Tensorflow转换RKNN模型求助 - Toybrick

from rknn.api import RKNN

import tensorflow as tf
import math
import time
import numpy as np
import os
import sys
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
ROOT_DIR = os.path.dirname(BASE_DIR)
sys.path.append(os.path.join(ROOT_DIR, 'utils'))
import tf_util
def placeholder_inputs(batch_size, num_point):
pointclouds_pl = tf.placeholder(tf.float32,
shape=(batch_size, num_point, 9))
labels_pl = tf.placeholder(tf.int32,
shape=(batch_size, num_point))
return pointclouds_pl, labels_pl
def get_model(point_cloud, is_training, bn_decay=None):
""" ConvNet baseline, input is BxNx3 gray image """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
# CONV
net = tf_util.conv2d(input_image, 64, [1,9], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv4', bn_decay=bn_decay)
points_feat1 = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv5', bn_decay=bn_decay)
# MAX
pc_feat1 = tf_util.max_pool2d(points_feat1, [num_point,1], padding='VALID', scope='maxpool1')
# FC
pc_feat1 = tf.reshape(pc_feat1, [batch_size, -1])
pc_feat1 = tf_util.fully_connected(pc_feat1, 256, bn=True, is_training=is_training, scope='fc1', bn_decay=bn_decay)
pc_feat1 = tf_util.fully_connected(pc_feat1, 128, bn=True, is_training=is_training, scope='fc2', bn_decay=bn_decay)
print(pc_feat1)
# CONCAT
pc_feat1_expand = tf.tile(tf.reshape(pc_feat1, [batch_size, 1, 1, -1]), [1, num_point, 1, 1])
points_feat1_concat = tf.concat(axis=3, values=[points_feat1, pc_feat1_expand])
# CONV
net = tf_util.conv2d(points_feat1_concat, 512, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv6')
net = tf_util.conv2d(net, 256, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv7')
net = tf_util.dropout(net, keep_prob=0.7, is_training=is_training, scope='dp1')
net = tf_util.conv2d(net, 13, [1,1], padding='VALID', stride=[1,1],
activation_fn=None, scope='conv8')
net = tf.squeeze(net, [2])
return net
def get_loss(pred, label):
""" pred: B,N,13
label: B,N """
loss = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=pred, labels=label)
return tf.reduce_mean(loss)
if __name__ == "__main__":
with tf.Graph().as_default():
a = tf.placeholder(tf.float32, shape=(32,4096,9))
net = get_model(a, tf.constant(True))
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
start = time.time()
for i in range(100):
print(i)
sess.run(net, feed_dict={a:np.random.rand(32,4096,9)})
print(time.time() - start)

import argparse
import math
import h5py
import numpy as np
import tensorflow as tf
import socket
import os
import sys
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
ROOT_DIR = os.path.dirname(BASE_DIR)
sys.path.append(BASE_DIR)
sys.path.append(ROOT_DIR)
sys.path.append(os.path.join(ROOT_DIR, 'utils'))
import provider
import tf_util
from model import *
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=0, help='GPU to use [default: GPU 0]')
parser.add_argument('--log_dir', default='log', help='Log dir [default: log]')
parser.add_argument('--num_point', type=int, default=4096, help='Point number [default: 4096]')
parser.add_argument('--max_epoch', type=int, default=50, help='Epoch to run [default: 50]')
parser.add_argument('--batch_size', type=int, default=24, help='Batch Size during training [default: 24]')
