Keras 从头开始培训VGG16

我试图从头开始训练我的VGG16网络。为此，我从

其中一位作者将代码编写为vgg-16_keras.py代码。在此代码中，预期的默认图像大小为224x224。我的输入图像也有相同的大小。所以，尺寸没有问题

接下来，我做了一些细微的更改，以便让体系结构准备好在我手头的一些示例图像上训练我的模型。当我尝试训练我的模型时，我得到了“负维”错误。为了调试代码，我尝试获取一些函数，这些函数为我提供了不同层的输出维度，但不幸的是没有

我正在发布我的代码以及错误消息

import keras
import numpy as np
from keras import backend as K
from keras.models import Sequential
from keras.layers import Activation, ZeroPadding2D, Convolution2D, MaxPooling2D, Dropout
from keras.layers.core import Dense, Flatten
from keras.optimizers import Adam
from keras.metrics import categorical_crossentropy
from keras.preprocessing.image import ImageDataGenerator
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import *
from matplotlib import pyplot as plt
from sklearn.metrics import confusion_matrix
import itertools
from matplotlib.pyplot import *


train_path="cats-and-dogs/train"
valid_path="cats-and-dogs/valid"
test_path="cats-and-dogs/test"

train_batches=ImageDataGenerator().flow_from_directory(train_path, target_size=(224,224), classes=['dog','cat'], batch_size=20)
valid_batches=ImageDataGenerator().flow_from_directory(valid_path, target_size=(224,224), classes=['dog','cat'], batch_size=10)
test_batches=ImageDataGenerator().flow_from_directory(test_path, target_size=(224,224), classes=['dog','cat'], batch_size=10)

imgs,labels=next(train_batches)

#Defining individual layers for oour CNN

l1=ZeroPadding2D((1,1),input_shape=(3,224,224))
l2=Convolution2D(64, 3, activation='relu')
l3=ZeroPadding2D((1,1))
l4=Convolution2D(64, 3, activation='relu')
l5=MaxPooling2D((2,2), strides=(2,2))

#
#
l6=ZeroPadding2D((1,1))
l7=Convolution2D(128, 3, activation='relu')
l8=ZeroPadding2D((1,1))
l9=Convolution2D(128, 3, activation='relu')
l10=MaxPooling2D((2,2), strides=(2,2))

l11=ZeroPadding2D((1,1))
l12=Convolution2D(256, 3, 3, activation='relu')
l13=ZeroPadding2D((1,1))
l14=Convolution2D(256, 3, 3, activation='relu')
l15=ZeroPadding2D((1,1))
l16=Convolution2D(256, 3, 3, activation='relu')
l17=MaxPooling2D((2,2), strides=(2,2))

l18=ZeroPadding2D((1,1))
l19=Convolution2D(512, 3, 3, activation='relu')
l20=ZeroPadding2D((1,1))
l21=Convolution2D(512, 3, 3, activation='relu')
l22=ZeroPadding2D((1,1))
l23=Convolution2D(512, 3, 3, activation='relu')
l24=MaxPooling2D((2,2), strides=(2,2))

l25=ZeroPadding2D((1,1))
l26=Convolution2D(512, 3, 3, activation='relu')
l27=ZeroPadding2D((1,1))
l28=Convolution2D(512, 3, 3, activation='relu')
l29=ZeroPadding2D((1,1))
l30=Convolution2D(512, 3, 3, activation='relu')
l31=MaxPooling2D((2,2), strides=(2,2))

l32=Flatten()
l33=Dense(4096, activation='relu')
l34=Dropout(0.5)
l35=Dense(4096, activation='relu')
l36=Dropout(0.5)
l37=Dense(1000, activation='softmax')

model = Sequential([l1,l2,l3,l4,l5,l6,l7,l8,l9,l10,l11,l12,l13,l14,l15,l16,l17,l18,l19,l20,l21,l22,l23,l24,l25,l26,l27,l28,l29,l30,l31,l32,l33,l34,l35,l36,l37])

