时间:2021-05-22
之前希望在手机端使用深度模型做OCR,于是尝试在手机端部署tensorflow模型,用于图像分类。
思路主要是想使用tflite部署到安卓端,但是在使用tflite的时候发现模型的精度大幅度下降,已经不能支持业务需求了,最后就把OCR模型调用写在服务端了,但是精度下降的原因目前也没有找到,现在这里记录一下。
工作思路:
1.训练图像分类模型;2.模型固化成pb;3.由pb转成tflite文件;
但是使用python 的tf interpreter 调用tflite文件就已经出现精度下降的问题,android端部署也是一样。
1.网络结构
from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_function import tensorflow as tfslim = tf.contrib.slim def ttnet(images, num_classes=10, is_training=False, dropout_keep_prob=0.5, prediction_fn=slim.softmax, scope='TtNet'): end_points = {} with tf.variable_scope(scope, 'TtNet', [images, num_classes]): net = slim.conv2d(images, 32, [3, 3], scope='conv1') # net = slim.conv2d(images, 64, [3, 3], scope='conv1_2') net = slim.max_pool2d(net, [2, 2], 2, scope='pool1') net = slim.batch_norm(net, activation_fn=tf.nn.relu, scope='bn1') # net = slim.conv2d(net, 128, [3, 3], scope='conv2_1') net = slim.conv2d(net, 64, [3, 3], scope='conv2') net = slim.max_pool2d(net, [2, 2], 2, scope='pool2') net = slim.conv2d(net, 128, [3, 3], scope='conv3') net = slim.max_pool2d(net, [2, 2], 2, scope='pool3') net = slim.conv2d(net, 256, [3, 3], scope='conv4') net = slim.max_pool2d(net, [2, 2], 2, scope='pool4') net = slim.batch_norm(net, activation_fn=tf.nn.relu, scope='bn2') # net = slim.conv2d(net, 512, [3, 3], scope='conv5') # net = slim.max_pool2d(net, [2, 2], 2, scope='pool5') net = slim.flatten(net) end_points['Flatten'] = net # net = slim.fully_connected(net, 1024, scope='fc3') net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout3') logits = slim.fully_connected(net, num_classes, activation_fn=None, scope='fc4') end_points['Logits'] = logits end_points['Predictions'] = prediction_fn(logits, scope='Predictions') return logits, end_pointsttnet.default_image_size = 28 def ttnet_arg_scope(weight_decay=0.0): with slim.arg_scope( [slim.conv2d, slim.fully_connected], weights_regularizer=slim.l2_regularizer(weight_decay), weights_initializer=tf.truncated_normal_initializer(stddev=0.1), activation_fn=tf.nn.relu) as sc: return sc基于slim,由于是一个比较简单的分类问题,网络结构也很简单,几个卷积加池化。
测试效果是很棒的。真实样本测试集能达到99%+的准确率。
2.模型固化,生成pb文件
#coding:utf-8 from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport tensorflow as tffrom nets import nets_factoryimport cv2import osimport numpy as npfrom datasets import dataset_factoryfrom preprocessing import preprocessing_factoryfrom tensorflow.python.platform import gfileslim = tf.contrib.slim#todo#support arbitray image size and num_class tf.app.flags.DEFINE_string( 'checkpoint_path', '/tmp/tfmodel/', 'The directory where the model was written to or an absolute path to a ' 'checkpoint file.') tf.app.flags.DEFINE_string( 'model_name', 'inception_v3', 'The name of the architecture to evaluate.')tf.app.flags.DEFINE_string( 'preprocessing_name', None, 'The name of the preprocessing to use. If left ' 'as `None`, then the model_name flag is used.')FLAGS = tf.app.flags.FLAGStf.app.flags.DEFINE_integer( 'eval_image_size', None, 'Eval image size')tf.app.flags.DEFINE_integer( 'eval_image_height', None, 'Eval image height')tf.app.flags.DEFINE_integer( 'eval_image_width', None, 'Eval image width')tf.app.flags.DEFINE_string( 'export_path', './ttnet_1.0_37_32.pb', 'the export path of the pd file')FLAGS = tf.app.flags.FLAGSNUM_CLASSES = 37 def main(_): network_fn = nets_factory.get_network_fn( FLAGS.model_name, num_classes=NUM_CLASSES, is_training=False) # pre_image = tf.placeholder(tf.float32, [None, None, 3], name='input_data') # preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name # image_preprocessing_fn = preprocessing_factory.get_preprocessing( # preprocessing_name, # is_training=False) # image = image_preprocessing_fn(pre_image, FLAGS.eval_image_height, FLAGS.eval_image_width) # images2 = tf.expand_dims(image, 0) images2 = tf.placeholder(tf.float32, (None,32, 32, 3),name='input_data') logits, endpoints = network_fn(images2) with tf.Session() as sess: output = tf.identity(endpoints['Predictions'],name="output_data") with gfile.GFile(FLAGS.export_path, 'wb') as f: f.write(sess.graph_def.SerializeToString()) if __name__ == '__main__': tf.app.run()3.生成tflite文件
