[GitHub] [tvm] AndrewZhaoLuo commented on a change in pull request #9982: [QNN] Add qnn.rsqrt op

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

AndrewZhaoLuo commented on a change in pull request #9982:
URL: https://github.com/apache/tvm/pull/9982#discussion_r788130953



##########
File path: tests/python/relay/test_pass_fake_quantization_to_integer.py
##########
@@ -303,6 +303,19 @@ def test_fake_quantize_global_avg_pool():
     compare_fq_to_int(op, [x_np], True)
 
 
+def test_fake_quantize_rsqrt():
+    x = relay.var("x", shape=[1, 3, 224, 224], dtype="int8")
+    zero = relay.const(0)
+
+    x = relay.qnn.op.dequantize(x, relay.const(2.0), zero)
+    op = relay.rsqrt(x)
+    op = relay.qnn.op.quantize(op, relay.const(2.0), zero)
+
+    x_np = np.random.randint(-128, 127, size=[1, 3, 224, 224], dtype="int8")
+
+    compare_fq_to_int(op, [x_np], True)

Review comment:
       Huh, shouldn't this fail? since the default lowering matches the fake-quantized version?




-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org