#model = Sequential([l1,l2,l3,l4,l5,l6,l7,l8,l9,l10])
#model = Sequential([l1,l2,l3,l4,l5,l6,l7,l8,l9,l10])
print("Now Printing the model summary \n")
print(model.summary())  

请注意，我没有对代码中给定的维度、超参数值进行任何更改。我只是从文档的角度修改了代码，比如命名不同的层，添加注释等等

另外，建议我自己诊断未来此类错误的方法

错误消息如下所示：

runfile('/home/upendra/vgg_from_scratch', wdir='/home/upendra') Found 200 images belonging to 2 classes. Found 100 images belonging to 2 classes. Found 60 images belonging to 2 classes. /home/upendra/vgg_from_scratch:53: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(256, (3, 3), activation="relu")`   l12=Convolution2D(256, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:55: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(256, (3, 3), activation="relu")`   l14=Convolution2D(256, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:57: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(256, (3, 3), activation="relu")`   l16=Convolution2D(256, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:61: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(512, (3, 3), activation="relu")`   l19=Convolution2D(512, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:63: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(512, (3, 3), activation="relu")`   l21=Convolution2D(512, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:65: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(512, (3, 3), activation="relu")`   l23=Convolution2D(512, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:69: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(512, (3, 3), activation="relu")`   l26=Convolution2D(512, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:71: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(512, (3, 3), activation="relu")`   l28=Convolution2D(512, 3, 3, activation='relu') /home/upendra/vgg_from_scratch:73: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(512, (3, 3), activation="relu")`   l30=Convolution2D(512, 3, 3, activation='relu') Traceback (most recent call last):

  File "<ipython-input-4-56412ac381d0>", line 1, in <module>
    runfile('/home/upendra/vgg_from_scratch', wdir='/home/upendra')

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/spyder_kernels/customize/spydercustomize.py", line 668, in runfile
    execfile(filename, namespace)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/spyder_kernels/customize/spydercustomize.py", line 108, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "/home/upendra/vgg_from_scratch", line 83, in <module>
    model = Sequential([l1,l2,l3,l4,l5,l6,l7,l8,l9,l10,l11,l12,l13,l14,l15,l16,l17,l18,l19,l20,l21,l22,l23,l24,l25,l26,l27,l28,l29,l30,l31,l32,l33,l34,l35,l36,l37])

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/keras/engine/sequential.py", line 92, in __init__
    self.add(layer)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/keras/engine/sequential.py", line 185, in add
    output_tensor = layer(self.outputs[0])

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/keras/engine/base_layer.py", line 457, in __call__
    output = self.call(inputs, **kwargs)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/keras/layers/pooling.py", line 157, in call
    data_format=self.data_format)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/keras/layers/pooling.py", line 220, in _pooling_function
    pool_mode='max')

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 3880, in pool2d
    data_format=tf_data_format)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 2153, in max_pool
    name=name)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 4640, in max_pool
    data_format=data_format, name=name)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3414, in create_op
    op_def=op_def)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1756, in __init__
    control_input_ops)

  File "/home/upendra/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1592, in _create_c_op
    raise ValueError(str(e))

ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_9/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

