mmfewshot

mmfewshot copied to clipboard

bad performance of Attention RPN in base training

2

When i train the attention rpn model in the base training stage, the performance is bad and far away from that of other detectors (meta rcnn), what may be the...

Fly-dream12

save_best=True while encountering empty result

1

**Describe the bug** Hi! I was deploying mmfewshot detection model on my own dataset. And "save_best=True" was added in evaluation dict. Error happens for ckpt saving when empty result come...

Chan-Sun

fatal: ambiguous argument 'HEAD': unknown revision or path not in the working tree. Use '--' to separate paths from revisions, like this: 'git <command> [<revision>...] -- [<file>...]'

1

我是用fsce的base训练，出现以下错误 fatal: ambiguous argument 'HEAD': unknown revision or path not in the working tree. Use '--' to separate paths from revisions, like this: 'git [...] -- [...]' 貌似和git提交有关 但是我并不需要提交任何代码

909368135

IndexError: FewShotCocoDataset: list index out of range

6

train config: python tools/detection/train.py configs/detection/fsce/coco/fsce_r101_fpn_coco_base-training.py I want to train my own dataset with mmfewshot, so I modified the categories in BASE_CLASS in coco.py. The result is an error: Traceback (most...

sanmulab

how to transfer attentionRPN to onnx format？

1

wang-kangkang

CPU overload

2

When running program CPU is heavily overload which is not gonna happen on MMDETECTION(in my experience)?

JulioZhao97

NwayKshotDataset初始化num_used_support_shots=None报错

1

NwayKshot这个类里面，我把num_used_support_shots初始化None,但是调用prepare_support_shots方法的时候又对num_used_support_shot进行“

rolsheng

result index in show of test.py

1

https://github.com/open-mmlab/mmfewshot/blob/main/mmfewshot/detection/apis/test.py#L72 ``` if is_module_wrapper(model): model.module.show_result( img_show, result[i], show=show, out_file=out_file, score_thr=show_score_thr) ``` should the index of result is j? result[j]? I get an error: IndexError: list index out of range

wang-kangkang

[Fix] single gpu test bug

1

## Motivation When the output result needs to be saved and a single gpu test is used, an error will be reported. The solution is to change result[i] in the...

LiangYang666

FSCE finetuning results with CPE loss on COCO

2

Hi, thank you for great codes! I find that there is no finetuning results of FSCE with CPE loss in the model zoo page (contrastive loss is None). Can you...

williamking5