWER_NAME, i)) as scope:
pointclouds_phs.append(
tf.placeholder(tf.float32,
shape=(batch_size, point_num,
3))) # for points
input_label_phs.append(
tf.placeholder(
tf.float32,
shape=(batch_size, NUM_CATEGORIES
))) # for one-hot category label
seg_phs.append(
tf.placeholder(
tf.int32,
shape=(batch_size,
point_num))) # for part labels
is_training_phs.append(
tf.placeholder(tf.bool, shape=()))
seg_pred = model.get_model(pointclouds_phs[-1], input_label_phs[-1], \
is_training=is_training_phs[-1], bn_decay=bn_decay, cat_num=NUM_CATEGORIES, \
part_num=NUM_PART_CATS, batch_size=batch_size, num_point=point_num, weight_decay=FLAGS.wd)
loss, per_instance_seg_loss, per_instance_seg_pred_res \
= model.get_loss(seg_pred, seg_phs[-1])
total_training_loss_ph = tf.placeholder(tf.float32,
shape=())
total_testing_loss_ph = tf.placeholder(tf.float32,
shape=())
seg_training_acc_ph = tf.placeholder(tf.float32,
shape=())
seg_testing_acc_ph = tf.placeholder(tf.float32,
shape=())
seg_testing_acc_avg_cat_ph = tf.placeholder(tf.float32,
shape=())
total_train_loss_sum_op = tf.summary.scalar(
'total_training_loss', total_training_loss_ph)
total_test_loss_sum_op = tf.summary.scalar(
'total_testing_loss', total_testing_loss_ph)
seg_train_acc_sum_op = tf.summary.scalar(
'seg_training_acc', seg_training_acc_ph)
seg_test_acc_sum_op = tf.summary.scalar(
'seg_testing_acc', seg_testing_acc_ph)
seg_test_acc_avg_cat_op = tf.summary.scalar(
'seg_testing_acc_avg_cat',
seg_testing_acc_avg_cat_ph)
tf.get_variable_scope().reuse_variables()
grads = trainer.compute_gradients(loss)
tower_grads.append(grads)
grads = average_gradients(tower_grads)
train_op = trainer.apply_gradients(grads, global_step=batch)
saver = tf.train.Saver(tf.global_variables(),
sharded=True,
max_to_keep=20)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
sess = tf.Session(config=config)
init = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
sess.run(init)
train_writer = tf.summary.FileWriter(SUMMARIES_FOLDER + '/train',
sess.graph)
test_writer = tf.summary.FileWriter(SUMMARIES_FOLDER + '/test')
train_file_list = provider.getDataFiles(TRAINING_FILE_LIST)
num_train_file = len(train_file_list)
test_file_list = provider.getDataFiles(TESTING_FILE_LIST)
num_test_file = len(test_file_list)
fcmd = open(os.path.join(LOG_STORAGE_PATH, 'cmd.txt'), 'w')
fcmd.write(str(FLAGS))
fcmd.close()
# write logs to the disk
flog = open(os.path.join(LOG_STORAGE_PATH, 'log.txt'), 'w')
def train_one_epoch(train_file_idx, epoch_num):
is_training = True
for i in range(num_train_file):
cur_train_filename = os.path.join(
hdf5_data_dir, train_file_list[train_file_idx[i]])
printout(flog, 'Loading train file ' + cur_train_filename)
cur_data, cur_labels, cur_seg = provider.load_h5_data_label_seg(
cur_train_filename)
cur_data, cur_labels, order = provider.shuffle_data(
cur_data, np.squeeze(cur_labels))
cur_seg = cur_seg[order, ...]