parser.add_argument('--learning_rate', type=float, default=0.001, help='Initial learning rate [default: 0.001]')
parser.add_argument('--momentum', type=float, default=0.9, help='Initial learning rate [default: 0.9]')
parser.add_argument('--optimizer', default='adam', help='adam or momentum [default: adam]')
parser.add_argument('--decay_step', type=int, default=300000, help='Decay step for lr decay [default: 300000]')
parser.add_argument('--decay_rate', type=float, default=0.5, help='Decay rate for lr decay [default: 0.5]')
parser.add_argument('--test_area', type=int, default=6, help='Which area to use for test, option: 1-6 [default: 6]')
FLAGS = parser.parse_args()
BATCH_SIZE = FLAGS.batch_size
NUM_POINT = FLAGS.num_point
MAX_EPOCH = FLAGS.max_epoch
NUM_POINT = FLAGS.num_point
BASE_LEARNING_RATE = FLAGS.learning_rate
GPU_INDEX = FLAGS.gpu
MOMENTUM = FLAGS.momentum
OPTIMIZER = FLAGS.optimizer
DECAY_STEP = FLAGS.decay_step
DECAY_RATE = FLAGS.decay_rate
LOG_DIR = FLAGS.log_dir
if not os.path.exists(LOG_DIR): os.mkdir(LOG_DIR)
os.system('cp model.py %s' % (LOG_DIR)) # bkp of model def
os.system('cp train.py %s' % (LOG_DIR)) # bkp of train procedure
LOG_FOUT = open(os.path.join(LOG_DIR, 'log_train.txt'), 'w')
LOG_FOUT.write(str(FLAGS)+'\n')
MAX_NUM_POINT = 4096
NUM_CLASSES = 13
BN_INIT_DECAY = 0.5
BN_DECAY_DECAY_RATE = 0.5
#BN_DECAY_DECAY_STEP = float(DECAY_STEP * 2)
BN_DECAY_DECAY_STEP = float(DECAY_STEP)
BN_DECAY_CLIP = 0.99
HOSTNAME = socket.gethostname()
ALL_FILES = provider.getDataFiles('indoor3d_sem_seg_hdf5_data/all_files.txt')
room_filelist = [line.rstrip() for line in open('indoor3d_sem_seg_hdf5_data/room_filelist.txt')]
# Load ALL data
data_batch_list = []
label_batch_list = []
for h5_filename in ALL_FILES:
data_batch, label_batch = provider.loadDataFile(h5_filename)
data_batch_list.append(data_batch)
label_batch_list.append(label_batch)
data_batches = np.concatenate(data_batch_list, 0)
label_batches = np.concatenate(label_batch_list, 0)
print(data_batches.shape)
print(label_batches.shape)
test_area = 'Area_'+str(FLAGS.test_area)
train_idxs = []
test_idxs = []
for i,room_name in enumerate(room_filelist):
if test_area in room_name:
test_idxs.append(i)
else:
train_idxs.append(i)
train_data = data_batches[train_idxs,...]
train_label = label_batches[train_idxs]
test_data = data_batches[test_idxs,...]
test_label = label_batches[test_idxs]
print(train_data.shape, train_label.shape)
print(test_data.shape, test_label.shape)
def log_string(out_str):
LOG_FOUT.write(out_str+'\n')
LOG_FOUT.flush()
print(out_str)
def get_learning_rate(batch):
learning_rate = tf.train.exponential_decay(
BASE_LEARNING_RATE, # Base learning rate.
batch * BATCH_SIZE, # Current index into the dataset.
DECAY_STEP, # Decay step.
DECAY_RATE, # Decay rate.
staircase=True)
learning_rate = tf.maximum(learning_rate, 0.00001) # CLIP THE LEARNING RATE!!
return learning_rate
def get_bn_decay(batch):
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)
return bn_decay
def train():
with tf.Graph().as_default():
with tf.device('/gpu:'+str(GPU_INDEX)):
pointclouds_pl, labels_pl = placeholder_inputs(BATCH_SIZE, NUM_POINT)
is_training_pl = tf.placeholder(tf.bool, shape=())
