vasgaowei/pytorch_MELM
The pytorch implementation of the Min-Entropy Latent Model for Weakly Supervised Object Detection
Python
Issues
- 0
Where is the code of proposal clique partition?
#29 opened by zhumeng98 - 0
myself datasets applied on the MELM
#28 opened by dingjietao - 2
About corloc
#27 opened by PURE-melo - 4
So many issues on PyTorch1.0
#26 opened by yarkable - 3
Pretrained Weight gives worse performance
#25 opened by yoyoleeisstrong - 1
How to run coco datesets by pytorch_MELM?
#24 opened by jieruyao49 - 5
The CorLoc of this code
#19 opened by zwy1996 - 2
Could this code be trained by multi-GPU?
#18 opened by zwy1996 - 1
RoIRingPoolFunction
#23 opened by b03505036 - 3
Are the refine_loss_1 and refine_loss_2 defined according to Accumulated Recurrent Learning?
#11 opened by jiafw - 1
Mainly part rewrite the code
#22 opened by b03505036 - 4
pytorch 1.0 doesn't work
#21 opened by tankche1 - 3
pool5_roi' referenced before assignment
#16 opened by ltc576935585 - 1
In the Github source code you provided,the test experiment is 45.86%.Can you check it again?
#20 opened by Elaineok - 0
thanks for your job
#17 opened by ltc576935585 - 2
- 0
AssertionError
#15 opened by xr0912 - 1
Complie wrong
#13 opened by ltc576935585 - 0
comolie wrong
#14 opened by ltc576935585 - 4
cudaCheckError() failed : no kernel image is available for execution on the device
#12 opened by kenanozturk - 2
cross_entropy=0, loss_box=0
#10 opened by Spark001 - 1
What should I change in your 'network' if I want to test the performance of your model on the other dataset?
#9 opened by magemoumou - 2
- 3
refined_loss_1 is nan
#7 opened by fanglinpu - 3
Reproducibility results
#6 opened by zwyyy215 - 3
File "./MELM-master/tools/../lib/nets/network.py", line 384, in get_refine_supervision roi_weights[:, 0] = max_box_score[gt_assignment, 0] ValueError: could not broadcast input array from shape (761) into shape (500)
#5 opened by nawang0226 - 1
pool5_roi = self._roi_ring_pool_layer(net_conv, rois, 0., 1.0) pool5_context = self._roi_ring_pool_layer(net_conv, rois, 1.0, 1.8) pool5_frame = self._roi_ring_pool_layer(net_conv, rois, scale_inner = 1.0 / 1.8, scale_outer = 1.0)
#4 opened by yjyyy - 0
- 3