import tensorflow as tf graph_def_file = "/datastore1/Colonist_Lord/Colonist_Lord/workspace/models/model_files/passport_model_with_tflite/ocr_frozen.pb"input_arrays = ["input_data"]output_arrays = ["output_data"] converter = tf.lite.TFLiteConverter.from_frozen_graph( graph_def_file, input_arrays, output_arrays)tflite_model = converter.convert()open("converted_model.tflite", "wb").write(tflite_model)使用pb文件进行测试,效果正常;使用tflite文件进行测试,精度下降严重。下面附上pb与tflite测试代码。
pb测试代码
with tf.gfile.GFile(graph_filename, "rb") as f: graph_def = tf.GraphDef() graph_def.ParseFromString(f.read()) with tf.Graph().as_default() as graph: tf.import_graph_def(graph_def) input_node = graph.get_tensor_by_name('import/input_data:0') output_node = graph.get_tensor_by_name('import/output_data:0') with tf.Session() as sess: for image_file in image_files: abs_path = os.path.join(image_folder, image_file) img = cv2.imread(abs_path).astype(np.float32) img = cv2.resize(img, (int(input_node.shape[1]), int(input_node.shape[2]))) output_data = sess.run(output_node, feed_dict={input_node: [img]}) index = np.argmax(output_data) label = dict_laebl[index] dst_floder = os.path.join(result_folder, label) if not os.path.exists(dst_floder): os.mkdir(dst_floder) cv2.imwrite(os.path.join(dst_floder, image_file), img) count += 1tflite测试代码
model_path = "converted_model.tflite" #"/datastore1/Colonist_Lord/Colonist_Lord/data/passport_char/ocr.tflite"interpreter = tf.contrib.lite.Interpreter(model_path=model_path)interpreter.allocate_tensors() # Get input and output tensors.input_details = interpreter.get_input_details()output_details = interpreter.get_output_details()for image_file in image_files: abs_path = os.path.join(image_folder,image_file) img = cv2.imread(abs_path).astype(np.float32) img = cv2.resize(img, tuple(input_details[0]['shape'][1:3])) # input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32) interpreter.set_tensor(input_details[0]['index'], [img]) interpreter.invoke() output_data = interpreter.get_tensor(output_details[0]['index']) index = np.argmax(output_data) label = dict_laebl[index] dst_floder = os.path.join(result_folder,label) if not os.path.exists(dst_floder): os.mkdir(dst_floder) cv2.imwrite(os.path.join(dst_floder,image_file),img) count+=1最后也算是绕过这个问题解决了业务需求,后面有空的话,还是会花时间研究一下这个问题。
如果有哪个大佬知道原因,希望不吝赐教。
补充知识:.pb 转tflite代码,使用量化,减小体积,converter.post_training_quantize = True
import tensorflow as tfpath = "/home/python/Downloads/a.pb" # pb文件位置和文件名inputs = ["input_images"] # 模型文件的输入节点名称classes = ['feature_fusion/Conv_7/Sigmoid','feature_fusion/concat_3'] # 模型文件的输出节点名称# converter = tf.contrib.lite.TocoConverter.from_frozen_graph(path, inputs, classes, input_shapes={'input_images':[1, 320, 320, 3]})converter = tf.lite.TFLiteConverter.from_frozen_graph(path, inputs, classes, input_shapes={'input_images': [1, 320, 320, 3]})converter.post_training_quantize = Truetflite_model = converter.convert()open("/home/python/Downloads/aNew.tflite", "wb").write(tflite_model)以上这篇tensorflow pb to tflite 精度下降详解就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
声明:本页内容来源网络,仅供用户参考;我单位不保证亦不表示资料全面及准确无误,也不保证亦不表示这些资料为最新信息,如因任何原因,本网内容或者用户因倚赖本网内容造成任何损失或损害,我单位将不会负任何法律责任。如涉及版权问题,请提交至online#300.cn邮箱联系删除。
1.tensorflow模型文件打包成PB文件importtensorflowastffromtensorflow.python.toolsimportfree
最近在学习tensorflow自带的量化工具的相关知识,其中遇到的一个问题是从tensorflow保存好的ckpt文件或者是保存后的.pb文件(这里的pb是把权
一,直接保存pb1,首先我们当然可以直接在tensorflow训练中直接保存为pb为格式,保存pb的好处就是使用场景是实现创建模型与使用模型的解耦,使得创建模型
由于项目需要,需要将TensorFlow保存的模型从ckpt文件转换为pb文件。importosfromtensorflow.pythonimportpywra
目标是想把在服务器上用pytorch训练好的模型转换为可以在移动端运行的tflite模型。最直接的思路是想把pytorch模型转换为tensorflow的模型,