Traceback (most recent call last): … chainer.utils.type_check.InvalidType: Invalid operation is performed in: ReLU (Forward) Expect : x.dtype.kind == f Actual: i != f In this case, kind of x (the first argument of the function relu() ) is expected to be f (floating-point), whereas the input was i (signed integer).
12/10/2017 · Exception in main training loop: Invalid operation is performed in: SoftmaxCrossEntropy (Forward) Expect : in_types[1].dtype.kind == i Actual: f != i Traceback (most recent call last): File /usr/local/lib/python3.6/site-packages/chainer/training/trainer.py, line 299, in run update() File /usr/local/lib/python3.6/site-packages/chainer/training/updater.py, line 223, in update.
????????????????? Expect: t.dtype.kind == i ??Actual: f != i??????????? ????????? In [5]:, def check_type_forward (self, in_types): type_check. expect (in_types. size == 2) x_type, t_type = in_types type_check. expect (x_type. dtype == numpy. float32, t_type. dtype. kind == ‘i’, x_type. shape == t_type. shape), ???????. ???????shape????????????????. Actual: 2 != 1??????????????????????????????????????. Actual: (1,2) != (1,1)????????? (1,1)???shape??????????? (1,2)???????????????. ?????????????????????????????chainer?????? …
act_and_train??????? self.model = q_function?init??Q??????????????????????????????no_backprop_mode??????????????????????????????action_value????, Expect : prod(in_types[0].shape[1:]) == in_types[1].shape[1] Actual: 300 != 301. ????????????? ???????????????????????????????????????????????????????
