我正在为Alexnet＆＃39;运行代码在Keras（Theano后端）：
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])#, AUCEpoch,PrecisionEpoch,RecallEpoch,F1Epoch])
print(X_train.shape)
print(model.summary())
debug result:
(268, 3, 227, 227)
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
input_1 (InputLayer) (None, 3, 227, 227) 0
____________________________________________________________________________________________________
conv_1 (Convolution2D) (None, -1, 55, 96) 2636928 input_1[0][0]
____________________________________________________________________________________________________
maxpooling2d_1 (MaxPooling2D) (None, -1, 27, 96) 0 conv_1[0][0]
____________________________________________________________________________________________________
convpool_1 (Lambda) (None, -1, 27, 96) 0 maxpooling2d_1[0][0]
____________________________________________________________________________________________________
zeropadding2d_1 (ZeroPadding2D) (None, 3, 31, 96) 0 convpool_1[0][0]
____________________________________________________________________________________________________
lambda_1 (Lambda) (None, 1, 31, 96) 0 zeropadding2d_1[0][0]
____________________________________________________________________________________________________
lambda_2 (Lambda) (None, 1, 31, 96) 0 zeropadding2d_1[0][0]
____________________________________________________________________________________________________
conv_2_1 (Convolution2D) (None, -3, 27, 128) 307328 lambda_1[0][0]
____________________________________________________________________________________________________
conv_2_2 (Convolution2D) (None, -3, 27, 128) 307328 lambda_2[0][0]
____________________________________________________________________________________________________
conv_2 (Merge) (None, -6, 27, 128) 0 conv_2_1[0][0]
conv_2_2[0][0]
______________________________________________________________________________.......................
.......................
______________________________________________________________________________
mil_1 (Convolution2D) (None, -5, 6, 128) 16512 convpool_5[0][0]
____________________________________________________________________________________________________
mil_2 (Convolution2D) (None, -5, 6, 128) 16512 mil_1[0][0]
____________________________________________________________________________________________________
mil_3 (Convolution2D) (None, -5, 6, 2) 258 mil_2[0][0]
____________________________________________________________________________________________________
softmax (Softmax4D) (None, -5, 6, 2) 0 mil_3[0][0]
____________________________________________________________________________________________________
output (MaxPooling2D) (None, -1, 1, 2) 0 softmax[0][0]
____________________________________________________________________________________________________
flatten (Flatten) (None, -2) 0 output[0][0]
____________________________________________________________________________________________________
Recalcmil (Recalc) (None, -2) 0 flatten[0][0]
====================================================================================================
Total params: 5,497,730
Trainable params: 5,497,730
Non-trainable params: 0
____________________________________________________________________________________________________
None
ValueError: Error when checking model target: expected Recalcmil to have shape (None, -2) but got array with shape (268, 2)
我真的对natwork的输出形状感到困惑。我不明白是什么导致形状的负数。
以下是该模型的源代码：
np.random.seed(1)
#srng = RandomStreams(1)
fold = 2 # 4
valfold = 4
lr = 5e-5
nb_epoch = 500
batch_size = 80
l2factor = 1e-5
l1factor = 0#2e-7
weighted = False #True
noises = 50
#data_augmentation = True
data_augmentation = False
modelname = 'alexnet' # miccai16, alexnet, levynet, googlenet
#pretrain = True
pretrain = False
mil=True
savename = modelname+'_fd'+str(fold)+'_vf'+str(valfold)+'_lr'+str(lr)+'_l2'+str(l2factor)+'_l1'\
+str(l1factor)+'_ep'+str(nb_epoch)+'_bs'+str(batch_size)+'_w'+str(weighted)+'_dr'+str(False)+str(noises)+str(pretrain)+'_mil'+str(mil)
print(savename)
nb_classes = 2
# input image dimensions
img_rows, img_cols = 227, 227
# the CIFAR10 images are RGB
img_channels = 1
# the data, shuffled and split between train and test sets
trX, y_train, teX, y_test, teteX, y_test_test = inbreast.loaddataenhance(fold, 5, valfold=valfold)
trY = y_train.reshape((y_train.shape[0],1))
teY = y_test.reshape((y_test.shape[0],1))
teteY = y_test_test.reshape((y_test_test.shape[0],1))
print('tr, val, te pos num and shape')
print(trY.sum(), teY.sum(), teteY.sum(), trY.shape[0], teY.shape[0], teteY.shape[0])
ratio = trY.sum()*1./trY.shape[0]*1.
