Keras 使用 Lambda層詳解
阿新 • • 發佈:2020-06-11
我就廢話不多說了,大家還是直接看程式碼吧!
from tensorflow.python.keras.models import Sequential,Model from tensorflow.python.keras.layers import Dense,Flatten,Conv2D,MaxPool2D,Dropout,Conv2DTranspose,Lambda,Input,Reshape,Add,Multiply from tensorflow.python.keras.optimizers import Adam def deconv(x): height = x.get_shape()[1].value width = x.get_shape()[2].value new_height = height*2 new_width = width*2 x_resized = tf.image.resize_images(x,[new_height,new_width],tf.image.ResizeMethod.NEAREST_NEIGHBOR) return x_resized def Generator(scope='generator'): imgs_noise = Input(shape=inputs_shape) x = Conv2D(filters=32,kernel_size=(9,9),strides=(1,1),padding='same',activation='relu')(imgs_noise) x = Conv2D(filters=64,kernel_size=(3,3),strides=(2,2),activation='relu')(x) x = Conv2D(filters=128,activation='relu')(x) x1 = Conv2D(filters=128,activation='relu')(x) x1 = Conv2D(filters=128,activation='relu')(x1) x2 = Add()([x1,x]) x3 = Conv2D(filters=128,activation='relu')(x2) x3 = Conv2D(filters=128,activation='relu')(x3) x4 = Add()([x3,x2]) x5 = Conv2D(filters=128,activation='relu')(x4) x5 = Conv2D(filters=128,activation='relu')(x5) x6 = Add()([x5,x4]) x = MaxPool2D(pool_size=(2,2))(x6) x = Lambda(deconv)(x) x = Conv2D(filters=64,activation='relu')(x) x = Lambda(deconv)(x) x = Conv2D(filters=32,activation='relu')(x) x = Lambda(deconv)(x) x = Conv2D(filters=3,activation='tanh')(x) x = Lambda(lambda x: x+1)(x) y = Lambda(lambda x: x*127.5)(x) model = Model(inputs=imgs_noise,outputs=y) model.summary() return model my_generator = Generator() my_generator.compile(loss='binary_crossentropy',optimizer=Adam(0.7,decay=1e-3),metrics=['accuracy'])
補充知識:含有Lambda自定義層keras模型,儲存遇到的問題及解決方案
一,許多應用,keras含有的層已經不能滿足要求,需要透過Lambda自定義層來實現一些layer,這個情況下,只能儲存模型的權重,無法使用model.save來儲存模型。儲存時會報
TypeError: can't pickle _thread.RLock objects
二,解決方案,為了便於後續的部署,可以轉成tensorflow的PB進行部署。
from keras.models import load_model import tensorflow as tf import os,sys from keras import backend as K from tensorflow.python.framework import graph_util,graph_io def h5_to_pb(h5_weight_path,output_dir,out_prefix="output_",log_tensorboard=True): if not os.path.exists(output_dir): os.mkdir(output_dir) h5_model = build_model() h5_model.load_weights(h5_weight_path) out_nodes = [] for i in range(len(h5_model.outputs)): out_nodes.append(out_prefix + str(i + 1)) tf.identity(h5_model.output[i],out_prefix + str(i + 1)) model_name = os.path.splitext(os.path.split(h5_weight_path)[-1])[0] + '.pb' sess = K.get_session() init_graph = sess.graph.as_graph_def() main_graph = graph_util.convert_variables_to_constants(sess,init_graph,out_nodes) graph_io.write_graph(main_graph,name=model_name,as_text=False) if log_tensorboard: from tensorflow.python.tools import import_pb_to_tensorboard import_pb_to_tensorboard.import_to_tensorboard(os.path.join(output_dir,model_name),output_dir) def build_model(): inputs = Input(shape=(784,),name='input_img') x = Dense(64,activation='relu')(inputs) x = Dense(64,activation='relu')(x) y = Dense(10,activation='softmax')(x) h5_model = Model(inputs=inputs,outputs=y) return h5_model if __name__ == '__main__': if len(sys.argv) == 3: # usage: python3 h5_to_pb.py h5_weight_path output_dir h5_to_pb(h5_weight_path=sys.argv[1],output_dir=sys.argv[2])
以上這篇Keras 使用 Lambda層詳解就是小編分享給大家的全部內容了,希望能給大家一個參考,也希望大家多多支援我們。