Как создать PB из сети, содержащей пакетную нормализацию - PullRequest
Новая
       22

Как создать PB из сети, содержащей пакетную нормализацию

0 голосов
/ 05 ноября 2019

Я хочу создать PB-файл из модели keras и предоставить ему EmguCV (или хотя бы opencv, предпочтительнее EmguCV), используя DnnInvoke.readnetfromTensorflow Я создаю сеть, используя код: 

from keras import backend as K
from keras.callbacks import *
from keras.layers import *
from keras.models import *
from keras.utils import *
from keras.optimizers import Adadelta, RMSprop, Adam, SGD
from keras.callbacks import ModelCheckpoint
from keras.callbacks import TensorBoard

from config import *


def ctc_lambda_func(args):
    iy_pred, ilabels, iinput_length, ilabel_length = args
    # the 2 is critical here since the first couple outputs of the RNN
    # tend to be garbage:
    iy_pred = iy_pred[:, 2:, :]  # no such influence
    return K.ctc_batch_cost(ilabels, iy_pred, iinput_length, ilabel_length)


def CRNN_model(is_training=True):
    inputShape = Input((width, height, 1), name='input')  # base on         Tensorflow backend
    conv_1 = Conv2D(64, (3, 3), activation='relu', padding='same')(inputShape)
    conv_2 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv_1)
    #batchnorm_2 = BatchNormalization()(conv_2)
    pool_2 = MaxPooling2D(pool_size=(2, 2))(conv_2)

    conv_3 = Conv2D(64, (3, 3), activation='relu', padding='same')(pool_2)
    conv_4 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv_3)
    #batchnorm_4 = BatchNormalization()(conv_4)
    pool_4 = MaxPooling2D(pool_size=(2, 2))(conv_4)

    conv_5 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool_4)
    conv_6 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv_5)
    pool_5 = MaxPool2D(pool_size=(2, 2))(conv_6)
    #batchnorm_6 = BatchNormalization()(conv_6)

    #bn_shape = batchnorm_6.get_shape()


    #print(bn_shape)

    #x_reshape = Reshape(target_shape=(int(bn_shape[1]), int(bn_shape[2] * bn_shape[3])))(batchnorm_6)
    #drop_reshape = Dropout(0.25, name='d1')(x_reshape)
    fl_1 = Flatten()(pool_5)
    fc_1 = Dense(256, activation='relu')(fl_1)

    #print(x_reshape.get_shape())
    #print(fc_1.get_shape())

    bi_LSTM_1 = Bidirectional(LSTM(256, return_sequences=True, kernel_initializer='he_normal'), merge_mode='sum')(fc_1)
    bi_LSTM_2 = Bidirectional(LSTM(128, return_sequences=True, kernel_initializer='he_normal'), merge_mode='concat')(bi_LSTM_1)

    #drop_rnn = Dropout(0.3, name='d2')(bi_LSTM_2)

    fc_2 = Dense(label_classes, kernel_initializer='he_normal', activation='softmax')(bi_LSTM_2)

    base_model = Model(inputs=[inputShape], outputs=fc_2) 

    labels = Input(name='the_labels', shape=[label_len], dtype='float32')
    input_length = Input(name='input_length', shape=[1], dtype='int64')
    label_length = Input(name='label_length', shape=[1], dtype='int64')

    loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([fc_2, labels, input_length, label_length])

    if is_training:
        return Model(inputs=[inputShape, labels, input_length, label_length], outputs=[loss_out]), base_model
    else:
        return base_model

и используюприведенный ниже код для создания файла .pb: 

import tensorflow as tf

mfname = './models/weights.01-0.080-0.007.hdf5'  # FIXME

tf.keras.backend.set_learning_phase(0)
sess = tf.keras.backend.get_session()
sess.as_default()

model = tf.keras.models.load_model(mfname, compile=False)

constant_graph = tf.graph_util.convert_variables_to_constants(
    sess,
    sess.graph.as_graph_def(),
    [out.op.name for out in model.outputs],
)
tf.train.write_graph(constant_graph, '', mfname[:-4] + '_graph.pb', as_text=False)

, но когда я вызываю DnnInvoke.readnetfromTensorflow, он показывает эту ошибку:

Emgu.CV.Util.CvException: 'OpenCV: Inputслой не найден: dens_1 / Tensordot / free '

Как я могу решить эту проблему?

...