lightingghost commented on issue #10220: Check failed: !ndinputs.back()->is_none() URL: https://github.com/apache/incubator-mxnet/issues/10220#issuecomment-375840105 Here is a minimum sample to reproduce this error ```python import mxnet as nd from mxnet import nd, sym, autograd from mxnet import gluon as g inp = nd.ones((20, 10)) class Test(g.nn.HybridBlock): def __init__(self): super(Test, self).__init__() self.fc1 = g.nn.Dense(100) self.fc2 = g.nn.Dense(20) def hybrid_forward(self, F, x): A = self.fc1(x) X = self.fc2(x) A = A.reshape((-1, 10, 10)) X = X.reshape((-1, 10, 2)) A = 0.5 <= A X = 0.5 <= X s = F.batch_dot(A, X) return s.sum() test = Test() #test.hybridize() test.initialize() with autograd.record(): l = test(inp) l.backward() ``` As stated earlier, calling `hybridize()` will make the error disappear. Besides, a slight change from `batch_dot` to `dot` will make the error disappear.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services