Keras 当我在epoch=1的情况下添加了每个epoch的步长时,训练预计到达时间为5小时
traindatagenerator=imagegenerator.flowfromdataframe(traindf,directory=IMAGEDIR,xcol=“imagename”,ycol=“target”,classmode=“raw”,batchsize=25,targetsize=(240240),shuffle=True)ValidDataFrame=imagegenerator.flowfromdataframe(valdf,directory=IMAGEDIR,xcol=“imagename”,ycol=“target”,classmode=“raw”,batchsize=25,targetsize=(240240),shuffle=True) classweights=classweight.computeclassweight('balanced',np.unique(traindatagenerator.labels),traindatagenerator.labels) 创建模型 model=get_model() 编译模型 compile(loss='binary\u crossentropy',optimizer='sgd',metrics=[tf.keras.metrics.AUC()) 创建回调 checkpoint=keras.callbacks.ModelCheckpoint('model'+str(foldvar)+'.h5',monitor='valaccurity',verbose=1,savebest_only=True,mode='max') 回调\u列表=[检查点] history=model.fitgenerator(traindatagenerator,validationdata=validdatagenerator,stepsperepoch=int(math.ceil(1.*Xtrain.shape[0]//25)),validationsteps=int(math.ceil(1.*XVal.shape[0]//25)),回调=callbackList,classweight=classweights,epoch=1)Keras 当我在epoch=1的情况下添加了每个epoch的步长时,训练预计到达时间为5小时,keras,resnet,Keras,Resnet,traindatagenerator=imagegenerator.flowfromdataframe(traindf,directory=IMAGEDIR,xcol=“imagename”,ycol=“target”,classmode=“raw”,batchsize=25,targetsize=(240240),shuffle=True)ValidDataFrame=imagegenerator.flowfromdataframe(valdf,directory=IMAGEDIR,xcol=