# Note the global_step=batch parameter to minimize.
# That tells the optimizer to helpfully increment the 'batch' parameter for you every time it trains.
batch = tf.Variable(0)
bn_decay = get_bn_decay(batch)
tf.summary.scalar('bn_decay', bn_decay)
# Get model and loss
pred = get_model(pointclouds_pl, is_training_pl, bn_decay=bn_decay)
loss = get_loss(pred, labels_pl)
tf.summary.scalar('loss', loss)
correct = tf.equal(tf.argmax(pred, 2), tf.to_int64(labels_pl))
accuracy = tf.reduce_sum(tf.cast(correct, tf.float32)) / float(BATCH_SIZE*NUM_POINT)
tf.summary.scalar('accuracy', accuracy)
# Get training operator
learning_rate = get_learning_rate(batch)
tf.summary.scalar('learning_rate', learning_rate)
if OPTIMIZER == 'momentum':
optimizer = tf.train.MomentumOptimizer(learning_rate, momentum=MOMENTUM)
elif OPTIMIZER == 'adam':
optimizer = tf.train.AdamOptimizer(learning_rate)
train_op = optimizer.minimize(loss, global_step=batch)
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Create a session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
config.log_device_placement = True
sess = tf.Session(config=config)
# Add summary writers
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(os.path.join(LOG_DIR, 'train'),
sess.graph)
test_writer = tf.summary.FileWriter(os.path.join(LOG_DIR, 'test'))
# Init variables
init = tf.global_variables_initializer()
sess.run(init, {is_training_pl:True})
ops = {'pointclouds_pl': pointclouds_pl,
'labels_pl': labels_pl,
'is_training_pl': is_training_pl,
'pred': pred,
'loss': loss,
'train_op': train_op,
'merged': merged,
'step': batch}
for epoch in range(MAX_EPOCH):
log_string('**** EPOCH %03d ****' % (epoch))
sys.stdout.flush()
train_one_epoch(sess, ops, train_writer)
eval_one_epoch(sess, ops, test_writer)
# Save the variables to disk.
if epoch % 10 == 0:
save_path = saver.save(sess, os.path.join(LOG_DIR, "model.ckpt"))
log_string("Model saved in file: %s" % save_path)
def train_one_epoch(sess, ops, train_writer):
""" ops: dict mapping from string to tf ops """
is_training = True
log_string('----')
current_data, current_label, _ = provider.shuffle_data(train_data[:,0:NUM_POINT,:], train_label)
file_size = current_data.shape[0]
num_batches = file_size // BATCH_SIZE
total_correct = 0
total_seen = 0
loss_sum = 0
for batch_idx in range(num_batches):
if batch_idx % 100 == 0:
print('Current batch/total batch num: %d/%d'%(batch_idx,num_batches))
start_idx = batch_idx * BATCH_SIZE
end_idx = (batch_idx+1) * BATCH_SIZE
feed_dict = {ops['pointclouds_pl']: current_data[start_idx:end_idx, :, :],
ops['labels_pl']: current_label[start_idx:end_idx],
ops['is_training_pl']: is_training,}
summary, step, _, loss_val, pred_val = sess.run([ops['merged'], ops['step'], ops['train_op'], ops['loss'], ops['pred']],
feed_dict=feed_dict)
train_writer.add_summary(summary, step)
pred_val = np.argmax(pred_val, 2)
correct = np.sum(pred_val == current_label[start_idx:end_idx])
total_correct += correct
total_seen += (BATCH_SIZE*NUM_POINT)
loss_sum += loss_val
log_string('mean loss: %f' % (loss_sum / float(num_batches)))
log_string('accuracy: %f' % (total_correct / float(total_seen)))
def eval_one_epoch(sess, ops, test_writer):
""" ops: dict mapping from string to tf ops """
is_training = False
total_correct = 0
total_seen = 0
loss_sum = 0
total_seen_class = [0 for _ in range(NUM_CLASSES)]
total_correct_class = [0 for _ in range(NUM_CLASSES)]
log_string('----')
current_data = test_data[:,0:NUM_POINT,:]
current_label = np.squeeze(test_label)
file_size = current_data.shape[0]
num_batches = file_size // BATCH_SIZE
for batch_idx in range(num_batches):
start_idx = batch_idx * BATCH_SIZE
end_idx = (batch_idx+1) * BATCH_SIZE
feed_dict = {ops['pointclouds_pl']: current_data[start_idx:end_idx, :, :],
ops['labels_pl']: current_label[start_idx:end_idx],
ops['is_training_pl']: is_training}
summary, step, loss_val, pred_val = sess.run([ops['merged'], ops['step'], ops['loss'], ops['pred']],
feed_dict=feed_dict)
test_writer.add_summary(summary, step)
pred_val = np.argmax(pred_val, 2)
correct = np.sum(pred_val == current_label[start_idx:end_idx])
total_correct += correct
total_seen += (BATCH_SIZE*NUM_POINT)
loss_sum += (loss_val*BATCH_SIZE)
for i in range(start_idx, end_idx):
for j in range(NUM_POINT):
l = current_label[i, j]
total_seen_class[l] += 1
total_correct_class[l] += (pred_val[i-start_idx, j] == l)
log_string('eval mean loss: %f' % (loss_sum / float(total_seen/NUM_POINT)))
log_string('eval accuracy: %f'% (total_correct / float(total_seen)))
log_string('eval avg class acc: %f' % (np.mean(np.array(total_correct_class)/np.array(total_seen_class,dtype=np.float))))
if __name__ == "__main__":
train()
LOG_FOUT.close()

W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/ceil.py:10: The name tf.ceil is deprecated. Please use tf.math.ceil instead.
