Closed AceCoooool closed 6 years ago
The issue proposed in issue 4. I test the situation of : both network is training on the dataset (not deform mnist), the test accuracy
---original net--- test_data: 99.03% test_scaled_data: 62.22% ---deformable net--- test_data: 98.67% test_scaled_data: 54.43%
I think the train phase should use undeform data, this can show the advantage of the deformable CNN's advantage.
The issue proposed in issue 4. I test the situation of : both network is training on the dataset (not deform mnist), the test accuracy
I think the train phase should use undeform data, this can show the advantage of the deformable CNN's advantage.