【问题标题】:couldn't train a model in keras无法在 keras 中训练模型
【发布时间】:2018-07-06 05:52:47
【问题描述】:

我正在尝试使用大小约为 19.2 GB 的 aflw dataset 在 keras 中训练用于人脸分析的多合一卷积模型。它成功显示模型摘要,但无法训练模型。

我有一台内存约为 4 GB 的计算机。

Loading pickle files
Loaded train, test and validation dataset
Loading test images
Loading validation images
dataset/adience.py:100: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.
  self.test_detection = self.test_dataset["is_face"].as_matrix()
Loaded all dataset and images
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            (None, 227, 227, 1)  0                                            
__________________________________________________________________________________________________
conv2d_1 (Conv2D)               (None, 55, 55, 96)   11712       input_1[0][0]                    
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, 55, 55, 96)   384         conv2d_1[0][0]                   
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D)  (None, 27, 27, 96)   0           batch_normalization_1[0][0]      
__________________________________________________________________________________________________
conv2d_2 (Conv2D)               (None, 27, 27, 256)  614656      max_pooling2d_1[0][0]            
__________________________________________________________________________________________________
batch_normalization_2 (BatchNor (None, 27, 27, 256)  1024        conv2d_2[0][0]                   
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D)  (None, 13, 13, 256)  0           batch_normalization_2[0][0]      
__________________________________________________________________________________________________
conv2d_3 (Conv2D)               (None, 13, 13, 384)  885120      max_pooling2d_2[0][0]            
__________________________________________________________________________________________________
conv2d_4 (Conv2D)               (None, 13, 13, 384)  1327488     conv2d_3[0][0]                   
__________________________________________________________________________________________________
conv2d_5 (Conv2D)               (None, 13, 13, 512)  1769984     conv2d_4[0][0]                   
__________________________________________________________________________________________________
conv2d_8 (Conv2D)               (None, 6, 6, 256)    393472      max_pooling2d_1[0][0]            
__________________________________________________________________________________________________
conv2d_9 (Conv2D)               (None, 6, 6, 256)    393472      conv2d_3[0][0]                   
__________________________________________________________________________________________________
max_pooling2d_4 (MaxPooling2D)  (None, 6, 6, 512)    0           conv2d_5[0][0]                   
__________________________________________________________________________________________________
concatenate_1 (Concatenate)     (None, 6, 6, 1024)   0           conv2d_8[0][0]                   
                                                                 conv2d_9[0][0]                   
                                                                 max_pooling2d_4[0][0]            
__________________________________________________________________________________________________
conv2d_10 (Conv2D)              (None, 6, 6, 256)    262400      concatenate_1[0][0]              
__________________________________________________________________________________________________
flatten_2 (Flatten)             (None, 9216)         0           conv2d_10[0][0]                  
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 2048)         18876416    flatten_2[0][0]                  
__________________________________________________________________________________________________
dropout_3 (Dropout)             (None, 2048)         0           dense_3[0][0]                    
__________________________________________________________________________________________________
dense_11 (Dense)                (None, 512)          1049088     dropout_3[0][0]                  
__________________________________________________________________________________________________
dropout_10 (Dropout)            (None, 512)          0           dense_11[0][0]                   
__________________________________________________________________________________________________
detection_probablity (Dense)    (None, 2)            1026        dropout_10[0][0]                 
==================================================================================================
Total params: 25,586,242
Trainable params: 25,585,538
Non-trainable params: 704
__________________________________________________________________________________________________
Epoch 1/10

它说 Epoch 1/10 但它停止了。是不是我电脑的计算问题?

【问题讨论】:

    标签: python python-2.7 keras conv-neural-network


    【解决方案1】:

    如果它开始这样运行,那么它可能有足够的内存来正常运行。您可以检查资源监视器以查看可用内存量。您还可以检查是否有任何 CPU 使用率。如果有 CPU 使用率,那么它可能只是训练非常缓慢。

    这是一个相当大的模型,因此在小 CPU 上训练可能需要很长时间。

    确保您的 Keras 详细程度设置为 1,以便每批都打印信息。虽然这是默认设置,但除非你更改它,否则它应该已经设置好了。

    model.fit(verbose=1)
    

    也尝试将批量大小调低到大小 1,看看是否有任何输出(因为它应该更快地完成较小的批量)。

    如果它运行正常但运行缓慢,最好的办法是让 GPU 运行它。如果你不能这样做,那么你可以尝试从源代码编译 Tensorflow,以确保你拥有所有 CPU 指令集和 MKL 库,如果你愿意,这可以加快速度。

    【讨论】:

    • 当我将批量大小设置为 1 时,它开始训练网络但我收到以下错误 Allocation of 75497472 exceeds 10% of system memory. 2018-07-18 09:47:05.318941: W tensorflow/core/framework/allocator.cc:101] Allocation of 75497472 exceeds 10% of system memory. 2018-07-18 09:47:05.679869: W tensorflow/core/framework/allocator.cc:101] Allocation of 75497472 exceeds 10% of system memory. 2018-07-18 09:47:05.793544: W tensorflow/core/framework/allocator.cc:101] 这是否意味着我必须使用 GPU 服务器进行训练?
    • 既然您知道它的工作原理,您可能希望尽可能将批处理大小恢复到至少 32 左右。如果该消息只是一个警告,那么您可以忽略它我猜如果它真的困扰您,您可以禁用来自 tensorflow 的警告。最终,尽管您的计算机具有非常少量的 RAM 来执行此类工作,但您可以非常努力地优化您的模型,或者获得一台更好的计算机,最好配备 GPU。尝试检查数据的数据类型,您也许可以通过降低精度来减少内存使用量
    猜你喜欢
    • 2019-01-20
    • 1970-01-01
    • 1970-01-01
    • 1970-01-01
    • 1970-01-01
    • 2018-08-28
    • 1970-01-01
    • 2020-09-01
    • 1970-01-01
    相关资源
    最近更新 更多