Python 2.7 ValueError:两种形状中的尺寸0必须相等，但对于'；分配'；（op:'；分配'；）输入形状：[5,5,3,30]，[30,1,5,5]

我正在使用keras编写简单的python代码，包括使用mnist标准数据集进行深入学习

这是我正在研究的代码：

import numpy
import cv2
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
import sys
from keras.preprocessing.image import ImageDataGenerator

K.set_image_dim_ordering('th')

img_width, img_height =28,28

def larger_model():
    # create model
    model = Sequential()
    model.add(Conv2D(30, (5, 5), input_shape=(3, 28, 28), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(15, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(10, activation='softmax')) #num_classes=10
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

img=cv2.imread(sys.argv[1])
img=cv2.resize(img,(img_width,img_height))
model=larger_model()

model.load_weights('./mnist.h5')

arr=numpy.array(img).reshape((3,img_width,img_height)).astype('float32') #

#arr=numpy.expand_dims(arr,axis=0)
arr/=255    
prediction=model.predict(arr)[0]          #

bestClass=''
bestConf= -1

for n in [0,1,2,3,4,5,6,7,8,9]:
    if prediction[n] > bestConf:
        bestClass = str[n]
        bestConf = prediction[n]

print " I think the digit is" + bestClass+ "with"+ str(bestConf*100) +"% confidence !"

这是即将出现的错误：

    Traceback (most recent call last):
  File "predict.py", line 39, in <module>
    model.load_weights('./mnist.h5')
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 720, in load_weights
    topology.load_weights_from_hdf5_group(f, layers)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 3048, in load_weights_from_hdf5_group
    K.batch_set_value(weight_value_tuples)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 2183, in batch_set_value
    assign_op = x.assign(assign_placeholder)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 516, in assign
    return state_ops.assign(self._variable, value, use_locking=use_locking)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/state_ops.py", line 271, in assign
    validate_shape=validate_shape)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_state_ops.py", line 45, in assign
    use_locking=use_locking, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2508, in create_op
    set_shapes_for_outputs(ret)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1873, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1823, in call_with_requiring
    return call_cpp_shape_fn(op, require_shape_fn=True)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
    debug_python_shape_fn, require_shape_fn)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 676, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Dimension 0 in both shapes must be equal, but are 5 and 30 for 'Assign' (op: 'Assign') with input shapes: [5,5,3,30], [30,1,5,5].

回溯（最近一次呼叫最后一次）：
文件“predict.py”，第39行，在
模型荷载重量（'./mnist.h5'）
文件“/usr/local/lib/python2.7/dist-packages/keras/models.py”，第720行，以装入重量表示
拓扑。从组（f，层）中加载权重
文件“/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py”，第3048行，从hdf5组加载权重
K.批量设置值（权重值元组）
文件“/usr/local/lib/python2.7/dist packages/keras/backend/tensorflow\u backend.py”，第2183行，在批处理设置值中
赋值（赋值占位符）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/ops/variables.py”，第516行，在assign中
返回状态分配（自变量、值、使用锁定=使用锁定）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/ops/state_ops.py”，第271行，在assign中
验证形状=验证形状）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/ops/gen_state_ops.py”，第45行，在assign中
使用锁定=使用锁定，名称=名称）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/framework/op_def_library.py”，第767行，在apply_op
op_def=op_def）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/framework/ops.py”，第2508行，在create_op中
为输出设置形状（ret）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/framework/ops.py”，第1873行，在集合形状中，用于输出
形状=形状函数（op）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/framework/ops.py”，第1823行，与
回传呼叫\u cpp\u shape\u fn（op，require\u shape\u fn=True）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/framework/common_shapes.py”，第610行，在call_cpp_shape_fn中
调试\u python\u形状\u fn，需要\u形状\u fn）
文件“/usr/local/lib/python2.7/dist packages/tensorflow/python/framework/common_shapes.py”，第676行，在“call\u cpp\u shape\u fn\u impl”中
提升值错误（错误消息）
ValueError:两个形状中的尺寸0必须相等，但对于输入形状为[5,5,3,30]、[30,1,5,5]的“分配”（op:“分配”）而言，尺寸0分别为5和30。

---

请帮助我，因为我在这里被困了很多天。提前谢谢

您尝试加载在不同体系结构上训练过的模型，然后是您定义的模型，因此它不知道如何分配变量。您尝试加载在不同体系结构上训练过的模型，然后是您定义的模型，因此它不知道如何分配变量。