search

apache / tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators
https://tvm.apache.org/
Apache License 2.0
11.75k stars 3.47k forks source link

[Bug] _test_tflite2_quantized_depthwise_convolution is unused #11356

Closed leandron closed 2 years ago

leandron commented 2 years ago

Creating this issue as a reminder that tests in the TFLite frontend seem to be missing _test_tflite2_quantized_depthwise_convolution, which shows lack of coverage for that particular operator.

valmirnjr commented 2 years ago

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_quantizedconvolution ____

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)))

blackkker commented 2 years ago

@leandron I think you can closed this issue.

leandron commented 2 years ago

Closed by https://github.com/apache/tvm/pull/12145