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/depth_to_space.py:12: The name tf.depth_to_space is deprecated. Please use tf.compat.v1.depth_to_space instead.
W:tensorflow:
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
* https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
* https://github.com/tensorflow/addons
* https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/log.py:10: The name tf.log is deprecated. Please use tf.math.log instead.
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/random_normal.py:9: The name tf.random_normal is deprecated. Please use tf.random.normal instead.
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/random_uniform.py:9: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/upsample.py:13: The name tf.image.resize_images is deprecated. Please use tf.image.resize instead.
/home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/common/__init__.py:87: UserWarning: FrontendHandler.get_outputs_names is deprecated. It will be removed in future release.. Use node.outputs instead.
warnings.warn(message)
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/rknn/api/rknn.py:67: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.compat.v1.graph_util.extract_sub_graph`
E Catch exception when loading tensorflow model: pointnet_model_final.pb!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 215, in rknn.api.rknn_base.RKNNBase.load_tensorflow
E File "rknn/base/RKNNlib/converter/convert_tf.py", line 527, in rknn.base.RKNNlib.converter.convert_tf.convert_tf.pre_process
E File "rknn/base/RKNNlib/converter/tensorflowloader.py", line 77, in rknn.base.RKNNlib.converter.tensorflowloader.TF_Graph_Preprocess.pre_proces
E File "rknn/base/RKNNlib/converter/tensorflowloader.py", line 520, in rknn.base.RKNNlib.converter.tensorflowloader.TF_Graph_Preprocess.freeze_switch_path_v3
E File "rknn/base/RKNNlib/converter/tensorflowloader.py", line 436, in rknn.base.RKNNlib.converter.tensorflowloader.TF_Graph_Preprocess.freeze_switch_path_v3.fix_select_branch
E File "rknn/base/RKNNlib/converter/tf_util.py", line 198, in rknn.base.RKNNlib.converter.tf_util.TFProto_Util.change_input
E File "/home/toybrick/.local/lib/python3.7/site-packages/google/protobuf/internal/containers.py", line 204, in __getitem__
E return self._values[key]
E IndexError: list index out of range
done
--> Building model
Traceback (most recent call last):
File "rknn_transfer.py", line 26, in <module>
rknn.build()
File "/home/toybrick/.local/lib/python3.7/site-packages/rknn/api/rknn.py", line 222, in build
inputs = self.rknn_base.net.get_input_layers()
AttributeError: 'NoneType' object has no attribute 'get_input_layers'

from rknn.api import RKNN
if __name__ == '__main__':
# 创建RKNN执行对象
rknn = RKNN()
rknn.config()
# 加载TensorFlow模型
# tf_pb='digital_gesture.pb'指定待转换的TensorFlow模型
# inputs指定模型中的输入节点
# outputs指定模型中输出节点
# input_size_list指定模型输入的大小
print('--> Loading model')
rknn.load_tensorflow(tf_pb='pointnet_model_final.pb',
inputs=['Placeholder'],
outputs=['Squeeze'],
input_size_list=[[4096, 3]])
print('done')
# 创建解析pb模型
# do_quantization=False指定不进行量化
# 量化会减小模型的体积和提升运算速度，但是会有精度的丢失
print('--> Building model')
rknn.build(do_quantization=False)
print('done')
# 导出保存rknn模型文件
print('--> Exporting model')
rknn.export_rknn('./digital_gesture.rknn')
print('done')
# Release RKNN Context
print('--> Release model')
rknn.release()
print('done')