inference.py

[wml666666]

Hello, when I was executing the inference.py file, I was prompted that "FPD is not in the models registry". I have executed "python setup.py install", but I am still experiencing this error when inference.

[wml666666]

Hi there, I hope you're doing well. I just wanted to follow up on my previous message regarding FPD inference. If you could provide an update or let me know when you might be able to respond, that would be greatly appreciated. Thank you!

[wangchen1801]

Hello, sorry for the late reply, I might not be able to respond promptly due to due to being busy with work.

However, this issue did not occur in my environment. Please try reinstalling this repository, and make sure "python setup.py install" is running in the right folder (not in the mmfewshot folder).

[wml666666]

Hello, sorry for the late reply, I might not be able to respond promptly due to due to being busy with work.

However, this issue did not occur in my environment. Please try reinstalling this repository, and make sure "python setup.py install" is running in the right folder (not in the mmfewshot folder).

Thank you for taking the time to reply to my message. I apologize for any inconvenience caused. I am glad to receive your feedback, which is very valuable to me. Thank you again for your help, and I hope your work goes smoothly.

[wangchen1801]

Thanks! Feel free to ask if you still have any questions.

[wml666666]

Thanks! Feel free to ask if you still have any questions.

Sorry to bother you, can you provide a script command for inference, similar to the training and testing you mentioned in README：
”# base trainingR
bash dist_train.sh
configs/fpd/voc/split1/fpd_r101_c4_2xb4_voc-split1_base-training.py 2
bash dist_test.sh
configs/fpd/voc/split1/fpd_r101_c4_2xb4_voc-split1_10shot-fine-tuning.py
./work_dirs/fpd_r101_c4_2xb4_voc-split1_10shot-fine-tuning/fpd_r101_c4_2xb4_voc-split1_10shot-fine-tuning_iter_2400.pth 2 “
Thank you very much!

[wangchen1801]

Hello, you might be referring to the inference.py in the mmfewshot. I haven't used this file before and can't provide instructions at the moment. However, I would recommend checking out the documentation in the mmfewshot or MMDetection repositories. They might have the information you're looking for.

[wml666666]

Hello, you might be referring to the inference.py in the mmfewshot. I haven't used this file before and can't provide instructions at the moment. However, I would recommend checking out the documentation in the mmfewshot or MMDetection repositories. They might have the information you're looking for.

Okay, thank you for your reply. There is also a question about "average results over multiple runs" that needs to be consulted. Is this result the average of multiple fine-tuning training results with different fewshot samples, or is it the average of multiple testing results with the fine-tuning training weights and then changing the fewshot samples.

[wangchen1801]

It refers to different fewshot samples. See issue#5 for more information.

[wml666666]

It refers to different fewshot samples. See issue#5 for more information.

Thank you for your response. I have already looked into issue # 5 you mentioned in advance, but I am still a bit confused. After changing the benchmark_ [K] shot.txt, do we need to conduct testing directly, or do we need to perform fine-tuning train and testing, or do we need to re execute all processes including base-training, fine-tuning train, and testing.

[wangchen1801]

We only need to fine-tuning the model on the new fewshot samples, i.e. perform fine-tuning train and testing.

[wml666666]

We only need to fine-tuning the model on the new fewshot samples, i.e. perform fine-tuning train and testing.

Okay, thank you for your reply. Thank you very much. Wishing you a happy life and smooth work!