print('tr ratio'+str(ratio))
weights = np.array((ratio, 1-ratio))
# trYori = np.concatenate((1-trY, trY), axis=1)
# teY = np.concatenate((1-teY, teY), axis=1)
# teteY = np.concatenate((1-teteY, teteY), axis=1)
X_train = trX.reshape(-1, img_channels, img_rows, img_cols)
X_test = teX.reshape(-1, img_channels, img_rows, img_cols)
X_test_test = teteX.reshape(-1, img_channels, img_rows, img_cols)
# X_train = trX.reshape(-1, img_rows, img_cols, img_channels)
# X_test = teX.reshape(-1, img_rows, img_cols, img_channels
# X_test_test = teteX.reshape(-1, img_rows, img_cols, img_channels)
print('tr, val, te mean, std')
print(X_train.mean(), X_test.mean(), X_test_test.mean())
# 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)
Y_test_test = np_utils.to_categorical(y_test_test, nb_classes)
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'val samples')
print(X_test_test.shape[0], 'test samples')
model = Sequential()
if modelname == 'alexnet':
X_train_extend = np.zeros((X_train.shape[0],3, 227, 227))
for i in xrange(X_train.shape[0]):
rex = np.resize(X_train[i,:,:,:], (227, 227))
X_train_extend[i,0,:,:] = rex
X_train_extend[i,1,:,:] = rex
X_train_extend[i,2,:,:] = rex
X_train = X_train_extend
X_test_extend = np.zeros((X_test.shape[0], 3,227, 227))
for i in xrange(X_test.shape[0]):
rex = np.resize(X_test[i,:,:,:], (227, 227))
X_test_extend[i,0,:,:] = rex
X_test_extend[i,1,:,:] = rex
X_test_extend[i,2,:,:] = rex
X_test = X_test_extend
X_test_test_extend = np.zeros((X_test_test.shape[0], 3, 227, 227))
for i in xrange(X_test_test.shape[0]):
rex = np.resize(X_test_test[i,:,:,:], (227,227))
X_test_test_extend[i,0,:,:] = rex
X_test_test_extend[i,1,:,:] = rex
X_test_test_extend[i,2,:,:] = rex
X_test_test = X_test_test_extend
if pretrain: # 227*227
alexmodel = convnet('alexnet', weights_path='alexnet_weights.h5', heatmap=False, l1=l1factor, l2=l2factor)
model = convnet('alexnet', outdim=2, l1=l1factor, l2=l2factor, usemil=mil)
for layer, mylayer in zip(alexmodel.layers, model.layers):
print(layer.name)
if mylayer.name == 'mil_1':
break
else:
weightsval = layer.get_weights()
print(len(weightsval))
mylayer.set_weights(weightsval)
else:
model = convnet('alexnet', outdim=2, l1=l1factor,l2=l2factor, usemil=mil)
