maekawatoshiki commented on code in PR #14536:
URL: https://github.com/apache/tvm/pull/14536#discussion_r1161769396
##########
tests/python/relay/test_pass_fake_quantization_to_integer.py:
##########
@@ -1114,5 +1114,36 @@ def test_fake_quantize_take():
compare_fq_to_int(op, [x_np])
+def test_fake_quantize_softmax():
+ x = relay.var("x", shape=[5, 10], dtype="float32")
+
+ x = relay.qnn.op.quantize(x, relay.const(0.08), relay.const(-48),
out_dtype="int8")
+ x = relay.qnn.op.dequantize(x, relay.const(0.08), relay.const(-48))
+ op = relay.op.nn.softmax(x, axis=1)
+ op = relay.qnn.op.quantize(op, relay.const(0.0038), relay.const(-128),
out_dtype="int8")
+ op = relay.qnn.op.dequantize(op, relay.const(0.0038), relay.const(-128))
+
+ x_np = np.random.random_sample([5, 10]).astype(np.float32) * 20.0 - 6
+ args = [x_np]
+
+ mod = tvm.IRModule.from_expr(op)
+ mod = tvm.relay.transform.InferType()(mod)
+ mod_int =
tvm.relay.transform.FakeQuantizationToInteger(hard_fail=True)(mod)
+ assert not tvm.ir.structural_equal(mod, mod_int)
+
+ result = (
+ relay.create_executor("vm", mod=mod, device=tvm.cpu(), target="llvm")
+ .evaluate()(*args)
+ .numpy()
+ )
+ result_int = (
+ relay.create_executor("vm", mod=mod_int, device=tvm.cpu(),
target="llvm")
+ .evaluate()(*args)
+ .numpy()
+ )
+
+ assert np.allclose(result_int, result, rtol=1, atol=0.05)
Review Comment:
I verified that `assert np.allclose(result_int, result, atol=0.05)` is fine.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
