我正在尝试按照“Fine-tune InceptionV3 on a new set of classes"示例代码冻结前172个图层并重新训练猫/狗数据集上的最后一层。我一直收到错误,我在底部注意到了。请我正在使用Ubuntu 16.04,keras 1.2.1,theano 0.9.0beta1.dev,numpy 1.12.0和python 3.5。
from PIL import Image
import os
import matplotlib.pyplot as plt
import numpy as np
data_root_dir = "/home/ubuntu/ML/data/dogscats/"
train_dir = os.path.join(data_root_dir,"sample", "train")
valid_dir = os.path.join(data_root_dir, "valid")
from keras.applications.inception_v3 import InceptionV3
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras import backend as K
# create the base pre-trained model
base_model = InceptionV3(weights='imagenet', include_top=True)
# add a global spatial average pooling layer
x = base_model.output
#x = GlobalAveragePooling2D()(x)
# let's add a fully-connected layer
x = Dense(1024, activation='relu')(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(2, activation='softmax')(x)
# this is the model we will train
model = Model(input=base_model.input, output=predictions)
for layer in model.layers[:172]:
layer.trainable = False
for layer in model.layers[172:]:
layer.trainable = True
from keras.optimizers import SGD
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='categorical_crossentropy')
from sklearn.preprocessing import OneHotEncoder
def get_data(path, target_size=(299,299)):
batches = get_batches(path, shuffle=False, batch_size=1, class_mode=None, target_size=target_size)
return np.concatenate([batches.next() for i in range(batches.nb_sample)])
def get_batches(dirname, gen=image.ImageDataGenerator(), shuffle=True, batch_size=2, class_mode='categorical',
target_size=(299,299)):
return gen.flow_from_directory(dirname, target_size=target_size,
class_mode=class_mode, shuffle=shuffle, batch_size=batch_size)
def onehot(x): return np.array(OneHotEncoder().fit_transform(x.reshape(-1,1)).todense())
# Use batch size of 1 since we're just doing preprocessing on the CPU
val_batches = get_batches(valid_dir, shuffle=False, batch_size=10)
train_batches = get_batches(train_dir, shuffle=False, batch_size=10)
val_classes = val_batches.classes
trn_classes = train_batches.classes
val_labels = onehot(val_classes)
trn_labels = onehot(trn_classes)
model.fit_generator(train_batches, samples_per_epoch=train_batches.n, nb_epoch=10,
validation_data=val_batches, nb_val_samples=val_batches.n)
例外情况是:average_exc_pad
的填充必须为零这是完整的堆栈跟踪:
ValueError Traceback (most recent call last)
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/theano/compile/function_module.py in __call__(self, *args, **kwargs)
883 outputs =\
--> 884 self.fn() if output_subset is None else\
885 self.fn(output_subset=output_subset)
ValueError: padding must be zero for average_exc_pad
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-4-369d7760ec6e> in <module>()
34
35 model.fit_generator(train_batches, samples_per_epoch=train_batches.n, nb_epoch=10,
---> 36 validation_data=val_batches, nb_val_samples=val_batches.n)
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/keras/engine/training.py in fit_generator(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, nb_worker, pickle_safe, initial_epoch)
1551 outs = self.train_on_batch(x, y,
1552 sample_weight=sample_weight,
-> 1553 class_weight=class_weight)
1554
1555 if not isinstance(outs, list):
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1314 ins = x + y + sample_weights
1315 self._make_train_function()
-> 1316 outputs = self.train_function(ins)
1317 if len(outputs) == 1:
1318 return outputs[0]
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/keras/backend/theano_backend.py in __call__(self, inputs)
957 def __call__(self, inputs):
958 assert isinstance(inputs, (list, tuple))
--> 959 return self.function(*inputs)
960
961
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/theano/compile/function_module.py in __call__(self, *args, **kwargs)
896 node=self.fn.nodes[self.fn.position_of_error],
897 thunk=thunk,
--> 898 storage_map=getattr(self.fn, 'storage_map', None))
899 else:
900 # old-style linkers raise their own exceptions
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/theano/gof/link.py in raise_with_op(node, thunk, exc_info, storage_map)
323 # extra long error message in that case.
324 pass
--> 325 reraise(exc_type, exc_value, exc_trace)
326
327
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/six.py in reraise(tp, value, tb)
683 value = tp()
684 if value.__traceback__ is not tb:
--> 685 raise value.with_traceback(tb)
686 raise value
687
/home/ubuntu/anaconda3/envs/tensorflow/lib/python3.5/site-packages/theano/compile/function_module.py in __call__(self, *args, **kwargs)
882 try:
883 outputs =\
--> 884 self.fn() if output_subset is None else\
885 self.fn(output_subset=output_subset)
886 except Exception:
ValueError: padding must be zero for average_exc_pad
Apply node that caused the error: AveragePoolGrad{ignore_border=True, mode='average_exc_pad', ndim=2}(Join.0, IncSubtensor{InplaceInc;::, ::, :int64:, :int64:}.0, TensorConstant{(2,) of 3}, TensorConstant{(2,) of 1}, TensorConstant{(2,) of 1})
Toposort index: 5270
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D), TensorType(int64, vector), TensorType(int64, vector), TensorType(int64, vector)]
Inputs shapes: [(10, 2048, 8, 8), (10, 2048, 8, 8), (2,), (2,), (2,)]
Inputs strides: [(524288, 256, 32, 4), (524288, 256, 32, 4), (8,), (8,), (8,)]
Inputs values: ['not shown', 'not shown', array([3, 3]), array([1, 1]), array([1, 1])]
Outputs clients: [[Elemwise{add,no_inplace}(CorrMM_gradInputs{half, (1, 1), (1, 1)}.0, CorrMM_gradInputs{half, (1, 1), (1, 1)}.0, CorrMM_gradInputs{half, (1, 1), (1, 1)}.0, AveragePoolGrad{ignore_border=True, mode='average_exc_pad', ndim=2}.0)]]
答案 0 :(得分:1)
在这种情况下进行微调可能意味着使用卷积层作为预训练的特征提取器。因此,您并不真正想要Inception网络的顶层(密集连接的层)。
更改
base_model = InceptionV3(weights='imagenet', include_top=True)
到
base_model = InceptionV3(weights='imagenet', include_top=False)
应该有用。
此外,如果您有200个课程,则应更改
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(2, activation='softmax')(x)
到
predictions = Dense(200, activation='softmax')(x)
所以你的最后一层将拥有所需的200个元素。