runfile（'/home/upendra/vgg_from_scratch'，wdir='/home/upendra'）找到了属于两个类的200个图像。找到了100张属于2类的图片。找到60张属于2类的图片/home/upendra/vgg_from_scratch:53:UserWarning：更新对keras2api的`Conv2D`调用：`Conv2D（256，（3,3），activation=“relu”）`l12=coulsion2d（256,3,3，activation='relu'）/home/upendra/vgg_from_scratch:55:UserWarning：更新对keras2api的`Conv2D`调用：`Conv2D（256，（3,3），activation=“relu”）`l14=coulion2d（256,3,3，activation='relu'）/home/upendra/vgg_from_scratch:57:UserWarning：更新对keras2api的`Conv2D`调用：`Conv2D（256，（3,3），activation=“relu”）`l16=covolion2d（256,3,3，activation='relu'）/home/upendra/vgg_from_scratch:61:UserWarning：更新对keras2api的`Conv2D`调用：`Conv2D（512，（3,3），activation=“relu”）`l19=Conv2D（512,3,3，activation='relu'）/home/upendra/vgg_从头开始：63:UserWarning：更新对Keras 2 API的`Conv2D`调用：`Conv2D（512,3,3），activation='relu'）`l21=convion2d（512,3,3，activation='relu'）/home/upendra/vgg_从头开始：65:UserWarning：更新对Keras 2 API的`Conv2D`调用：`Conv2D:`Conv2D（512,3,3,3），activation=“relu”）`l23=Convolution2D（512,3,3，activation='relu'）/home/upendra/vgg_从头开始：69:UserWarning：更新对Keras 2 API的`Conv2D`调用：`Conv2D（512，（3,3），activation=“relu”）`l26=Convolution2D（512,3,3，activation='relu'））/home/upendra/vgg_from_scratch:71:UserWarning：更新对keras2api的`Conv2D`调用：`Conv2D（512，（3,3），activation=“relu”）`l28=coulsion2d（512,3,3，activation='relu'）/home/upendra/vgg_from_scratch:73:UserWarning：更新对keras2api的`Conv2D`调用：`Conv2D（512，（3,3），activation=“relu”）`l30=coulion2d（512,3,3，activation='relu'）回溯（最近一次呼叫最后一次）：
文件“”，第1行，在
运行文件（'/home/upendra/vgg_from_scratch'，wdir='/home/upendra'）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/spyder_kernels/customize/spydercurcstomize.py”，第668行，在运行文件中
execfile（文件名、命名空间）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/spyder_kernels/customize/spydercurcstomize.py”，第108行，在execfile中
exec（编译（f.read（），文件名，'exec'），命名空间）
文件“/home/upendra/vgg_from_scratch”，第83行，in
模型=顺序（[l1，l2，l3，l4，l5，l6，l7，l8，l9，l10，l11，l12，l13，l14，l15，l16，l17，l18，l19，l20，l21，l22，l23，l25，l26，l27，l28，l29，l29，l30，l31，l32，l34，l35，l36，l37]）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/keras/engine/sequential.py”，第92行，在__
添加（图层）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/keras/engine/sequential.py”，第185行，添加
输出张量=层（自输出[0]）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/keras/engine/base\u layer.py”，第457行，在调用中__
输出=自调用（输入，**kwargs）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/keras/layers/pooling.py”，调用中第157行
数据格式=自。数据格式）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/keras/layers/pooling.py”，第220行，在池函数中
池（模式=最大值）
pool2d中的文件“/home/upendra/anaconda3/lib/python3.6/site packages/keras/backend/tensorflow_backend.py”，第3880行
数据_格式=tf_数据_格式）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/nn_ops.py”，第2153行，在max_池中
名称=名称）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/gen_nn_ops.py”，第4640行，在max_pool中
数据格式=数据格式，名称=名称）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/op_def_library.py”，第787行，在“应用”op_helper中
op_def=op_def）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第3414行，在create_op中
op_def=op_def）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第1756行，在__
控制（输入操作）
文件“/home/upendra/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第1592行，在_create_c_op
提升值错误（str（e））
ValueError:输入形状为[？，1112128]的“max_Poolg2D_9/MaxPool”（op:“MaxPool”）的1减去2导致负维度大小。

我怀疑您的Conv2D定义有误

如果你有这样的东西：

Convolution2D(512, 3, 3, activation='relu')

我想你的意思是：

Convolution2D(512, (3, 3), activation='relu')

您可能应该避免使用位置参数以避免混淆，您的位置参数意味着：

Convolution2D(filters=512, kernel_size=3, strides=3, activation='relu')

我不记得VGG16的跨步是

（3，3）

，这是您定义的。如果我错了，请纠正我，我会更新这个（我没有把VGG架构烧坏）

通知