[GitHub] [incubator-tvm] d-smirnov commented on a change in pull request #6018: Added support for tflite quantized maximum and minimum

[GitBox <gi...@apache.org>]

d-smirnov commented on a change in pull request #6018:
URL: https://github.com/apache/incubator-tvm/pull/6018#discussion_r454579971



##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -1281,70 +1287,72 @@ def test_all_unary_elemwise():
 # Element-wise
 # ------------
 
-def _test_elemwise(math_op, data, fused_activation_function=None, quantized=False, qnn_op=None):
+def _test_elemwise(math_op, data, fused_activation_function=None, quantized=False, qnn_op=None, same_qnn_params=False):
     """ One iteration of elemwise """
 
     assert len(data) == 2
 
     # Test with two tensors
-    with tf.Graph().as_default():
-        in_data = [array_ops.placeholder(shape=data[0].shape, dtype='float32', name='in_0'),
-                   array_ops.placeholder(shape=data[1].shape, dtype='float32', name='in_1')]
-
-        if quantized:
+    def __test_elemwise( in_data ):

Review comment:
       I slightly simplified unit test (using current implementation). Is there an example with different quantisation parameters for two input tensors and one output tensor written using Keras?




----------------------------------------------------------------
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:
users@infra.apache.org