ChainerCV 输入图像数据格式

Question

我有一个包含 250 个形状图像（3、320、240）和 250 个注释文件的图像集。我正在使用 ChainerCV 来检测和识别图像中的两个类：球和球员。这里我们使用的是在 ImageNet 数据集上预训练的 SSD300 模型。

编辑： 创建数据集对象的类

bball_labels = ('ball','player')
class BBall_dataset(VOCBboxDataset):
  def _get_annotations(self, i):
    id_ = self.ids[i]
    anno = ET.parse(os.path.join(self.data_dir, 'Annotations', id_ + 
'.xml'))
    bbox = []
    label = []
    difficult = []
    for obj in anno.findall('object'):
      bndbox_anno = obj.find('bndbox')
      bbox.append([int(bndbox_anno.find(tag).text) - 1 for tag in ('ymin', 
'xmin', 'ymax', 'xmax')])
      name = obj.find('name').text.lower().strip()
      label.append(bball_labels.index(name))
    bbox = np.stack(bbox).astype(np.float32)
    label = np.stack(label).astype(np.int32)
    difficult = np.array(difficult, dtype=np.bool)
    return bbox, label, difficult

下载预训练模型

import chainer
from chainercv.links import SSD300
from chainercv.links.model.ssd import multibox_loss

class MultiboxTrainChain(chainer.Chain):
    def __init__(self, model, alpha=1, k=3):
        super(MultiboxTrainChain, self).__init__()
        with self.init_scope():
            self.model = model
        self.alpha = alpha
        self.k = k
    def forward(self, imgs, gt_mb_locs, gt_mb_labels):
        mb_locs, mb_confs = self.model(imgs)
        loc_loss, conf_loss = multibox_loss(
            mb_locs, mb_confs, gt_mb_locs, gt_mb_labels, self.k)
        loss = loc_loss * self.alpha + conf_loss

        chainer.reporter.report(
            {'loss': loss, 'loss/loc': loc_loss, 'loss/conf': conf_loss},
            self)
        return loss

model = SSD300(n_fg_class=len(bball_labels), pretrained_model='imagenet')
train_chain = MultiboxTrainChain(model)

转换数据集 导入必要的库

class Transform(object):
  def __init__(self, coder, size, mean):
    self.coder = copy.copy(coder)
    self.coder.to_cpu()

    self.size = size
    self.mean = mean
  def __call__(self, in_data):
    img, bbox, label = in_data
    img = random_distort(img)
    if np.random.randint(2):
      img, param = transforms.random_expand(img, fill=self.mean, 
 return_param=True)
      bbox = transforms.translate_bbox(bbox, y_offset=param['y_offset'], 
x_offset=param['x_offset'])
      img, param = random_crop_with_bbox_constraints(img, bbox, 
return_param=True)
      bbox, param = transforms.crop_bbox(bbox, y_slice=param['y_slice'], 
x_slice=param['x_slice'],allow_outside_center=False, return_param=True)
      label = label[param['index']]

    _, H, W = img.shape
    img = resize_with_random_interpolation(img, (self.size, self.size))
    bbox = transforms.resize_bbox(bbox, (H, W), (self.size, self.size))

    img, params = transforms.random_flip(img, x_random=True, 
return_param=True)
    bbox = transforms.flip_bbox(bbox, (self.size, self.size), 
x_flip=params['x_flip'])

    img -= self.mean
    mb_loc, mb_label = self.coder.encode(bbox, label)

    return img, mb_loc, mb_label
    transformed_train_dataset = TransformDataset(train_dataset, 
    Transform(model.coder, model.insize, model.mean))

    train_iter = 
    chainer.iterators.MultiprocessIterator(transformed_train_dataset, 
batchsize)
    valid_iter = chainer.iterators.SerialIterator(valid_dataset, 
batchsize, 
    repeat=False, shuffle=False) 

在训练过程中会抛出以下错误：

Exception in thread Thread-4:
Traceback (most recent call last):
  File "/usr/lib/python3.6/threading.py", line 916, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.6/threading.py", line 864, in run
    self._target(*self._args, **self._kwargs)
  File "/usr/local/lib/python3.6/dist- 
packages/chainer/iterators/multiprocess_iterator.py", line 401, in 
fetch_batch
    batch_ret[0] = [self.dataset[idx] for idx in indices]
  File "/usr/local/lib/python3.6/dist-
........................................................................
packages/chainer/iterators/multiprocess_iterator.py", line 401, in 
<listcomp>
    batch_ret[0] = [self.dataset[idx] for idx in indices]
  File "/usr/local/lib/python3.6/dist- 
packages/chainer/dataset/dataset_mixin.py", line 67, in __getitem__
    return self.get_example(index)
  File "/usr/local/lib/python3.6/dist- 
packages/chainer/datasets/transform_dataset.py", line 51, in get_example
    in_data = self._dataset[i]
  File "/usr/local/lib/python3.6/dist- 
packages/chainer/dataset/dataset_mixin.py", line 67, in __getitem__
    return self.get_example(index)
  File "/usr/local/lib/python3.6/dist-- 
packages/chainercv/utils/image/read_image.py", line 120, in read_image
    return _read_image_cv2(path, dtype, color, alpha)
  File "/usr/local/lib/python3.6/dist- 
packages/chainercv/utils/image/read_image.py", line 49, in _read_image_cv2
    if img.ndim == 2:
AttributeError: 'NoneType' object has no attribute 'ndim'
    TypeError: 'NoneType' object is not iterable

我想知道是什么原因造成的。在这种情况下输入数据格式是否不正确？以及如何解决这种情况。

Answer 1

这个问题是由于一个被忽视的小情况造成的，即文本文件在图像列表被剪切、复制和粘贴到同一个文件中时存在间隙。文本文件是在记事本中创建的。在记事本中索引是不可见的，但是一旦您在 github 中查看初始索引仍然存在并且索引仍然存在的文本文件，即使列表的大小被缩减，这些间隙也是可见的。例如，首先创建了 182 个图像的列表，但后来减少到 170 个。因此，当我们使用 Dataset Creation 对象时，代码会读取文本文件的所有行，即它将读取 182 而不是 170。 这影响了使用错误读取的数据集训练模型。 为 train、val 和 test 创建了一组新的文本文件，现在训练正常进行了。