-
Hi Detectron,
Recently I tried to add my custom coco data to run Detectron and encountered the following issues.
(1) "segmentation" in coco data like below，
{"segmentation": **[[**499.71, 397.2…
-
トップページが地味なので、有名かつ魅力的なあたらしめのモデルの動作イメージを縮小して数枚配置したいと思います。
-
### 问题确认 Search before asking
- [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
## 评估结果
```
python tools/eval.py -c configs/p…
-
The number of files after conversion is less than the number of files in json. Also some of the converted files have empty labels.
-
### 📚 The doc issue
Hi, is it possible to subclass/reuse `torchvision.prototype.datasets.Coco` to create a custom COCO-format DataPipe? For example If I have the following data:
```
data/vision…
-
I want to just have a try training in a smaller dataset(about 150 image files, and I also generate my own annotation json file). when running train.lua, the program got stuck in "start training". I pr…
-
```
(paddlex_det) C:\Paddle\PaddleX-release-3.0-beta1>python main.py -c paddlex/configs/semantic_segmentation/Deeplabv3_Plus-R50.yaml -o Global.mode=evaluate -o Global.dataset_dir=F:\Bai\V2\Datasets\…
-
Hi, I need to be able to load the pre-trained model and apply it to unseen images (not train or val images), and then output the coco.json annotations file (and also image masks.png would be good). Ho…
-
### Describe your problem in detail.
Opening this issue as suggested by @Remi-Gau in [this Neurostars topic](https://neurostars.org/t/bids-space-entity-orig/25679). In writing a BIDS app that needs…
-
Thanks for sharing your code.It makes life easier.I have one question that will it improve the performance if I combine multiple dataset to train the model?