cur_labels_one_hot = convert_label_to_one_hot(cur_labels)
num_data = len(cur_labels)
num_batch = num_data // (FLAGS.num_gpu * batch_size
) # For all working gpus
total_loss = 0.0
total_seg_acc = 0.0
for j in range(num_batch):
begidx_0 = j * batch_size
endidx_0 = (j + 1) * batch_size
begidx_1 = (j + 1) * batch_size
endidx_1 = (j + 2) * batch_size
feed_dict = {
# For the first gpu
pointclouds_phs[0]:
cur_data[begidx_0:endidx_0, ...],
input_label_phs[0]:
cur_labels_one_hot[begidx_0:endidx_0, ...],
seg_phs[0]:
cur_seg[begidx_0:endidx_0, ...],
is_training_phs[0]:
is_training,
# For the second gpu
pointclouds_phs[1]:
cur_data[begidx_1:endidx_1, ...],
input_label_phs[1]:
cur_labels_one_hot[begidx_1:endidx_1, ...],
seg_phs[1]:
cur_seg[begidx_1:endidx_1, ...],
is_training_phs[1]:
is_training,
}
# train_op is for both gpus, and the others are for gpu_1
_, loss_val, per_instance_seg_loss_val, seg_pred_val, pred_seg_res \
= sess.run([train_op, loss, per_instance_seg_loss, seg_pred, per_instance_seg_pred_res], \
feed_dict=feed_dict)
per_instance_part_acc = np.mean(
pred_seg_res == cur_seg[begidx_1:endidx_1, ...],
axis=1)
average_part_acc = np.mean(per_instance_part_acc)
total_loss += loss_val
total_seg_acc += average_part_acc
total_loss = total_loss * 1.0 / num_batch
total_seg_acc = total_seg_acc * 1.0 / num_batch
lr_sum, bn_decay_sum, batch_sum, train_loss_sum, train_seg_acc_sum = sess.run(\
[lr_op, bn_decay_op, batch_op, total_train_loss_sum_op, seg_train_acc_sum_op], \
feed_dict={total_training_loss_ph: total_loss, seg_training_acc_ph: total_seg_acc})
train_writer.add_summary(train_loss_sum,
i + epoch_num * num_train_file)
train_writer.add_summary(lr_sum,
i + epoch_num * num_train_file)
train_writer.add_summary(bn_decay_sum,
i + epoch_num * num_train_file)
train_writer.add_summary(train_seg_acc_sum,
i + epoch_num * num_train_file)
train_writer.add_summary(batch_sum,
i + epoch_num * num_train_file)
printout(flog, '\tTraining Total Mean_loss: %f' % total_loss)
printout(flog, '\t\tTraining Seg Accuracy: %f' % total_seg_acc)
def eval_one_epoch(epoch_num):
is_training = False
total_loss = 0.0
total_seg_acc = 0.0
total_seen = 0
total_seg_acc_per_cat = np.zeros(
(NUM_CATEGORIES)).astype(np.float32)
total_seen_per_cat = np.zeros((NUM_CATEGORIES)).astype(np.int32)
for i in range(num_test_file):
cur_test_filename = os.path.join(hdf5_data_dir,
test_file_list[i])
printout(flog, 'Loading test file ' + cur_test_filename)
cur_data, cur_labels, cur_seg = provider.load_h5_data_label_seg(
cur_test_filename)
cur_labels = np.squeeze(cur_labels)
cur_labels_one_hot = convert_label_to_one_hot(cur_labels)
num_data = len(cur_labels)
num_batch = num_data // batch_size
# Run on gpu_1, since the tensors used for evaluation are defined on gpu_1
for j in range(num_batch):
begidx = j * batch_size
endidx = (j + 1) * batch_size
feed_dict = {
pointclouds_phs[1]: cur_data[begidx:endidx, ...],
input_label_phs[1]: cur_labels_one_hot[begidx:endidx,
