mmfewshot

mmfewshot copied to clipboard

Hi is there plans to update this repository to be compatible with MMEngine?

austinmw

We meet problem when training on classification models. We test several times, the code is blocked on this line of command in classification.api.train

jwfanDL

When I was studying the process of small sample learning, I came across tiff images in the data set. At this point, there is a problem with the dataset loading,...

jianandeng023

**Describe the bug** I run the "demo/demo_attention_rpn_detector_inference.py.py" as example arguments, and it works. However, when I change the option "proto-net" to "baseline++" the error happened as follow. ``` File "C:\GitSource\SolVision3.0\AI_Vision_WPF\TaskProcess\bin\x64\Release\PYD\slmmm\packages\mmfewshot\demo\demo_metric_classifier_1shot_inference.py",...

p890040

save best weights

1

I set evaluation = dict(interval=2000, metric='bbox', classwise=True, save_best='auto') to save the best weight like mmdetection, but it does not work. What should I do? thanks

s690

In base training of Meta RCNN, when I use one_support_shot_per_iamge=True, the loss is normal，while when I use one_support_shot_per_iamge=False, the loss will become nan. besides, I find that only one target...

s690

chamfer_distance_forward miss in module _ext

2

python ./tools/classification/train.py configs/classification/baseline/cub/baseline_conv4_1xb64_cub_5way-1shot.py No CUDA runtime is found, using CUDA_HOME=':/usr/local/cuda-11.1' Traceback (most recent call last): File "./tools/classification/train.py", line 13, in from mmcls.models import build_classifier File "/anaconda3/envs/openmmlab/lib/python3.7/site-packages/mmcls/models/__init__.py", line 2, in from...

henbucuoshanghai

How to set seed to non for training, so that the results have randomness

qjh666888

I am using a custom COCO-type dataset. The classes and everything are updated, and in my log file, it can pick up my dataset and divide it according to the...

imadgohar

I am using TFA, the dataset is in VOC format. I have total 5 classes and in three splits I am dividing it like this ALL CLASSES=[A,B,C,D,E] Split_1_base=[A,B,C,D] Split_2_base=[A,B,C] Split_3_base=[A,B]...

imadgohar