ModuleNotFoundError: No module named 'ipykernel' about redet

[chandlerbing65nm]

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.

[csuhan]

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).

[chandlerbing65nm]

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).

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

[csuhan]

Please refer to https://github.com/csuhan/ReDet/blob/master/INSTALL.md for data preparation

[chandlerbing65nm]

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

[csuhan]

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,

ReDet/demo_large_image.py

Lines 89 to 90 in 44825e6

	self.dataset = get_dataset(self.data_test)
	self.classnames = self.dataset.CLASSES

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')

[chandlerbing65nm]

@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?

[csuhan]

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.