...],
seg_phs[1]: cur_seg[begidx:endidx, ...],
is_training_phs[1]: is_training
}
loss_val, per_instance_seg_loss_val, seg_pred_val, pred_seg_res \
= sess.run([loss, per_instance_seg_loss, seg_pred, per_instance_seg_pred_res], \
feed_dict=feed_dict)
per_instance_part_acc = np.mean(
pred_seg_res == cur_seg[begidx:endidx, ...], axis=1)
average_part_acc = np.mean(per_instance_part_acc)
total_seen += 1
total_loss += loss_val
total_seg_acc += average_part_acc
for shape_idx in range(begidx, endidx):
total_seen_per_cat[cur_labels[shape_idx]] += 1
total_seg_acc_per_cat[
cur_labels[shape_idx]] += per_instance_part_acc[
shape_idx - begidx]
total_loss = total_loss * 1.0 / total_seen
total_seg_acc = total_seg_acc * 1.0 / total_seen
test_loss_sum, test_seg_acc_sum = sess.run(\
[total_test_loss_sum_op, seg_test_acc_sum_op], \
feed_dict={total_testing_loss_ph: total_loss, \
seg_testing_acc_ph: total_seg_acc})
test_writer.add_summary(test_loss_sum,
(epoch_num + 1) * num_train_file - 1)
test_writer.add_summary(test_seg_acc_sum,
(epoch_num + 1) * num_train_file - 1)
printout(flog, '\tTesting Total Mean_loss: %f' % total_loss)
printout(flog, '\t\tTesting Seg Accuracy: %f' % total_seg_acc)
for cat_idx in range(NUM_CATEGORIES):
if total_seen_per_cat[cat_idx] > 0:
printout(
flog, '\n\t\tCategory %s Object Number: %d' %
(all_obj_cats[cat_idx][0],
total_seen_per_cat[cat_idx]))
printout(
flog, '\t\tCategory %s Seg Accuracy: %f' %
(all_obj_cats[cat_idx][0],
total_seg_acc_per_cat[cat_idx] /
total_seen_per_cat[cat_idx]))
if not os.path.exists(MODEL_STORAGE_PATH):
os.mkdir(MODEL_STORAGE_PATH)
for epoch in range(TRAINING_EPOCHES):
printout(flog, '\n<<< Testing on the test dataset ...')
eval_one_epoch(epoch)
printout(
flog, '\n>>> Training for the epoch %d/%d ...' %
(epoch, TRAINING_EPOCHES))
train_file_idx = np.arange(0, len(train_file_list))
np.random.shuffle(train_file_idx)
train_one_epoch(train_file_idx, epoch)
if epoch % 5 == 0:
cp_filename = saver.save(
sess,
os.path.join(MODEL_STORAGE_PATH,
'epoch_' + str(epoch) + '.ckpt'))
printout(
flog, 'Successfully store the checkpoint model into ' +
cp_filename)
flog.flush()
flog.close()
def predict():
is_training = False
with tf.device('/gpu:' + str(gpu_to_use)):
pointclouds_ph, input_label_ph = placeholder_inputs()
is_training_ph = tf.compat.v1.placeholder(tf.bool, shape=())
seg_pred = model.get_model(pointclouds_ph, input_label_ph, \
cat_num=NUM_OBJ_CATS, part_num=NUM_PART_CATS, is_training=is_training_ph, \
batch_size=batch_size, num_point=point_num, weight_decay=0.0, bn_decay=None)
saver = tf.train.Saver()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
with tf.Session(config=config) as sess:
if not os.path.exists(output_dir):
os.mkdir(output_dir)
flog = open(os.path.join(output_dir, 'log.txt'), 'a')
printout(flog, 'Loading model %s' % pretrained_model_path)
saver.restore(sess, pretrained_model_path)
printout(flog, 'Model restored.')
