lzx1413 PytorchSSD issues

lzx1413 / PytorchSSD

pytorch version of SSD and it's enhanced methods such as RFBSSD,FSSD and RefineDet

MIT License

709 stars 237 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

all loss is nan

#109 vanson1104 opened 7 months ago
0
from .nms.cpu_nms import cpu_nms, cpu_soft_nms ImportError: /home/gabriel/PytorchSSD/utils/nms/cpu_nms.so: undefined symbol: _Py_ZeroStruct

#108 Gabriel-Arredondo opened 2 years ago
0
想问下大家，在训练的过程中又碰到AP为0的情况吗，我是用的自己的数据集训练的。num_class啥的都改过了，实在不知道该咋办了

#107 YXB-NKU opened 2 years ago
0
The mAP of SSD-Resnet is lower than SSD-VGG16.

#106 Taotaoxu opened 3 years ago
1
Unexpected key(s) in state_dict: L2Norm.weight

#105 linhl97 opened 4 years ago
2
TypeError: Expected Ptr<cv::UMat> for argument 'src'

#104 yosunpeng closed 4 years ago
1
'RFBNet' object has no attribute 'module'

#103 ZhangAdjy opened 4 years ago
0
No module named 'yacs'

#102 johsnows opened 4 years ago
0
fssd divergent

#101 lucasjinreal opened 4 years ago
1
IndexError: too many indices for array

#100 XN-0808 closed 4 years ago
1
每次到测试阶段都报错

#99 ZephyrNg opened 4 years ago
0
File "train_test.py", line 127, in <module> net = build_net(size=300, num_classes=7) File "/home/syh-hwj/daima/PytorchSSD/models/FSSD_vgg.py", line 224, in build_net return FSSD(*feature_transform_module(vgg(vgg_base[str(size)], 3), add_extras(extras[str(size)], 1024), size=300), File "/home/syh-hwj/daima/PytorchSSD/models/base_models.py", line 14, in vgg conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1) File "/home/syh-hwj/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 297, in __init__ False, _pair(0), groups, bias) File "/home/syh-hwj/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 33, in __init__ out_channels, in_channels // groups, *kernel_size)) RuntimeError: CUDA error: out of memory

#98 jaychou790118 closed 4 years ago
0
RuntimeError: copy_if failed to synchronize: device-side assert triggered

#97 Crystal950504 opened 4 years ago
0
Where can I download other pre-trained mobilenet models?

#96 sagittahjz opened 4 years ago
0
batch_size=16 or batch_size=32 ?

#95 DonghoonPark12 closed 5 years ago
1
Add HarDNet as backbone models

#94 PingoLH closed 4 years ago
1
Add HarDNet as backbone models

#93 PingoLH closed 5 years ago
0
Why Refinedet only support 320 input dim?

#92 CVkongwx opened 5 years ago
1
What is the RFB_E model in models/ folder?

#91 DonghoonPark12 opened 5 years ago
0
Where is L2Norm???

#90 DonghoonPark12 closed 5 years ago
0
No module named 'utils.nms.cpu_nms'

#89 Chida15 opened 5 years ago
0
Hi, I need your help ! RefineDet320 voc 2007 only get mAP=0.76, lower than SSD300?

#88 espectre closed 5 years ago
4
how can see map?

#87 hlh199603 opened 5 years ago
0
map test

#86 hlh199603 opened 5 years ago
0
Something I want to ask.

#85 CS-Jackson opened 5 years ago
1
ImportError: cannot import name '_mask' from 'pycocotools'

#84 CS-Jackson closed 5 years ago
2
How is the detection effect on small targets?

#83 WY51BE opened 5 years ago
2
i meet a problem

#82 YYZ-rose closed 5 years ago
1
How to specify a gpu to train?

#81 sagittahjz closed 5 years ago
2
How can I do inference after finishing the learning?

#80 NogizakaDaisuki opened 5 years ago
1
Pytorch 1.0 可以使用该代码吗？

#79 hungsing92 closed 5 years ago
1
A problem about branch 0.4

#78 SingL3 closed 1 year ago
2
FSSD_vgg架构

#77 songwsx closed 5 years ago
2
A problem with Multi-Scale test

#76 WangTianYuan closed 5 years ago
1
关于 refinedet_train_test.py

#75 rw1995 closed 5 years ago
0
shape not match problem fixed and support python2

#74 liuliu66 closed 5 years ago
0
arm decode.....

#73 AiIsBetter closed 5 years ago
0
one of the variables needed for gradient computation has been modified by an inplace operation

#72 miaoshuyu opened 5 years ago
2
RefineDet dataArgument

#71 CNHNLP opened 5 years ago
1
SSD_VGG 在VOC2007上map只有74.7%

#70 peijinwang opened 5 years ago
3
Connection reset by peer

#69 peijinwang opened 5 years ago
1
do you add resnet basenet?

#68 peijinwang closed 5 years ago
1
the architecture of FSSD_mobile

#67 fanbinqi closed 5 years ago
2
RuntimeError: randperm is only implemented for CPU

#66 achillesli closed 5 years ago
1
run ssd error:value cannot be converted to type float without overflow: inf

#65 vickersmith opened 5 years ago
3
compile make.sh error

#64 vickersmith closed 5 years ago
0
Is rgb_std = (1,1,1) in train_test.py right?

#63 beckhamchen closed 5 years ago
1
关于提供的模型文件RFB512_E_34_4.pth

#62 achillesli opened 5 years ago
2
The shape of the mask [32, 6375] at index 0 does not match the shape of the indexed tensor [204000, 1] at index 0

#61 xxlei closed 5 years ago
2
0.4branch, refinedet, training, OC&OL loss nan and memory error.

#60 liuruijin17 opened 5 years ago
2