ckt624 commented on a change in pull request #15349: Numpy Tensordot Operator
URL: https://github.com/apache/incubator-mxnet/pull/15349#discussion_r303748262
##########
File path: tests/python/unittest/test_numpy_op.py
##########
@@ -27,6 +27,152 @@
from mxnet.test_utils import check_numeric_gradient
from common import assertRaises, with_seed
import random
+import collections
+
+
+@with_seed()
+@npx.use_np_shape
+def test_np_tensordot():
+ class TestTensordot(HybridBlock):
+ def __init__(self, axes):
+ super(TestTensordot, self).__init__()
+ self._axes = axes
+
+ def hybrid_forward(self, F, a, b):
+ return F.np.tensordot(a, b, self._axes)
+
+ def tensordot_backward(a, b, axes=2):
+ if (a.ndim < 1) or (b.ndim < 1):
+ raise ValueError('An input is zero-dim')
+
+ if _np.isscalar(axes):
+ a_axes_summed = [i + a.ndim - axes for i in range(axes)]
+ b_axes_summed = [i for i in range(axes)]
+ else:
+ if len(axes) != 2:
+ raise ValueError('Axes must consist of two arrays.')
+ a_axes_summed, b_axes_summed = axes
+ if _np.isscalar(a_axes_summed):
+ a_axes_summed = a_axes_summed,
+ if _np.isscalar(b_axes_summed):
+ b_axes_summed = b_axes_summed,
+
+ if len(a_axes_summed) != len(b_axes_summed):
+ raise ValueError('Axes length mismatch')
+
+ a_axes_remained = []
+ for i in range(a.ndim):
+ if not (i in a_axes_summed):
+ a_axes_remained.append(i)
+ a_axes = a_axes_remained[:] + a_axes_summed[:]
+
+ b_axes_remained = []
+ for i in range(b.ndim):
+ if not (i in b_axes_summed):
+ b_axes_remained.append(i)
+ b_axes = b_axes_summed[:] + b_axes_remained[:]
+
+ ad1 = _np.prod([a.shape[i] for i in a_axes_remained]) if
len(a_axes_remained) > 0 else 1
+ ad2 = _np.prod([a.shape[i] for i in a_axes_summed]) if
len(a_axes_summed) > 0 else 1
+ bd1 = _np.prod([b.shape[i] for i in b_axes_summed]) if
len(b_axes_summed) > 0 else 1
+ bd2 = _np.prod([b.shape[i] for i in b_axes_remained]) if
len(b_axes_remained) > 0 else 1
+
+ out_grad = _np.ones((ad1, bd2))
+
+ new_a = _np.transpose(a, a_axes)
+ new_a_shape = new_a.shape[:]
+ new_a = new_a.reshape((ad1, ad2))
+ new_b = _np.transpose(b, b_axes)
+ new_b_shape = new_b.shape[:]
+ new_b = new_b.reshape((bd1, bd2))
+
+ reverse_a_axes = [0 for i in a_axes]
+ for i in range(len(a_axes)):
+ reverse_a_axes[a_axes[i]] = i
+
+ reverse_b_axes = [0 for i in b_axes]
+ for i in range(len(b_axes)):
+ reverse_b_axes[b_axes[i]] = i
+
+ grad_b = _np.dot(new_a.T, out_grad).reshape(new_b_shape)
+ grad_b = _np.transpose(grad_b, reverse_b_axes)
+ grad_a = _np.dot(out_grad, new_b.T).reshape(new_a_shape)
+ grad_a = _np.transpose(grad_a, reverse_a_axes)
+
+ return [grad_a, grad_b]
+
+ # test non zero size input
+ tensor_shapes = [
Review comment:
Changed. Thx.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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
