fundamentalvision/Deformable-DETR
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
PythonApache-2.0
Issues
- 0
单机多卡训练卡住
#240 opened by sevenandseven - 1
- 0
关于MSDeformAttn中sampling_locations的归一化如何理解问题
#239 opened by 20231211 - 3
- 2
*Ignore this post
#237 opened by K20qhuy - 3
Problem of error in ms_deformable_im2col_cuda: no kernel image is available for execution on the device in NVIDIA GeForce RTX 3090
#202 opened by momo1986 - 1
Extracting mAP for each class
#236 opened by HeinZingerRyo - 0
cuda problem of MSDA
#234 opened by bluemoon223 - 0
Reference points
#233 opened by ReefAlturki - 0
可视化问题
#231 opened by fengmuyanghua - 2
DLL load failed while importing MultiScaleDeformableAttention: %1 不是有效的 Win32 应用程序。如何解决?
#216 opened by wanghua12 - 0
Format of groundtruth bounding box format
#230 opened by zhi-dian - 4
How to visulize the sampling points?
#194 opened by quxu91 - 0
- 0
- 0
Question about sampling_offest, sampling_locations normalize for F.grid_sample
#227 opened by SnaKey0u0 - 0
Does MSDeformable support torch.compile?
#226 opened by Lwzzzzzz - 1
- 3
undefined symbol: _Z27ms_deform_attn_cuda_forwardRKN2at6TensorES2_S2_S2_S2_i
#225 opened by bshakya77 - 0
batch % im2col_step_ == 0 INTERNAL ASSERT FAILED
#224 opened by bio-mlhui - 1
No module named 'MultiScaleDeformableAttention'
#223 opened by CODERED555 - 6
I have successfully installed groundingdino and can run through the code using 3090, but an error will be reported when using A100 or V100.
#210 opened by zdxff - 0
- 0
- 6
NotImplementedError: Cuda is not availabel
#207 opened by Chenxu-666 - 1
AttributeError: module 'MultiScaleDeformableAttention' has no attribute 'ms_deform_attn_forward'
#220 opened by iGFreedom - 1
What do the four values of pred_box mean?
#217 opened by small-code-cat - 0
Is this repository still usable on Google Colab?
#219 opened by victoic - 1
about the information of query embeddings
#190 opened by aooating - 1
- 0
Why is the class-error always 100 when I train on a class with deformable detr, and the final prediction result is the background
#215 opened by xiao-student12 - 0
Confusing in the notation x_k and z_q
#214 opened by wennycooper - 1
problem with exporting the model into torchscript
#211 opened by Zalways - 0
RuntimeError: Could not export Python function call 'MSDeformAttnFunction'. Remove calls to Python functions before export. Did you forget to add @script or @script_method annotation? If this is a nn.ModuleList, add it to __constants__:
#212 opened by Zalways - 1
- 1
Compile error
#209 opened by MrPeterJin - 1
Tracing the Deformable Attention Module
#208 opened by Mona77 - 1
Compiling CUDA operators?
#203 opened by narwyllllll - 1
CUDA Compile Operators
#193 opened by kapilrs2 - 0
model implementation question
#206 opened by shamanneo - 0
Error Separting Backbone from Deformable DETR
#205 opened by victoic - 1
Why is the classification cost in matcher formulated as the positive minus negative?
#200 opened by Godricly - 0
- 0
About Segmentation
#199 opened by sirosann - 0
The Meaning of Variables (src_valid_ratios)
#197 opened by haiyang426 - 0
parallel problem
#195 opened by huxycn - 3
- 0
AP=0,how to solve?thanks
#191 opened by M088 - 0
- 0
Small scale object detection issue
#188 opened by aliman80