# let's train the model using SGD + momentum (how original).
sgd = Adam(lr=lr) #SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])#, AUCEpoch,PrecisionEpoch,RecallEpoch,F1Epoch])
print(X_train.shape)
print(model.summary())
#filepath = savename+'-{epoch:02d}-{val_loss:.2f}-{val_acc:.2f}.hdf5' #-{val_auc:.2f}-\
#{val_prec:.2f}-{val_reca:.2f}-{val_f1:.2f}.hdf5'
#checkpoint0 = ModelCheckpoint(filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='max')
#checkpoint1 = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
checkpoint0 = LossEpoch(savename, validation_data=(X_test, Y_test), interval=1)
checkpoint1 = ACCEpoch(savename, validation_data=(X_test, Y_test), interval=1)
checkpoint2 = AUCEpoch(savename, validation_data=(X_test, Y_test), interval=1)
checkpoint3 = PrecisionEpoch(savename, validation_data=(X_test, Y_test), interval=1)
checkpoint4 = RecallEpoch(savename, validation_data=(X_test, Y_test), interval=1)
checkpoint5 = F1Epoch(savename, validation_data=(X_test, Y_test), interval=1)
#checkpoint2 = ModelCheckpoint(filepath, monitor='val_auc', verbose=1, save_best_only=True, mode='max')
#checkpoint3 = ModelCheckpoint(filepath, monitor='val_prec', verbose=1, save_best_only=True, mode='max')
#checkpoint4 = ModelCheckpoint(filepath, monitor='val_reca', verbose=1, save_best_only=True, mode='max')
#checkpoint5 = ModelCheckpoint(filepath, monitor='val_f1', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint0, checkpoint1, checkpoint2, checkpoint3, checkpoint4, checkpoint5]
#callbacks_list = [AUCEpoch, PrecisionEpoch, RecallEpoch, F1Epoch, checkpoint0, checkpoint1]
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)
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=45.0, # 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,
zerosquare=True,
zerosquareh=noises,
zerosquarew=noises,
zerosquareintern=0.0) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(X_train)
# fit the model on the batches generated by datagen.flow()
if weighted:
model.fit_generator(datagen.flow(X_train, Y_train,
batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_epoch,
validation_data=(X_test, Y_test),
callbacks=callbacks_list,
class_weight=[weights[0], weights[1]])
else:
print('X_train shape:', X_train.shape)
print('Y_train shape:', Y_train.shape)
print('X_test shape:', X_test.shape)
print('Y_test shape:', Y_test.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'val samples')
print(X_test_test.shape[0], 'test samples')
model.fit_generator(datagen.flow(X_train, Y_train,
batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_epoch,
validation_data=(X_test, Y_test),
callbacks=callbacks_list)
我认为我输入的格式正确（无，3,227,227），但输出错误。
这是＆＃39; alexnet＆＃39;：
def AlexNet(outdim=1000, weights_path=None, heatmap=False, l1=0, l2=0, usemil=False, usemymil=False, k=1., usemysoftmil=False, softmink=1., softmaxk=1.,\
sparsemil=False, sparsemill1=0., sparsemill2=0., saveact=False):
l1factor = l1
l2factor = l2
if heatmap:
inputs = Input(shape=(3,None,None))
else:
inputs = Input(shape=(3,227,227))
conv_1 = Convolution2D(96, 11, 11,subsample=(4,4),activation='relu', W_regularizer=l1l2(l1=l1factor, l2=l2factor),
name='conv_1')(inputs)
conv_2 = MaxPooling2D((3, 3), strides=(2,2))(conv_1)
conv_2 = crosschannelnormalization(name="convpool_1")(conv_2)
conv_2 = ZeroPadding2D((2,2))(conv_2)
conv_2 = merge([
Convolution2D(128,5,5,activation="relu",name='conv_2_'+str(i+1), W_regularizer=l1l2(l1=l1factor, l2=l2factor))(
splittensor(ratio_split=2,id_split=i)(conv_2)
) for i in range(2)], mode='concat',concat_axis=1,name="conv_2")
conv_3 = MaxPooling2D((3, 3), strides=(2, 2))(conv_2)
conv_3 = crosschannelnormalization()(conv_3)
conv_3 = ZeroPadding2D((1,1))(conv_3)
conv_3 = Convolution2D(384,3,3,activation='relu',name='conv_3', W_regularizer=l1l2(l1=l1factor, l2=l2factor))(conv_3)
conv_4 = ZeroPadding2D((1,1))(conv_3)
conv_4 = merge([
Convolution2D(192,3,3,activation="relu",name='conv_4_'+str(i+1), W_regularizer=l1l2(l1=l1factor, l2=l2factor))(
splittensor(ratio_split=2,id_split=i)(conv_4)
) for i in range(2)], mode='concat',concat_axis=1,name="conv_4")
conv_5 = ZeroPadding2D((1,1))(conv_4)
conv_5 = merge([
Convolution2D(128,3,3,activation="relu",name='conv_5_'+str(i+1), W_regularizer=l1l2(l1=l1factor, l2=l2factor))(
splittensor(ratio_split=2,id_split=i)(conv_5)
) for i in range(2)], mode='concat',concat_axis=1,name="conv_5")
