Theano/Lasagne/Nolearn神经网络图像输入

Question

我正致力于图像分类任务,并决定使用Lasagne + Nolearn进行神经网络原型.像MNIST数字分类这样的所有标准例子运行良好,但是当我尝试使用自己的图像时会出现问题.

我想使用3通道图像,而不是灰度图像.还有我正在尝试从图像中获取数组的代码:

 img = Image.open(item)
 img = ImageOps.fit(img, (256, 256), Image.ANTIALIAS)
 img = np.asarray(img, dtype = 'float64') / 255.
 img = img.transpose(2,0,1).reshape(3, 256, 256)   
 X.append(img)

这是NN的代码及其拟合:

X, y = simple_load("new")

X = np.array(X)
y = np.array(y)


net1 = NeuralNet(
    layers=[  # three layers: one hidden layer
        ('input', layers.InputLayer),
        ('hidden', layers.DenseLayer),
        ('output', layers.DenseLayer),
        ],
    # layer parameters:
    input_shape=(None, 65536),  # 96x96 input pixels per batch
    hidden_num_units=100,  # number of units in hidden layer
    output_nonlinearity=None,  # output layer uses identity function
    output_num_units=len(y),  # 30 target values

    # optimization method:
    update=nesterov_momentum,
    update_learning_rate=0.01,
    update_momentum=0.9,

    regression=True,  # flag to indicate we're dealing with regression problem


       max_epochs=400,  # we want to train this many epochs
        verbose=1,
        )

  net1.fit(X, y)

我接受了这样的例外情况:

Traceback (most recent call last):
  File "las_mnist.py", line 39, in <module>
    net1.fit(X[i], y[i])
  File "/usr/local/lib/python2.7/dist-packages/nolearn/lasagne.py", line 266, in fit
    self.train_loop(X, y)
  File "/usr/local/lib/python2.7/dist-packages/nolearn/lasagne.py", line 273, in train_loop
    X, y, self.eval_size)
  File "/usr/local/lib/python2.7/dist-packages/nolearn/lasagne.py", line 377, in train_test_split
    kf = KFold(y.shape[0], round(1. / eval_size))
IndexError: tuple index out of range

那么,您以哪种格式"提供"您的网络图像数据？ 感谢您的答案或任何提示!

Answer 1

如果您正在进行分类,则需要修改以下几项:

1. 在您设置的代码中regression = True.要做分类,请删除此行.
2. 如果要输入3个不同的通道,请确保输入形状与X的形状匹配

3. 因为您正在进行分类,所以您需要输出使用softmax非线性(此时您将拥有无法帮助您进行分类的标识)

   X, y = simple_load("new")
   
   X = np.array(X)
   y = np.array(y)
   
   net1 = NeuralNet(
       layers=[  # three layers: one hidden layer
           ('input', layers.InputLayer),
           ('hidden', layers.DenseLayer),
           ('output', layers.DenseLayer),
           ],
       # layer parameters:
       input_shape=(None, 3, 256, 256),  # TODO: change this
       hidden_num_units=100,  # number of units in hidden layer
       output_nonlinearity=lasagne.nonlinearities.softmax, # TODO: change this
       output_num_units=len(y),  # 30 target values
   
       # optimization method:
       update=nesterov_momentum,
       update_learning_rate=0.01,
       update_momentum=0.9,
   
       max_epochs=400,  # we want to train this many epochs
       verbose=1,
   

   )

Answer 2

我还在烤宽面条用户论坛中询问过这个问题，Oliver Duerr 通过代码示例为我提供了很多帮助： https://groups.google.com/forum/# !topic/lasagne-users/8ZA7hr2wKfM