Issues
- 0
For Efficient Graph-Based Image Segmentation, the function remove_small_components does not remove any
#55 opened by xysue2000 - 17
Key mismatch while loading the model?
#28 opened by Jumabek - 0
_Py_ZeroStruct
#54 opened by Azkarehman - 3
RuntimeError: expected backend CPU and dtype Float but got backend CPU and dtype Long
#52 opened by PRAYALANKAR - 4
Problem on Loss Function [division by zero]
#35 opened by ahkarami - 0
SSDLoss with hard negative mining
#53 opened by sandylaker - 0
is there paper about FPNSSD?
#51 opened by liuliu66 - 2
Error when testing on VOC dataset
#40 opened by bowenc0221 - 1
Corner case of box_nms
#50 opened by DHPO - 1
- 0
COCO evaluation code
#41 opened by bowenc0221 - 3
Problem in getting anchor box
#44 opened by AlanStark - 0
PyTorch Version support
#47 opened by AlanStark - 0
why with hard_example_mining use this?
#46 opened by kweisamx - 0
Some questions about train
#45 opened by LiangSiyuan21 - 0
'FPNSSD512' object has no attribute 'steps'
#43 opened by nico1as - 0
Image size while prediciton
#42 opened by MohitTare - 1
- 1
The code to generate dataset lists
#26 opened by D-X-Y - 2
"RuntimeError: seq can't be empty" in demo.py
#15 opened by nico1as - 0
Evaluation speed or frame per second?
#39 opened by zxiaomzxm - 0
Why not reduce the rgb_mean in the preprocess?
#38 opened by liuwei16 - 4
Training on new dataset
#37 opened by ljtruong - 4
Non Normalized coordinates
#30 opened by vaishnavm217 - 0
Dimension mismatch in box_coder.py
#36 opened by chrisliu54 - 2
random_crop results in image with zero target.
#16 opened by chenyuntc - 5
Scale Ratios
#34 opened by ahkarami - 0
Add Other Detection Models
#33 opened by ahkarami - 0
Change Anchor Boxes
#32 opened by ahkarami - 8
evaluation
#14 opened by nationalflag - 1
Some questions in models.ssd.net.py
#19 opened by YingdiZhang - 1
Why do you evaluate on cpu(not on gpu)?
#29 opened by Jumabek - 6
device-side assert triggered
#25 opened by AminAbd - 0
ssd training cuda problem
#27 opened by kelly08385 - 0
retina anchor box computation
#24 opened by to3i - 1
RuntimeError: dimension out of range (expected to be in range of [-1, 0], but got 1)
#23 opened by geonseoks - 0
training strategy?
#22 opened by YingdiZhang - 0
- 0
Does your train set contain difficult instances?
#20 opened by Z-Zheng - 0
How can I train FPNSSD network?
#18 opened by wang-tf - 0
why index < 0 ?
#17 opened by airyym - 3
Weights files are missing
#2 opened by lemairecarl - 0
Question about run time
#13 opened by CNSaintNeo - 0
Question about focal loss impementation
#12 opened by Tord-Zhang - 2
About the results on the Leaderboard
#11 opened by szq0214 - 0
Difference from DSSD?
#10 opened by Rizhiy - 1
Why not using models from torchvision.models?
#6 opened by aosokin - 1
will release pretrained model?
#5 opened by jxlijunhao - 2
Bug: class target can't be negative
#4 opened by lemairecarl - 1
Add license
#3 opened by lemairecarl