dense_1 = MaxPooling2D((3, 3), strides=(2,2),name="convpool_5")(conv_5)
if heatmap:
dense_1 = Convolution2D(4096,6,6,activation="relu",name="dense_1",W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_2 = Convolution2D(4096,1,1,activation="relu",name="dense_2",W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_3 = Convolution2D(outdim, 1,1,name="dense_3",W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_2)
prediction = Softmax4D(axis=1,name="softmax")(dense_3)
elif usemil:
dense_1 = Convolution2D(128,1,1,activation='relu',name='mil_1',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_2 = Convolution2D(128,1,1,activation='relu',name='mil_2',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_3 = Convolution2D(outdim,1,1,name='mil_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_2)
prediction_1 = Softmax4D(axis=1, name='softmax')(dense_3)
#prediction = Flatten(name='flatten')(prediction_1)
#dense_3 = Dense(outdim,name='dense_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(prediction)
#prediction = Activation("softmax",name="softmax2")(dense_3)
prediction_1 = MaxPooling2D((6,6), name='output')(prediction_1)
prediction = Flatten(name='flatten')(prediction_1)
prediction = Recalc(axis=1, name='Recalcmil')(prediction)
elif usemymil:
dense_1 = Convolution2D(128,1,1,activation='relu',name='mil_1',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_2 = Convolution2D(128,1,1,activation='relu',name='mil_2',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_3 = Convolution2D(1,1,1,activation='sigmoid',name='mil_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_2)
#prediction_1 = Softmax4D(axis=1, name='softmax')(dense_3)
#prediction = ExtractDim(axis=1, name='extract')(prediction_1)
prediction = Flatten(name='flatten')(dense_3)
prediction = ReRank(k=k, label=1, name='output')(prediction)
elif usemysoftmil:
dense_1 = Convolution2D(128,1,1,activation='relu',name='mil_1',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_2 = Convolution2D(128,1,1,activation='relu',name='mil_2',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_3 = Convolution2D(1,1,1,activation='sigmoid',name='mil_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_2)
#prediction_1 = Softmax4D(axis=1, name='softmax')(dense_3)
#prediction = ExtractDim(axis=1, name='extract')(prediction_1)
prediction = Flatten(name='flatten')(dense_3)
prediction = SoftReRank(softmink=softmink, softmaxk=softmaxk, label=1, name='output')(prediction)
elif sparsemil:
dense_1 = Convolution2D(128,1,1,activation='relu',name='mil_1',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_2 = Convolution2D(128,1,1,activation='relu',name='mil_2',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
prediction_1 = Convolution2D(1,1,1,activation='sigmoid',name='mil_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor),\
activity_regularizer=activity_l1l2(l1=sparsemill1, l2=sparsemill2))(dense_2)
# prediction_1 = Softmax4D(axis=1, name='softmax')(prediction_1)
#dense_3 = Convolution2D(outdim,1,1,name='mil_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_2)
#prediction_1 = Softmax4D(axis=1, name='softmax')(dense_3)
#prediction_1 = ActivityRegularizerOneDim(l1=sparsemill1, l2=sparsemill2)(prediction_1)
#prediction = MaxPooling2D((6,6), name='output')(prediction_1)
# prediction_1 = Convolution2D(1, 3, 3, activation='sigmoid', border_mode='same', name='smooth', \
# W_regularizer=l1l2(l1=l1factor, l2=l2factor), activity_regularizer=activity_l1l2(l1=sparsemill1, l2=sparsemill2))(prediction_1)
prediction = Flatten(name='flatten')(prediction_1)
if saveact:
model = Model(input=inputs, output=prediction)
return model
prediction = RecalcExpand(axis=1, name='Recalcmil')(prediction)
else:
dense_1 = Flatten(name="flatten")(dense_1)
dense_1 = Dense(4096, activation='relu',name='dense_1',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_1)
dense_2 = Dropout(0.5)(dense_1)
dense_2 = Dense(4096, activation='relu',name='dense_2',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_2)
dense_3 = Dropout(0.5)(dense_2)
dense_3 = Dense(outdim,name='dense_3',W_regularizer=l1l2(l1=l1factor, l2=l2factor))(dense_3)
prediction = Activation("softmax",name="softmax")(dense_3)
model = Model(input=inputs, output=prediction)
if weights_path:
model.load_weights(weights_path)
return model
答案 0 :(得分：1)
这是因为输入形状的格式与当前配置的通道排序不匹配。似乎您正在使用TensorFlow后端，默认使用＆＃34;频道最后＆＃34;，而您的输入形状采用格式＆＃34;频道优先＆＃34;。
只需将输入形状更改为（227,227,3）和相应的数据。