汇总预测与数据增强在千层面



我正在研究MNIST数据集,并使用数据增强来训练神经网络。我有一个BatchIterator,它从每张图片中随机提取24,24个子图像,并将其用作神经网络的输入。

就训练而言,一切都很顺利。但对于预测,我想从给定的图像中提取5个子图像,并平均预测,但我不能让它工作:

这是我的BatchIterator:

class CropIterator(BatchIterator):
    def __init__(self, batch_size, crop=4, testing=False):
        super(CropIterator, self).__init__(batch_size)
        self.testing = testing
        self.crop = crop

    def transform(self, Xb, yb):
        crop = self.crop
        batch_size, channels, width, height = Xb.shape
        if not self.testing:
            y_new = yb      
            X_new = np.zeros([batch_size, channels, width - crop, height - crop]).astype(np.float32)
            for i in range(batch_size):
                x = np.random.randint(0, crop+1)
                y = np.random.randint(0, crop+1)
                X_new[i] = Xb[i, :, x:x+width-crop, y:y+height-crop]
        else:
            X_new = np.zeros([5 * batch_size, channels, width - crop, height - crop]).astype(np.float32)
            y_new = np.zeros(5 * batch_size).astype(np.int32)
            for i in range(batch_size):
                for idx, position in enumerate([(0,0), (0, crop), (crop, 0), (crop, crop), (crop//2, crop//2)]):
                    # all extreme cropppings + the middle one
                    x_idx = position[0]
                    y_idx = position[1]
                    X_new[5*i+idx, :] = Xb[i, :, x_idx:x_idx+width-crop, y_idx:y_idx+height-crop]
                    y_new[5*i+idx] = yb[i]
        return X_new, y_new

拟合我的网络训练数据工作,但当我做net.predict(X_test)时,我得到一个错误,因为CropIterator.transform()是,我相信,yb等于None

下面是完整的调用栈:

/usr/local/lib/python2.7/site-packages/nolearn/lasagne/base.pyc in predict(self, X)
    526             return self.predict_proba(X)
    527         else:
--> 528             y_pred = np.argmax(self.predict_proba(X), axis=1)
    529             if self.use_label_encoder:
    530                 y_pred = self.enc_.inverse_transform(y_pred)
/usr/local/lib/python2.7/site-packages/nolearn/lasagne/base.pyc in predict_proba(self, X)
    518     def predict_proba(self, X):
    519         probas = []
--> 520         for Xb, yb in self.batch_iterator_test(X):
    521             probas.append(self.apply_batch_func(self.predict_iter_, Xb))
    522         return np.vstack(probas)
/usr/local/lib/python2.7/site-packages/nolearn/lasagne/base.pyc in __iter__(self)
     78             else:
     79                 yb = None
---> 80             yield self.transform(Xb, yb)
     81 
     82     @property
<ipython-input-56-59463a9f9924> in transform(self, Xb, yb)
     33                     y_idx = position[1]
     34                     X_new[5*i+idx, :] = Xb[i, :, x_idx:x_idx+width-crop, y_idx:y_idx+height-crop]
---> 35                     y_new[5*i+idx] = yb[i]
     36         return X_new, y_new
     37 
TypeError: 'NoneType' object has no attribute '__getitem__'

关于如何在CropIterator.transform()的测试部分修复它的任何想法?

查看nolearn.lasagne.BatchIterator的代码以及nolearn.lasagne.NeuralNet类如何使用它,看起来BatchIterator s需要在不提供y时工作,即在预测模式下。请注意520行的调用,其中提供了X,但没有给出y的值,因此它默认为None

你的CropIterator目前假设yb总是一个非None值。我不知道当yb不提供时做任何有用的事情是否有意义,但我假设您可以转换Xb并返回Noney_new,如果ybNone

相关内容

  • 没有找到相关文章

最新更新