Questions about Resnet 12 backbone

[LoveMiki]

Hello, I am reading your codes and there are a few questions i want to ask.

1. What is the purpose of the outputs of second last layer? I found that the outputs of second last layer are used to compute the point similarities, but why don't we just use the outputs of the last layer(i.e., embedding features of images)?
2. What is the exact meaning of num_queries? You describe it as the number of samples in query set, so when num_queries = 1, dose it means that there is only one image in query set? However, i found that the there are five images in the query set when num_queries is set to 1.

[Godxia]

The second question. num_queries = 1 means 1query image every way

[LoveMiki]

The second question. num_queries = 1 means 1query image every way

As I have mentioned, there are 5 images (way) per class (shot) when num_queries = 1

[AlienceGG]

Hello, I am reading your codes and there are a few questions i want to ask.

1. What is the purpose of the outputs of second last layer? I found that the outputs of second last layer are used to compute the point similarities, but why don't we just use the outputs of the last layer(i.e., embedding features of images)?
2. What is the exact meaning of num_queries? You describe it as the number of samples in query set, so when num_queries = 1, dose it means that there is only one image in query set? However, i found that the there are five images in the query set when num_queries is set to 1.

1. The second last layer is utilized for better generalization in DPGN, which might provide more userful information in initialization.
2. Because it has 5 way. :) num_queries means num_queries per way.

Yours
DPGN team

[lgx12345678]

Hello, I encountered this error when running the command python3 main.py --dataset_root dataset/ --config config/5way_1shot_resnet12_mini-imagenet.py --num_gpu 0 --mode train: RuntimeError: Given input size: (512x6x6). Calculated output size: (512x0x0). Output size is too small. I haven't made any changes to any other parts of the code or configuration. How can I resolve this issue?