0
我对CNN相当新。这是我第一次使用keras,tensorflow等。我有一个load_weights函数的问题。我已经培训了CNN(cifar100),现在我想通过加载它的权重并评估它来测试它。load_weights Keras模型错误
这是错误,我得到的堆栈回溯:
Traceback (most recent call last):
File "<ipython-input-17-247d6312ea1b>", line 1, in <module>
runfile('/home/nikola/Desktop/cifar100-Version2.py', wdir='/home/nikola/Desktop')
File "/home/nikola/anaconda2/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 866, in runfile
execfile(filename, namespace)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 94, in execfile
builtins.execfile(filename, *where)
File "/home/nikola/Desktop/cifar100-Version2.py", line 80, in <module>
model.load_weights('cifar100_best_accuracy.hdf5')
File "/home/nikola/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 2520, in load_weights
self.load_weights_from_hdf5_group(f)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 2605, in load_weights_from_hdf5_group
K.batch_set_value(weight_value_tuples)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1045, in batch_set_value
assign_op = x.assign(assign_placeholder)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variables.py", line 575, in assign
return state_ops.assign(self._variable, value, use_locking=use_locking)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_state_ops.py", line 47, in assign
use_locking=use_locking, name=name)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2242, in create_op
set_shapes_for_outputs(ret)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1617, in set_shapes_for_outputs
shapes = shape_func(op)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1568, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/home/nikola/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 675, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimension 0 in both shapes must be equal, but are 3 and 32 for 'Assign_11' (op: 'Assign') with input shapes: [3,3,3,32], [32,3,3,3].
我试图延长keras cifar10代码cifar100代码。我设法训练它,但我也想评估它。通过评估,我可以确定我的模型是否好,它的得分是多少。
这是我的代码:
from __future__ import print_function
from keras.datasets import cifar100
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils, generic_utils
from six.moves import range
#import numpy as np
#import matplotlib.pyplot as plt
batch_size = 32
nb_classes = 100
classes = [...100 classes...`enter code here`]
test_only =True;
save_weights = True;
nb_epoch = 200
data_augmentation = True
# input image dimensions
img_rows, img_cols = 32, 32
# The CIFAR10 images are RGB.
img_channels = 3
# The data, shuffled and split between train and test sets:
(X_train, y_train), (X_test, y_test) = cifar100.load_data()
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
# Convert class vectors to binary class matrices.
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Convolution2D(32, 3, 3, border_mode='same',
input_shape=X_train.shape[1:]))
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Convolution2D(64, 3, 3, border_mode='same'))
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
if test_only:
model.load_weights('cifar100_best_accuracy.hdf5')
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
if not data_augmentation:
print('Not using data augmentation.')
model.fit(X_train, Y_train,
batch_size=batch_size,
nb_epoch=nb_epoch,
validation_data=(X_test, Y_test),
shuffle=True)
score = model.evaluate(X_test, Y_test, batch_size = batch_size)
print('Test score:', score)
else:
print('Using real-time data augmentation.')
# This will do preprocessing and realtime data augmentation:
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=0, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# Compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied).
datagen.fit(X_train)
model_check_point = ModelCheckpoint('cifar100_best_accuracy.hdf5', monitor='acc', verbose=0, save_best_only=True, save_weights_only=False, mode='auto')
# Fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(X_train, Y_train,
batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_epoch,
callbacks=[model_check_point],
validation_data=(X_test, Y_test))
看起来像是某处形状不匹配。我认为诀窍是在形状中设置正确的顺序:batch_size,图像高度,图像大小和通道数量。我认为你需要调试一下才能找出问题所在。如果我是你,我会减少模型到1层模型,以简化调试。 –
我已经在一台PC(Windows 10)上训练过CNN,并且我试图在另一台PC上的Ubuntu上load_weights。这两者之间的任何不匹配是否会使我成为问题? –
我想不出任何。你能否在同一台电脑上加载(Windows 10)? –