Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Flaky] TFLite quantized conv test #6084

Merged
merged 6 commits into from
Jul 24, 2020
Merged

[Flaky] TFLite quantized conv test #6084

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
01ce30a
[Flaky] TFLite quantized conv test
anijain2305 Jul 17, 2020
2b26b9c
Retrigger
anijain2305 Jul 17, 2020
95eba9c
Retrigger
anijain2305 Jul 17, 2020
b1bf55d
Commenting out tests
anijain2305 Jul 20, 2020
6892dc7
Retirgger
anijain2305 Jul 22, 2020
067a33f
Retrigger
anijain2305 Jul 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 8 additions & 6 deletions tests/python/frontend/tflite/test_forward.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -785,6 +785,7 @@ def representative_data_gen():
def _test_tflite2_quantized_depthwise_convolution(input_shape, kernel_shape,
dilations, strides, padding, data_format, depth_multiplier):
"""One iteration of TFLite2 quantized depthwise convolution with given shapes and attributes"""

data_format = "channels_last" if "NHWC" else "channels_first"
data = np.random.uniform(0, 1, input_shape).astype('float32')
kernel = np.random.uniform(0, 1, kernel_shape).astype('float32')
Expand Down Expand Up @@ -914,13 +915,14 @@ def test_forward_convolution():
_test_tflite2_quantized_convolution([1, 17, 17, 19], [3, 3, 19, 19], [1, 1], [2, 2], 'VALID', 'NHWC')
_test_tflite2_quantized_convolution([1, 17, 17, 124], [1, 1, 124, 19], [1, 1], [1, 1], 'SAME', 'NHWC')

# Disable as tests are flaky - https://github.com/apache/incubator-tvm/issues/6064
# depthwise convolution
_test_tflite2_quantized_depthwise_convolution([1, 8, 8, 128], [1, 1, 128, 1], [1, 1], [1, 1],
'SAME', 'NHWC', 1)
_test_tflite2_quantized_depthwise_convolution([1, 17, 17, 12], [3, 3, 12, 1], [1, 1], [2, 2],
'VALID', 'NHWC', 1)
_test_tflite2_quantized_depthwise_convolution([1, 24, 24, 3], [7, 7, 3, 8], [1, 1], [2, 2],
'SAME', 'NHWC', 8)
# _test_tflite2_quantized_depthwise_convolution([1, 8, 8, 128], [1, 1, 128, 1], [1, 1], [1, 1],
# 'SAME', 'NHWC', 1)
# _test_tflite2_quantized_depthwise_convolution([1, 17, 17, 12], [3, 3, 12, 1], [1, 1], [2, 2],
# 'VALID', 'NHWC', 1)
# _test_tflite2_quantized_depthwise_convolution([1, 24, 24, 3], [7, 7, 3, 8], [1, 1], [2, 2],
# 'SAME', 'NHWC', 8)



Expand Down