xingmimfl / pytorch_rfcn Goto Github PK

R-FCN.pytorch$ python test_net.py --dataset pascal_voc --arch rfcn --net res101 --checksession $SESSION --checkepoch $EPOCH --checkpoint $CHECKPOINT --cuda

Traceback (most recent call last):
File "test_net.py", line 30, in
from model.utils.net_utils import save_net, load_net, vis_detections
File "/data/repos/R-FCN.pytorch/lib/model/utils/net_utils.py", line 8, in
from model.roi_crop.functions.roi_crop import RoICropFunction
File "/data/repos/R-FCN.pytorch/lib/model/roi_crop/functions/roi_crop.py", line 4, in
from .._ext import roi_crop
File "/data/repos/R-FCN.pytorch/lib/model/roi_crop/_ext/roi_crop/init.py", line 3, in
from ._roi_crop import lib as _lib, ffi as _ffi
ModuleNotFoundError: No module named 'model.roi_crop._ext.roi_crop._roi_crop'

When I trained the network, memory-usage increased linearly. Has anyone else encountered this problem?
I use python 3.6 and pytorch 4.0 in the experiments.

What results on VOC/COCO did you achieve?

Are you sure that spatial scale is affected by dilation?
I'm pretty sure that spatial scale is only affected by stride.

you said the psroi_pooling operation from this RFCN repository
but you can see this issue

how to evaluate your model?