Example of Faster R-CNN failed to change batch size

[atinfinity]

System information (version)

• Chainer : 4.0.0
• CuPy : 4.0.0
• ChainerCV : 0.9.0
• CUDA : 9.1.85
• cuDNN : 7.1.3
• Operating System : Ubuntu 16.04 64bit
• Python : Python 3.5.2

Detailed description

I tried to change batch size of examples/faster_rcnn/train.py.
But, the following error message was displayed.

Exception in main training loop: all the input array dimensions except for the concatenation axis must match exactly
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/trainer.py", line 306, in run
    update()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py", line 149, in update
    self.update_core()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py", line 154, in update_core
    in_arrays = self.converter(batch, self.device)
  File "/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py", line 133, in concat_examples
    [example[i] for example in batch], padding[i])))
  File "/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py", line 163, in _concat_arrays
    return xp.concatenate([array[None] for array in arrays])
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
  File "train.py", line 137, in <module>
    main()
  File "train.py", line 133, in main
    trainer.run()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/trainer.py", line 320, in run
    six.reraise(*sys.exc_info())
  File "/usr/local/lib/python3.5/dist-packages/six.py", line 693, in reraise
    raise value
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/trainer.py", line 306, in run
    update()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py", line 149, in update
    self.update_core()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py", line 154, in update_core
    in_arrays = self.converter(batch, self.device)
  File "/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py", line 133, in concat_examples
    [example[i] for example in batch], padding[i])))
  File "/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py", line 163, in _concat_arrays
    return xp.concatenate([array[None] for array in arrays])
ValueError: all the input array dimensions except for the concatenation axis must match exactly

Is this a limitation of ChainerCV(or Chainer)?

Steps to reproduce

I changed batch size of examples/faster_rcnn/train.py.

train_iter = chainer.iterators.MultiprocessIterator(
-    train_data, batch_size=1, n_processes=None, shared_mem=100000000)
+    train_data, batch_size=2, n_processes=None, shared_mem=100000000)
test_iter = chainer.iterators.SerialIterator(
-    test_data, batch_size=1, repeat=False, shuffle=False)
+    test_data, batch_size=2, repeat=False, shuffle=False)    

And, I executed train.py.

$ python3 train.py

[Hakuyume]

Currently, our implementation of Faster R-CNN supports only batchsize=1. Please see here.