manupa-arm commented on a change in pull request #9910:
URL: https://github.com/apache/tvm/pull/9910#discussion_r786569130
##########
File path: tests/python/contrib/test_ethosu/test_legalize.py
##########
@@ -1502,5 +1503,61 @@ def verify(ext_func):
verify(mod["tvmgen_default_ethos_u_main_0"])
[email protected](
+ "ifm_shape,ifm_scale,ifm_zp,ofm_scale,ofm_zp",
+ [[(1, 8, 8, 3), 1.0, 0, 1.0, 0], [(1, 20, 30, 3), 1.345, 34, 0.32, -23]],
+)
+def test_ethosu_requantize(ifm_shape, ifm_scale, ifm_zp, ofm_scale, ofm_zp):
Review comment:
Since requantize is a sub-pattern of other patterns -- we would need a
test to ensure that such offloads are not affected in the presense of extra
requantize ops.
##########
File path: tests/python/contrib/test_ethosu/test_codegen.py
##########
@@ -949,7 +949,10 @@ def concat_func(*inputs):
op = tf.concat(list(inputs), axis)
return op
- _compare_tvm_with_tflite(concat_func, shapes, accel_type)
+ # TODO(lhutton1) For now output is not bit exact with TFLite.
+ # This is because TFLite reference kernels are not being used.
+ # For this, TFLite will need upgrading to 2.6.
+ _compare_tvm_with_tflite(concat_func, shapes, accel_type,
output_tolerance=1)
Review comment:
Why is this changed now ?
--
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]
