Pretrained Weight gives worse performance about pytorch_melm HOT 3 OPEN

The number of Region Proposals used in training can affect the detection performance. So you may try adjust the number of proposals. It can be done by modifying the code in network.py as in issue #20

from pytorch_melm.

The current runnable version is highly dependent on PyTorch 0.4.0, but many files need to be compiled by the FFI library. But in the later version of PyTorch, this FFI library has been removed, is there an alternative to compile the following files: RoiPooling
RoiRingpooling
RoIAlign
NMS

This four modules relies on FFI that was deprecated in pytorch 1.0 and later.

from pytorch_melm.

I will write a README.md file for pytorch1.0 branch later. The operations you mentioned RoiRingpooling, RoIAlign, NMS are moved to ops folder. And before importing these modules, you should complie the files first by running the following code:

• cd lib

• bash make_cuda.sh

Type in bash make.sh won't compile the corresponding files in pytorch1.0 branch. I will delete maks.sh file in pytorch1.0 branch and make a statement in README.md file.

from pytorch_melm.