-
Congrats on the great work.
If I want to use your model using a custom dataset, how can I go about it? More specifically, do I need to generate the kpt_anns by myself?
-
I'm training my own dataset with mask scoring rcnn. When I run with "configs/e2e_ms_rcnn_R_50_FPN_1x.yaml", error occurred.
error to do with training:
Traceback (most recent call last):
File "tools…
-
Thank you for such an excellent job!
I would like to know how to save the images generated from the demo, and how to train the custom dataset. By the way, I run the code and test an image and get sep…
-
## Checklist:
1. 查找[历史相关issue](https://github.com/PaddlePaddle/PaddleX/issues)寻求解答
2. 翻阅[FAQ常见问题汇总和答疑](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/FAQ/FAQ.md)
3. 确认bug是否在新版本里还未修复
4…
-
Hi
I am getting this error when Loading the dataset for fine tuning.
from detr_tf.data import load_tfcsv_dataset
train_iterator, class_names = load_tfcsv_dataset("train", config.batch_size, c…
-
Traceback (most recent call last):
File "./coco.py", line 498, in
layers='heads')
File "/data/g/weidaihua/Mask_RCNN-master/model.py", line 2207, in train
validation_data=next(val_gene…
-
Hi, I am trying to reproduce your evaluation on _"ade20k_panoptic_val"_ dataset, but there is issue with the visual prompts generation. The script is looking for _anns[ann['id']] = ann_ and giving _Ke…
-
when downloading datasets，we met two errors, error info is shown as below:
A.
Initializing download: https://dl.fbaipublicfiles.com/billion-scale-ann-benchmarks/bigann/base.1B.u8bin
Unable to con…
-
in dataset_segmented.py __getitem__
the shape of seg of seg_masks is (333, 500)
the shape of img is (500, 333)
is it normal?
@waleedgondal
`seg_masks = return_segMasks(anns, self.coco)
…
-
This is my input JSON RLE:
```
segment_data_set = {
"info": {
"year": 2018,
"version": "N.A.",
"description": "fashion-pixel-annotation",
"contributor": "z…