waytrue17 commented on a change in pull request #20226: URL: https://github.com/apache/incubator-mxnet/pull/20226#discussion_r622595738
########## File path: tests/python-pytest/onnx/test_operators.py ########## @@ -1234,21 +1235,22 @@ def test_onnx_export_sequence_reverse(tmp_path, dtype, params): # onnx LSTM from opset 11 does not support float64 [email protected]('mode', ['lstm', 'gru']) [email protected]('mode', ['lstm', 'gru', 'rnn_tanh', 'rnn_relu']) @pytest.mark.parametrize('dtype', ['float32']) [email protected]('state_size', [16, 32]) [email protected]('state_size', [16, 32, 64]) @pytest.mark.parametrize('input_size', [16, 32, 64]) @pytest.mark.parametrize('num_layers', [1, 2]) @pytest.mark.parametrize('batch_size', [1, 2, 4]) [email protected]('seq_length', [16, 32]) Review comment: Saw the same assertion issue with large seq_length/state_size/input_size. Will need to further decrease one of them to pass `rnn`, just like what we did before for `lstm` and `gru`. -- 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. For queries about this service, please contact Infrastructure at: [email protected]
