Final_Output_Size vector? Will it be image with embeddings?

[ssaikiran123]

System information (version)

• Pytorch => :grey_question:
• Operating System / Platform => :grey_question:
• Cuda => :grey_question:

Detailed description

Steps to reproduce

Issue submission checklist

• [ ] I checked the problem with documentation, FAQ, issues, and have not found solution. 1.Please let me know what is the final output vector size and will it give me the image with embeddings for CASIA B? 2.I went through the paper and know that each frame image is being normalized to 64x44 and 3major process are 1.Local Temporal Aggregation(LTA) 2.Global and Local Feature Extraction(GLFE) 3.Generalize Mean(Gem) Pooling player in Feature Mapping. Final output from the model is Yout from feature mapping which is a vector.

3. I referred this paper GaitGL(ICCV2021)

[ssaikiran123]

1.Please let me know what is the final output vector size and will it give me the image with embeddings for CASIA B? 2.I went through the paper and know that each frame image is being normalized to 64x44 and 3major process are 1.Local Temporal Aggregation(LTA) 2.Global and Local Feature Extraction(GLFE) 3.Generalize Mean(Gem) Pooling player in Feature Mapping. Final output from the model is Yout from feature mapping which is a vector.

[darkliang]

You can check out tensor.size() by yourself.

[chuanfushen]

As you mentioned, you are interested in the shape of the final vectors, you could check the original implement form https://github.com/bb12346/GaitGL/blob/a169610383d58cfc3fa3f5cc7e293860e705e2c1/model/network/vgg_c3d.py#L196

OpenGait wraps the embedding into a python dictionary format, you can print out the tensor as darkliang said. https://github.com/ShiqiYu/OpenGait/blob/8edfc80326166d38e94300ffd143767882fa4025/opengait/modeling/models/baseline.py#L32-L33

[ssaikiran123]

OK I will do as suggested and update

[github-actions[bot]]

Stale issue message