Python 使用ImageDataGenerator将Imagenet数据加载到多个GPU

我正在尝试从文件夹加载Imagenet数据集，以便在ResNet18模型上对其进行训练。由于Imagenet是一个大型数据集，所以我尝试将数据样本分布在多个GPU上。当我检查是否使用nvidia smi进行培训时，它表明培训已在所述GPU上开始。然而，各个时期的训练准确率并没有提高，而且损失似乎也没有减少。我怀疑这可能是因为我的x_-train，y_-train在GPU上分配时是如何加载的

我想知道x_train，y_train=next（train_生成器）是否在每个历元中迭代所有数据集。如果不是，那么我只在125（批次大小=125）数据样本上进行培训

在多个GPU上分发数据时，如何有效地将张量数据馈送到from_tensor_slices（）

 strategy = tensorflow.distribute.MirroredStrategy()
 init_lr = 0.1
 epochs =60
 batch_size = 125
 My_wd=0.0001
 Loss = 'categorical_crossentropy'
 Optimizer = SGD(lr=init_lr,decay=0.0005, momentum=0.9, nesterov=False)

 def get_dataset():
     train_data_dir = 'Datasets/Imagenet/ILSVRC2012_img_train/ILSVRC2012_img_train'
     validation_data_dir = 'Datasets/Imagenet/ILSVRC2012_img_train/ILSVRC2012_img_train'
     datagen = ImageDataGenerator(rescale=1./255, horizontal_flip=True, validation_split = 0.2)
     val_datagen = ImageDataGenerator(rescale=1./255)
     train_generator = datagen.flow_from_directory(train_data_dir,target_size=(224,224),color_mode='rgb',batch_size= batch_size, subset= "training",class_mode='categorical', shuffle=True, seed=42) 
     val_generator = datagen.flow_from_directory(validation_data_dir,target_size=(224,224),color_mode='rgb',batch_size= batch_size, subset = "validation",class_mode='categorical', shuffle=True, seed=42) 

     x_train, y_train = next(train_generator)
     x_val,y_val = next(val_generator)

 return (
         tensorflow.data.Dataset.from_tensor_slices((x_train, y_train)).shuffle(1024977).repeat().batch(global_batch_size),
         tensorflow.data.Dataset.from_tensor_slices((x_train, y_train)).shuffle(256190).repeat().batch(global_batch_size),

     )
train_generator, val_generator = get_dataset()
 with strategy.scope():
     model=resnet(input_shape=input_shape,num_classes=1000)
     model.compile(loss=catcross_entropy_logits_loss() ,optimizer = Optimizer, metrics=['acc'])

 model.summary()
 history = model.fit(train_generator,
                               validation_data=val_generator,
                               epochs=epochs,
                               verbose=1,
                               use_multiprocessing=False,
                               workers=1,
                               callbacks=callbacks,
                               validation_steps=val_generator.n // batch_size,
                               steps_per_epoch =train_generator.n // batch_size)