Clustered-Object-Detection-in-Aerial-Image

Clustered-Object-Detection-in-Aerial-Image copied to clipboard

Datasets

4

In the paper, you select a portion of the DOTA dataset for training and validation, can you share it?

Gary3410

can you share the code about uavdt format to json or xml format transform code?

2

can you share the code about uavdt format to json or xml format transform code?

wong1998

Generating cluster region ground truth

11

I want to train model in server, so I can not run: run "./detectron/ops/add_cluster_annotation.m" to generate cluster ground truth and add it to original object annotation files. run "./detectron/ops/visdrone2cocoformat.m" to...

sh7jacobi

Error on training

2

I have the error on training: terminate called after throwing an instance of 'caffe2::EnforceNotMet' what(): [enforce fail at conv_op_cudnn.cc:572] status == CUDNN_STATUS_SUCCESS. 8 vs 0. , Error at: /var/lib/jenkins/workspace/caffe2/operators/conv_op_cudnn.cc:572: CUDNN_STATUS_EXECUTION_FAILED...

sh7jacobi

Train with random weights

1

How I can train without pretrained weights?

sh7jacobi

Docker build Failed

1

I assume that there are problems with versions. For example, last version of opencv is not supported by python2. In this docker is used the python2. Also there is the...

sh7jacobi

MeanShiftCluster Can't be found

3

I met this problem when I run the matlab file: Clustered-Object-Detection-in-Aerial-Image/detectron/ops/add_cluster_annotation.m and I can't find the definition to this function. Looking forward to your reply, thanks.

ZhipeiYang

pre-trained model

4

Kindly share your trained model. Thanks, Ajmal

ma-siddiqui

AssertionError: Detectron ops lib not found; make sure that your Caffe2 version includes Detectron module

1

After I run the makefile, and run: python detectron/tests/test_spatial_narrow_as_op.py then i get this tip. I can make it from the official Detectron but can't run the train process

ZhipeiYang

How long will the code be released?

1

I am very interested in your excellent research and look forward to your release of your experimental code. Look forward to your reply. Thanks.

ZhipeiYang