Keras'fit_generator额外的训练值

Question

train_datagen = ImageDataGenerator(
                    rescale=1./255,
                    shear_range=0.1,
                    zoom_range=0.1,
                    rotation_range=5.,
                    width_shift_range=0.1,
                    height_shift_range=0.1)

val_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
                    train_data_dir,
                    target_size = (img_width, img_height),
                    batch_size = 20,
                    shuffle = True,
                    classes = TYPES,
                class_mode = 'categorical')

validation_generator = val_datagen.flow_from_directory(
                    val_data_dir,
                    target_size=(img_width, img_height),
                    batch_size=20,
                    shuffle = True,
                    classes = TYPES,
                    class_mode = 'categorical')

model.fit_generator(
                train_generator,
                samples_per_epoch = 2000,
                nb_epoch = 20
            )

Epoch 14/50
 480/2000 [======>.......................] - ETA: 128s - loss: 0.8708

Epoch 13/50
2021/2000 [==============================] - 171s - loss: 0.7973 - acc: 0.7041 

我的ImageGenerators从文件夹中读取2261次训练和567次测试图像.我试图用2000 samples_per_epoch和20 batch_size训练我的模型.对于samples_per_epoch,Batch_size可以被整除,但不知何故它正在添加额外的值并显示警告:

(UserWarning:Epoch包含的不仅仅是samples_per_epoch样本,可能会影响学习结果.samples_per_epoch正确设置以避免此警告).

它适用于Single-Gpu但如果我尝试使用Multi-Gpus进行训练,则会出现以下错误:

InvalidArgumentError(参见上面的回溯):不兼容的形状:[21] vs. [20] [[Node:Equal = Equal [T = DT_INT64,_device ="/ job:localhost/replica:0/task:0/gpu:0 "](ArgMax,ArgMax_1)]] [[节点:渐变/ concat_25_grad/Slice_1/_10811 = _Recvclient_terminated = false,recv_device ="/ job:localhost/replica:0/task:0/gpu:1",send_device ="/ job:localhost/replica:0/task:0/cpu:0",send_device_incarnation = 1,tensor_name ="edge_101540_gradients/concat_25_grad/Slice_1",tensor_type = DT_FLOAT,_device ="/ job:localhost/replica:0/task:0/GPU:1" ]]

我正在使用该代码进行模型并行化:

谢谢你的帮助...

Answer 1

训练数据数量必须等于samples_per_epoch \xc3\x97\xe3\x80\x80batch_size。\n请将训练数据数量减少1条数据，使其达到2260。\nsteps_per_epoch=113\nbatch_size=20

\n