我正在尝试实现CapsuleNet来对某些数字进行分类。所有图像都是RGB图像，已转换为灰度并调整为 32 X 32 ，数据集具有 10 个分类输出。
X_train_all.shape ：
(2075, 32, 32, 1)
y_train_all.shape ：(2075, 10)
以下是我到目前为止尝试过的内容。
首先，定义CapsNet模型。以下是胶囊网络的主要架构，包括 PrimaryCaps 和 DigitCaps 等。
def CapsNet(input_shape, n_class, routings):
x = layers.Input(shape=input_shape)
# Layer 1
conv1 = layers.Conv2D()(x)
# Layer 2
primarycaps = PrimaryCap()
# Layer 3
digitcaps = CapsuleLayer()(primarycaps)
# Layer 4
out_caps = Length(name='capsnet')(digitcaps)
# Decoder network.
y = layers.Input()
masked_by_y = Mask()([digitcaps, y])
masked = Mask()(digitcaps)
# Shared Decoder model in training and prediction
decoder = models.Sequential(name='decoder')
decoder.add(layers.Dense(512, activation='relu', input_dim=16*n_class))
decoder.add(layers.Dense(1024, activation='relu'))
decoder.add(layers.Dense(np.prod(input_shape), activation='sigmoid'))
decoder.add(layers.Reshape(target_shape=input_shape, name='out_recon'))
# Models for training and evaluation (prediction)
train_model = models.Model([x, y], [out_caps, decoder(masked_by_y)])
evals_model = models.Model(x, [out_caps, decoder(masked)])
return train_model, evals_model
这仅返回train_model和eval_model。现在，下面是我已经实施的实际培训过程。
def train_caps(model, data, epoch_size_frac=1.0):
# unpacking the data
(x_train, y_train), (x_val, y_val) = data
# compile the model
model.compile (....)
# --------------Begin Training with data augmentation --------------
def train_generator (...)
# Training with data augmentation.
history = model.fit_generator (...)
return model
现在要训练模型并在其上拟合数据，我使用了 K折叠交叉验证方法。假设它是K折=5。就像下面的代码一样，我们保存了5折模型并节省了重量。
cvscores = []
for train, val in kfold.split(X_train_all, y_train_all):
print ('Fold: ', Fold)
# define model
model, eval_model = CapsNet ( ... )
X_train = X_train_all[train]
X_val = X_train_all[val]
y_train = y_train_all[train]
y_val = y_train_all[val]
# train -
train_caps( ... ) # calling actual training
# # Save each fold model
model_name = 'Fold_'+ str(Fold) + '.h5'
model.save(model_name)
# evaluate the model
scores = model.evaluate(X_val, y_val, verbose = 0)
print("%s: %.2f%%" % (model.metrics_names[7], scores[3]*100))
cvscores.append(scores[3] * 100)
Fold = Fold + 1
问题出现在评估部分。 scores = model.evaluate(X_val, y_val, verbose = 0)并显示：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-36-12f206477b39> in <module>()
----> 1 scores = model.evaluate(X_val, Y_val, verbose = 0)
2 print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[[[218.],
[1.],
[0.],
...,
[1.],
[1.],
我还有其他方法可以评估模型性能并评估得分吗？
以这种方式，如何找到最佳模型？我在想，我们可以加载（假设） 2加权折叠模型，并在其上获取平均得分值或类似集合方法。下面是我到目前为止尝试过的东西。
def ensemble(models, model_input):
Models_output = [model(model_input) for model in models]
Avg = keras.layers.average(Models_output)
model_Ensemble = Model(inputs = model_input, outputs = Avg, name = 'ens')
model_Ensemble.compile( ... )
return modelEnsemble
并加载我们得到 K-fold 交叉验证方法的保存权重。
import keras
model_1, eval_model_1 = CapsNet(input_shape=[32, 32, 1],
n_class=10,
routings=3)
model_2, eval_model_2 = CapsNet()
models = []
# Load weights
model_1.load_weights('Fold_1.h5')
model_1.name = 'model_1'
models.append(model_1)
model_2.load_weights('Fold_2.h5')
model_2.name = 'model_2'
models.append(model_2)
model_input = Input(shape=models[0].input_shape[1:])
ensemble_model = ensemble(models, model_input)
这将引发以下错误。我知道，我在这里遗漏了一些东西，但无法弄清楚该如何管理。
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-37-8cec3f452a69> in <module>()
4 model_1, eval_model_1 = CapsNet(input_shape=[32, 32, 1],
5 n_class=10,
----> 6 routings=3)
7
8 model_2, eval_model_2 = CapsNet(input_shape=[32, 32, 1],
<ipython-input-31-d96b4a5e15ad> in CapsNet(input_shape, n_class, routings)
44
45 # Shared Decoder model in training and prediction
---> 46 decoder = models.Sequential(name='decoder')
47 decoder.add(layers.Dense(512, activation='relu', input_dim=16*n_class))
48 decoder.add(layers.Dense(1024, activation='relu'))
AttributeError: 'list' object has no attribute 'Sequential'
如果我简短地概述我的问题或遇到的问题是-我无法使用model.evaluate(...,...)方法评估模型性能。并进一步得到此归因错误。
任何帮助或建议都将受到高度赞赏。谢谢。
答案 0 :(得分：0)
在以下一行中，输入train_model的是两个数组的列表。
train_model = models.Model([x, y], [out_caps, decoder(masked_by_y)])
但是，当您调用模型。在 K折交叉验证部分中进行评估时，您正在传递单个numpy数组作为输入（X_val）。
scores = model.evaluate(X_val, y_val, verbose = 0)
在这种情况下，我还想知道您是否要使用训练模型或验证模型。从调用方法的方式以及评估模型的意图出发，可以推断出您可能想调用eval_model的评估方法。
scores = eval_model.evaluate(X_val, y_val, verbose = 0)