valmirnjr commented on issue #11356:
URL: https://github.com/apache/tvm/issues/11356#issuecomment-1146776453
Hi @leandron , I'd like to work on this issue. When I try to run
`test_forward_quantized_convolution` I see that
`_test_tflite2_quantized_depthwise_convolution` fails. Is this the problem?
> $ pytest
tests/python/frontend/tflite/test_forward.py::test_forward_quantized_convolution
> [11:41:02] ../src/target/target_kind.cc:163: Warning: Unable to detect
CUDA version, default to "-arch=sm_20" instead
> enabled targets: llvm
> pytest marker:
> ======================================== test session starts
========================================
> platform linux -- Python 3.8.10, pytest-6.2.3, py-1.10.0, pluggy-0.13.1
> rootdir: /home/valmir/Documentos/Projects/tvm
> collected 1 item
>
> tests/python/frontend/tflite/test_forward.py F
[100%]
>
> ============================================= FAILURES
==============================================
> ________________________________ test_forward_quantized_convolution
_________________________________
>
> def test_forward_quantized_convolution():
> for int_quant_dtype in [tf.int8, tf.int16]:
> > _test_tflite2_quantized_convolution(
> (1, 28, 28, 1),
> (1, 1),
> 12,
> data_format="NHWC",
> int_quant_dtype=int_quant_dtype,
> )
>
> tests/python/frontend/tflite/test_forward.py:945:
> _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_ _ _ _ _ _ _ _ _ _ _ _ _ _
> tests/python/frontend/tflite/test_forward.py:937: in
_test_tflite2_quantized_convolution
> tvm_output = run_tvm_graph(tflite_model_quant, data,
data_in.name.replace(":0", ""))
> tests/python/frontend/tflite/test_forward.py:239: in run_tvm_graph
> m.set_input(e, tvm.nd.array(input_data[i].astype(input_data[i].dtype)))
> _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_ _ _ _ _ _ _ _ _ _ _ _ _ _
--
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]
