msracver Deformable-ConvNets issues

msracver / Deformable-ConvNets

Deformable Convolutional Networks

MIT License

4.01k stars 953 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

About the range of offset

#302 Chris-city opened 12 months ago
1
PyTorch version of deformable convolution does not exist

#301 ghost closed 1 year ago
1
src/cpu/dcn_v2_cpu.cpp:227:55: 错误：‘THFloatBlas_gemv’在此作用域中尚未声明

#300 oszn opened 2 years ago
0
Is it useful to use dcn on 1x1conv?

#299 kirkzZ opened 2 years ago
1
convert to onnx

#298 ggsddu7 opened 2 years ago
0
fix test

#284 kinney-sun opened 3 years ago
0
How to get the sampling points?

#283 kirkzZ closed 2 years ago
4
How to get the receptive field?

#282 kirkzZ closed 2 years ago
4
fix error in modulated_deformable_conv function

#281 developer0hye opened 3 years ago
0
Why is the magnitude of mask multiplied by 2?

#280 developer0hye opened 3 years ago
1
Some questions of the testting process in classification tasks

#279 crocodilegogogo opened 3 years ago
0
occasions where sampling locations are outside of the image boundary

#278 vlee-harmonicinc opened 4 years ago
0
Does anyone sovle the problem of over large offset?

#277 hmjbuaa opened 4 years ago
1
visualize the deformable convolution of rcnn_dcn

#276 xuwwwux closed 4 years ago
0
DCN for 3D

#275 doramran opened 4 years ago
0
The channels' order of offsets layer

#274 whulc opened 4 years ago
0
error when run deeplab(cityscapes) ValueError: zero-size array to reduction operation minimum which has no identity`

#273 zyxu1996 opened 4 years ago
0
compile DCN v2 fatal error: ../linalg.h: No such file or directory

#272 jiashu-zhu opened 4 years ago
4
Deeplab Training Detail

#271 donhk1011 opened 4 years ago
0
Has anyone successfully trained Faster-RCNN with Modulated Deformable Conv?

#270 chongruo opened 4 years ago
0
Can I only use CUDA8.0?

#269 WHY95666 opened 4 years ago
0
Question about num_deformable_group

#268 chongruo closed 4 years ago
3
docs: fix typo

#267 Jason-Cooke opened 4 years ago
0
mxnet.base.MXNetError: Error in operator fpn_p4_sum:

#266 herrickli opened 4 years ago
1
dcn = DCN(64, 64, kernel_size=(3,3), stride=1, padding=1, deformable_groups=2).cuda()

#265 xiaoliqiangxxqzz opened 4 years ago
0
undefined symbol: _ZN2at7getTypeERKNS_6TensorE

#264 xiaoliqiangxxqzz opened 4 years ago
2
Update pascal_voc_eval.py

#263 light201212 opened 4 years ago
0
Could you provide results file in json form from DCN v2?

#262 ArchNew opened 4 years ago
0
##

#261 evorta closed 5 years ago
0
#

#260 evorta closed 5 years ago
0
raise MXNetError(py_str(_LIB.MXGetLastError()))

#259 wander1985 opened 5 years ago
0
keras deformable

#258 ICDI0906 opened 5 years ago
0
Which version of tensorflow should be used?

#257 wander1985 closed 5 years ago
0
What does `mAP@0.75` mean?

#256 jiec-msft closed 5 years ago
1
Is the evaluation correct for pascal segmentation ?

#255 pengwangucla opened 5 years ago
0
Symbol file to train DCNv2

#254 miraj7789 opened 5 years ago
0
windows10 when i build cython ,someone can help me ?i really don't know how to deal.

#253 gdut3118007086 opened 5 years ago
0
Confusion about why a single conv layer is able to learn the offsets

#252 eezywu opened 5 years ago
3
why not use im2col_step in ModulatedDeformableConvolutionOp?

#251 Google1234 opened 5 years ago
0
why use conv-layer to predict conv offset while fc-layer predict pool offset?

#250 hust-kevin opened 5 years ago
1
Question about dcnv2 ops

#249 henrylee2570 opened 5 years ago
0
Exception while resuming training: assert isinstance(step, list) and len(step) >= 1 AssertionError

#248 pervaizniazi opened 5 years ago
1
RCNNLogLoss not decreas

#247 zhengye1995 opened 5 years ago
0
Could you explain why mask generated by Sigmoid in mdcn is doubled?

#246 JrPeng opened 5 years ago
1
this gemm operation seemes useless

#245 BIGKnight closed 5 years ago
1
RpnL1loss is very high when I use 8gpus and change lr to 0.01

#244 anorthman opened 5 years ago
0
loss

#243 anorthman closed 5 years ago
0
In readme, for deeplab, we use 4 GPUs for all experiments

#242 KeyKy opened 5 years ago
0
Seems the implementation of offsets is different from the original paper?

#241 SUZhaoyu opened 5 years ago
1
why slicing the input data at the batch dimension ?

#240 Google1234 closed 5 years ago
0