zcdu / dcnv2 Goto Github PK

    ./make.sh         # build
    python testcpu.py    # run examples and gradient check on cpu
    python testcuda.py   # run examples and gradient check on gpu 

Now the master branch is for pytorch 1.7.0, configuration:

1. python3.7.9
2. cuda11.1( cuda11.0 cannot support RTX30 compute)
3. gcc 9
4. g++ 9
5. Ubuntu2104
6. pytorch1.7.0

• Gradient check w.r.t offset (solved)
• Backward is not reentrant (minor)

This is an adaption of the official Deformable-ConvNets.

Update: all gradient check passes with double precision.

Another issue is that it raises RuntimeError: Backward is not reentrant. However, the error is very small (<1e-7 for float <1e-15 for double), so it may not be a serious problem (?)

Please post an issue or PR if you have any comments.