batch_data = np.zeros([batch_size, point_num, 3]).astype(np.float32)
total_acc = 0.0
total_seen = 0
total_acc_iou = 0.0
total_per_cat_acc = np.zeros((NUM_OBJ_CATS)).astype(np.float32)
total_per_cat_iou = np.zeros((NUM_OBJ_CATS)).astype(np.float32)
total_per_cat_seen = np.zeros((NUM_OBJ_CATS)).astype(np.int32)
ffiles = open(test_file_list, 'r')
lines = [line.rstrip() for line in ffiles.readlines()]
pts_files = [line.split()[0] for line in lines]
seg_files = [line.split()[1] for line in lines]
labels = [line.split()[2] for line in lines]
ffiles.close()
########################################################################################################
# load their data
# len_pts_files = len(pts_files)
# for shape_idx in range(len_pts_files):
# if shape_idx % 100 == 0:
# printout(flog, '%d/%d ...' % (shape_idx, len_pts_files))
# cur_gt_label = on2oid[labels[shape_idx]] # 0/1/.../15
# cur_label_one_hot = np.zeros((1, NUM_OBJ_CATS), dtype=np.float32)
# #cur_label_one_hot[0, cur_gt_label] = 1
# pts_file_to_load = os.path.join(ply_data_dir, pts_files[shape_idx])
# seg_file_to_load = os.path.join(ply_data_dir, seg_files[shape_idx])
# pts, seg = load_pts_seg_files(pts_file_to_load, seg_file_to_load, objcats[cur_gt_label])
# batch_data[0, ...] = pc_augment_to_point_num(pc_normalize(pts), point_num)
#########################################################################################################
# Load sapien data
cur_label_one_hot = np.zeros(
(1, NUM_OBJ_CATS), dtype=np.float32
) # dummy info for pure part segmentation without cat info
sapien_h5_files = os.listdir(sapien_h5_dir)
for h5_file_path in sapien_h5_files:
pts, seg = load_h5_data(os.path.join(sapien_h5_dir, h5_file_path),
point_num)
# only take one point cloud from the first camera angle at the first time instance
pts = pts[0, :]
seg = seg[0, :]
batch_data[0, ...] = pc_normalize(pts)
#########################################################################################################
ori_point_num = len(seg)
seg_pred_res = sess.run(seg_pred,
feed_dict={
pointclouds_ph: batch_data,
input_label_ph: cur_label_one_hot,
is_training_ph: is_training
})
seg_pred_res = seg_pred_res[0, ...]
#iou_oids = object2setofoid[objcats[cur_gt_label]]
#non_cat_labels = list(set(np.arange(NUM_PART_CATS)).difference(set(iou_oids)))
#mini = np.min(seg_pred_res)
#seg_pred_res[:, non_cat_labels] = mini - 1000
seg_pred_val = np.argmax(seg_pred_res, axis=1)[:ori_point_num]
seg_acc = np.mean(seg_pred_val == seg)
total_acc += seg_acc
total_seen += 1
#total_per_cat_seen[cur_gt_label] += 1
#total_per_cat_acc[cur_gt_label] += seg_acc
#mask = np.int32(seg_pred_val == seg)
# total_iou = 0.0
# iou_log = ''
# for oid in iou_oids:
# n_pred = np.sum(seg_pred_val == oid)
# n_gt = np.sum(seg == oid)
# n_intersect = np.sum(np.int32(seg == oid) * mask)
# n_union = n_pred + n_gt - n_intersect
# iou_log += '_' + str(n_pred)+'_'+str(n_gt)+'_'+str(n_intersect)+'_'+str(n_union)+'_'
# if n_union == 0:
# total_iou += 1
# iou_log += '_1\n'
# else:
# total_iou += n_intersect * 1.0 / n_union
# iou_log += '_'+str(n_intersect * 1.0 / n_union)+'\n'
# avg_iou = total_iou / len(iou_oids)
# total_acc_iou += avg_iou
# total_per_cat_iou[cur_gt_label] += avg_iou
if output_verbose:
output_color_point_cloud(
pts, seg,
os.path.join(output_dir,
str(h5_file_path) + '_gt.obj'))
output_color_point_cloud(
pts, seg_pred_val,
os.path.join(output_dir,
str(h5_file_path) + '_pred.obj'))
output_color_point_cloud_red_blue(
pts, np.int32(seg == seg_pred_val),
os.path.join(output_dir,
str(h5_file_path) + '_diff.obj'))
with open(os.path.join(output_dir,
str(h5_file_path) + '.log'),
'w') as fout:
printout(flog, str(h5_file_path) + ':\n')
fout.write('Total Point: %d\n\n' % ori_point_num)
printout(flog, 'Total Point: %d\n\n' % ori_point_num)
#fout.write('Ground Truth: %s\n' % objnames[cur_gt_label])
fout.write('Accuracy: %f\n' % seg_acc)
printout(flog, 'Accuracy: %f\n' % seg_acc)
#fout.write('IoU: %f\n\n' % avg_iou)
#fout.write('IoU details: %s\n' % iou_log)
printout(flog, 'Accuracy: %f' % (total_acc / total_seen))
