issues
search
DingXiaoH
/
RepVGG
RepVGG: Making VGG-style ConvNets Great Again
MIT License
3.3k
stars
433
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Why would you use 3x3+1x1+identity instead of 3x3+3x3+identity?
#119
hopef
opened
5 months ago
0
Running example_pspnet.py generates an error: raise NotImplementedError
#118
fhf526
closed
6 months ago
1
The diff is large when BN use other initialization method in verify script
#117
2h4dl
opened
8 months ago
0
Question about training and inference models
#116
hosytuyen
opened
8 months ago
0
为什么SEBlock中使用Conv2D而不是Linear层？
#115
Z-Xiong
closed
9 months ago
1
关于量化的问题，一般是对重参数化后的模型，再进一步进行量化的吗
#114
LKAMING97
opened
10 months ago
0
多分支存在非线性的合并
#113
piaohe20221128
opened
10 months ago
1
Question about RepVGG usage for downstream task
#112
imdsafi09
closed
10 months ago
0
为什么RepVgg的单个block拿出来测试，重参数化前后输出的结果是不一样的
#111
lokiwizard
closed
1 year ago
0
a mistake in code
#110
Halance
opened
1 year ago
1
jit.trace error
#109
nistarlwc
opened
1 year ago
0
关于多卡训练卡死的问题
#108
SEUvictor
opened
1 year ago
1
The bug of QAT
#107
qhy991
opened
1 year ago
0
Training script inquiry
#106
zw615
opened
1 year ago
0
Question about multi-branch and single-branch network
#105
MiaoJieF
opened
1 year ago
1
subprocess.CalledProcessError: Command '['/usr/bin/python3', '-u', 'main.py', '--local_rank=0']' returned non-zero exit status 1.
#104
starsky68
closed
1 year ago
0
请问如果我用RepVGG作为backbone，并且在neck中有其他的操作，比如5*5卷积，这样训练出来的模型还能做结构重参数化吗？
#103
AssassinJay
closed
1 year ago
1
how to prune repvgg
#102
sinoaidi
opened
1 year ago
0
Paper Question - Why less favored than MobileNets for low-powered devices?
#101
ksachdeva
opened
1 year ago
1
why get different result after reparam
#100
fenghuoxiguozu
opened
1 year ago
3
eq_kernel in get_custom_L2 missing contribution of rbr_identity.
#99
vchiley
opened
1 year ago
0
question about insert BN before QAT
#98
zhaoxin111
opened
1 year ago
0
How is 1x1 conv with identity matrix as kernel equal to Identity layer
#97
prakashjayy
closed
1 year ago
1
mmsegmentation
#96
endaoguansanlu
opened
1 year ago
0
convert.py
#95
HonestyBrave
closed
1 year ago
0
CIFAR10训练的参数？
#94
wooozihui
opened
1 year ago
0
关于repconv switch-to-deploy的问题
#93
pierrelzw
opened
1 year ago
0
what matter does "get_custom_L2" do?
#92
shoutOutYangJie
opened
2 years ago
1
Re-params quantized RepVGG model
#91
thancaocuong
closed
2 years ago
2
Any reference about get_custom_L2?
#90
JoJoistheBestOne
closed
2 years ago
1
Paper Question: Use compression idea and generate same result as multi-branch model?
#89
oconnor127
opened
2 years ago
1
why not use python3 -m torch.distributed.launch
#88
xiangyun-hz
closed
2 years ago
0
3x3 convolution
#87
SpiritAshes
closed
2 years ago
1
Hyperparameters for RepVGGplus-L2pse
#86
zhreshold
opened
2 years ago
0
Some questions about quantization
#85
Desmond-97
opened
2 years ago
9
MegEngine Implemention of RepVGG
#84
Asthestarsfalll
closed
1 year ago
0
SSD with RepVGG backbone
#83
thuangb
opened
2 years ago
2
for style transfer task training
#82
MaltoseMai
opened
2 years ago
0
Training with another dataset?
#81
Enescigdem
closed
2 years ago
1
questions about training on custom datasets？
#80
Hezhexi2002
opened
2 years ago
0
PTQ精度问题
#79
huoshuai-dot
closed
2 years ago
1
How to understand the Structural re-parameterization of a RepVGG block
#78
jyang68sh
closed
2 years ago
2
Given input size: (64x240x320). Calculated output size: (64x0x1). Output size is too small
#77
DonMuv
opened
2 years ago
1
anyone use repvgg backbone in insightface face recognition task?
#76
xiakj
opened
2 years ago
1
Update Arxiv Paper with RepVGGplus
#75
Zacharias030
opened
2 years ago
2
Where is the re-parameter module?
#74
typhoonlee
opened
2 years ago
2
Weight decay will be applied to the weight of BN in identity branch and the weight of FC when using --custwd?
#73
wangjinwei94
closed
2 years ago
2
RepVGGplus-L2pse how to compute acc top 1 top 5
#72
chgit0214
closed
2 years ago
2
RepVGGplus-L2pse用于回归任务需要修改最后的输出吗
#71
z965631
opened
2 years ago
0
test memory
#70
Qingyuncookie
closed
2 years ago
1
Next