Comments (8)
I know the problem....
If you want to test the performance on DOTA, you must download and prepare the dataset. https://github.com/csuhan/ReDet/blob/master/GETTING_STARTED.md
While the modifications to
demo_large_image.py
is just for inference on a single image.
Yup, that's what I'm thinking too. It's just that the DOTA dataset filesize is so big, I'll try to download it. Thanks for the help btw.
from redet.
we have not tested on colab.
You can try pip install jupyter
or pip install ipykernel
.
Please note our repo requires torch<=1.3 (it may be hard to install on colab via pip).
from redet.
we have not tested on colab.
You can trypip install jupyter
orpip install ipykernel
.Please note our repo requires torch<=1.3 (it may be hard to install on colab via pip).
I've installed the ipykernel now, but I have another issue.
ReResNet Orientation: 8 Fix Params: False
loading annotations into memory...
Traceback (most recent call last):
File "demo_large_image.py", line 137, in <module>
r"work_dirs/ReDet_re50_refpn_1x_dota15_ms/ReDet_re50_refpn_1x_dota15_ms-9d1a523c.pth")
File "demo_large_image.py", line 89, in __init__
self.dataset = get_dataset(self.data_test)
File "/content/ReDet/mmdet/datasets/utils.py", line 109, in get_dataset
dset = obj_from_dict(data_info, datasets)
File "/usr/local/lib/python3.7/site-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/utils.py", line 78, in obj_from_dict
return obj_type(**args)
File "/content/ReDet/mmdet/datasets/custom.py", line 68, in __init__
self.img_infos = self.load_annotations(ann_file)
File "/content/ReDet/mmdet/datasets/coco.py", line 25, in load_annotations
self.coco = COCO(ann_file)
File "/usr/local/lib/python3.7/site-packages/pycocotools-2.0.2-py3.7-linux-x86_64.egg/pycocotools/coco.py", line 84, in __init__
with open(annotation_file, 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/workfs/jmhan/dota15_1024_ms/test1024/DOTA1_5_test1024.json
from redet.
Please refer to https://github.com/csuhan/ReDet/blob/master/INSTALL.md for data preparation
from redet.
Please refer to https://github.com/csuhan/ReDet/blob/master/INSTALL.md for data preparation
Yep, I followed all in the INSTALL.md
Here is my colab link for ReDet: https://colab.research.google.com/drive/1MARFKSAUTHUu4lA7eYLA0TLrQZm9WOZF?usp=sharing
from redet.
Yeah, the reason is our inference code tries to get the classname
tuple with the function get_dataset
, while get_dataset
requires annotation files:
FileNotFoundError: [Errno 2] No such file or directory: '/workfs/jmhan/dota15_1024_ms/test1024/DOTA1_5_test1024.json
To temporarily solve the issue,
Lines 89 to 90 in 44825e6
Try to replace the two lines above with
# for DOTA v1.0
self.classnames = ('plane', 'baseball-diamond',
'bridge', 'ground-track-field',
'small-vehicle', 'large-vehicle',
'ship', 'tennis-court',
'basketball-court', 'storage-tank',
'soccer-ball-field', 'roundabout',
'harbor', 'swimming-pool',
'helicopter')
from redet.
@csuhan Thanks for the help. Sorry to bother, but I still got the same error.
my colab can be run directly here: https://colab.research.google.com/drive/1MARFKSAUTHUu4lA7eYLA0TLrQZm9WOZF?usp=sharing
can you try running it in your colab to see if the same error persist?
from redet.
I know the problem....
If you want to test the performance on DOTA, you must download and prepare the dataset. https://github.com/csuhan/ReDet/blob/master/GETTING_STARTED.md
While the modifications to demo_large_image.py
is just for inference on a single image.
from redet.
Related Issues (20)
- ReDet with Dota 1 multiscale OBB - only able to achieve 79.2% so far HOT 5
- Update Regression Losses Dictionary HOT 1
- mmcv 无法导入 DictAction, mmcv.runner无法导入init_dist HOT 2
- 执行test.py时,提示缺少val.txt文件,我该如何获得这个文件呢?
- Can I run ReDet by removing the ReFPN part
- /ReDet_re50_refpn_1x_dota15_ms/ReDet_re50_refpn_1x_dota15_ms-9d1a523c.pth is not a checkpoint file
- The slow speed of test
- The training failed even though the accuracy up to 99.7 and the loss is 0.2 HOT 1
- ninja: error: build.ninja:3: lexing error HOT 1
- ImageNet accuracy HOT 1
- 将RPN head改成FCOS head该怎么操作呢,我看您的代码里有FCOShead的代码
- Test error
- calculate the map
- Set batchsize in inference
- HRSC2016 HOT 1
- 我用re-resnet50替换其他特征提取网络时发生了错误,能帮我解答吗,问题如下。 HOT 1
- nv
- Welcome update to OpenMMLab 2.0
- ReResnet50 pretrain model difference HOT 1
- 作者您好,将特征图用您给的方法进行可视化后无法达到您论文中给出的可视化图的效果,请问什么原因呢,飞机没有清晰的结构
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from redet.