joe-siyuan-qiao / DetectoRS

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

joe-siyuan-qiao/DetectoRS Issues

fusion module no found未找到问题
Updated 5 months ago
Welcome update to OpenMMLab 2.0
Updated a year ago
hello,How to use RFP to own network, using PyTorch, without MMD,please
Updated 2 years ago1
only detection for DetectoRS
Updated 2 years ago1
BiFPN and RFP
Updated 2 years ago1
trained r50 model
Updated 2 years ago
from . import deform_conv_cuda error
Updated 2 years ago2
Is x(t,i-1) equal to x(t-1,i-1)?
Updated 2 years ago
I am a deep learning researcher. When I deployed version V2 and started training, ROOt_dir was not found, but I clearly configured this directory. I would like to ask, what is the cause of this, is it system related
Updated 3 years ago
from . import deform_conv_cuda ImportError: cannot import name 'deform_conv_cuda' from 'mmdet.ops.dcn'
Updated 3 years ago
Please add ability to do Panoptic Segmentation
Updated 3 years ago3
Hello, can RFP be used instead of FPN for one-stage detectors？
Updated 3 years ago
recursive fpn
Closed 3 years ago
replace FPN with RFP
Updated 3 years ago9
Hello, I just integrated recursive FPN into FoveBox, but there was an error: KeyError: 'FPN is not in the neck Registry ', can you help me
Updated 3 years ago1
GPU and training
Updated 3 years ago1
Failed to export onnx model
Updated 3 years ago
Implementation detail about detectoRS
Updated 3 years ago1
how to use RFP instead of FPN
Updated 4 years ago
instruction execution error in conda
Updated 4 years ago
KeyError: 'PointSetAnchorDetector is not in the detector registry'
Updated 4 years ago
TypeError: bbox_head={'num_classes': 1} in child config cannot inherit from base because bbox_head is a dict in the child config but is of type <class 'list'> in base config. You may set `_delete_=True` to ignore the base config
Updated 4 years ago
KeyError: 'ConvWS is already registered in conv layer'
Updated 4 years ago1
DetectoRS with mmdetection2
Updated 4 years ago3
The problem is “The model and loaded state dict do not match exactly”
Updated 4 years ago2
IndexError: list index out of range
Updated 4 years ago3
rfp and stage_with_rfp
Updated 4 years ago
Syntax errors in config file: Instance segmentation through DetectoRS-ResNeXt-101-32x4d
Updated 4 years ago
how to get stuffthingmaps/train2017/ dataset?
Updated 4 years ago3
About ASPP Module
Updated 4 years ago1
MMCV version
Updated 4 years ago
Model usage
Updated 4 years ago2
RFP file
Updated 4 years ago1
Why don't use sigmoid in the switch
Updated 4 years ago2
An issue on re-implementation with COCO2017 dataset
Updated 4 years ago1
Confused installation specification
Updated 4 years ago1
custom dataset without 'stuffthingmaps'
Closed 4 years ago1
Class-Incremental Training for saving training time
Updated 4 years ago1
The size of 'out' and 'rfp_feat' is not match
Updated 4 years ago1
I got an error report when training
Closed 4 years ago1
The configuration file that does target detection alone，how to change it?
Closed 4 years ago
max scale is 1333*800,how to use 4096 * 2048??
Updated 4 years ago1
TypeError: __init__() got an unexpected keyword argument 'rfp' for mmdet v2.0 branch
Closed 4 years ago2
TTA Question
Updated 4 years ago1
How to train this model on custom coco dataset?
Updated 4 years ago1
Can I use the model for only object detection?
Updated 4 years ago1
reproduce detectoRS htc x101 performance on coco
Updated 4 years ago7
only run object detection without running segmented part of the instance.
Updated 4 years ago1
AssertionError: Caught AssertionError in DataLoader worker process 0.
Updated 4 years ago1
Custom Training
Updated 4 years ago1