AirDet

AirDet copied to clipboard

Test result of COCO dataset

1

I tried to reproduce according to the steps in the README, and finally got the test results as shown in the figure. I don't know whether this result is correct....

dhgras

Inference

1

Is there anyway that I can use your weight to do inference via webcam? Would it be prossible if you could provide inference part. I have tried to use the...

Remosy

The fine-tuning code

2

When is the fine-tuned code updated? I think it is also important to reproduce your performance.

shanguangcv

the question of Numclass seting

1

The Numclass of coco is 80,Why is the NUM_CLASSES of Base-FSOD-C4.yaml set 1.

liuyuxun12

IndexError: list index out of range

2

您好， 使用数据集coco_2017_train_nonvoc时可以进行训练。 使用数据集coco_2017_train_voc_1_shot时会报错。  请问，这是什么问题造成的？

CodeUp-Ma

The performance of other methods in Table 1

1

Hi, in Table 1, you compare your model with some other methods on COCO 2017. In previous works, other methods perform experiments on COCO 2014 and report 10-shot and 30-shot...

shanguangcv

"ignore" in COCO json file is not supported

1

AIMan-Zzx

The weight of R101 provided

1

In the paper, R101 is frozen in stem and ResNet1 block. However, I print the weights and they are different from the in1k R101 model. Have they finetuned?

dmy1997

In COCO, I Get a very low AP score, how can I fix it?

8

I get less than 3 AP in COCO, but I get the AP that similar to you in VOC; I check my output log find that many object in COCO...

sixone-Jiang

Correct supports cannot be generated in the VOC dataset

1

When I execute this line of code:bash generate_support_data.sh I found that adjusting the value of the shot only generated 1-shot，it may be that my file structure is not right, can...

lgzid