1adrianb / 1adrianb/face-alignment-training

How can I get the whole Network structure of FAN ?

Ouverte
#22 1 commentaire 0 réactions 0 personnes assignées Voir sur GitHub
Langage dominant
Lua
Étoiles
152
Forks
44
Métriques de merge des PR
Aucune PR mergée en 30 j

Description

I have tried your python code of FAN which actually has a very good result. But I have a visualize problem. Sorry that i am unfamiliar with lua and torch. I have tried python-graphviz in your project in FAN in python but I failed with getting "NoneType" pdf which contained nothing.
Could you give a whole visualized network structure with some specific values like netscope of Caffe or Tensorboard of tensorflow?
I mean the network of 2D face feature structure is OK, all structure is best!

Guide de contribution

Aucun guide de contribution indexé pour ce dépôt

Piste de recherche

The issue asks for a visualized network structure of the FAN model, similar to Netscope or TensorBoard. The repository uses Lua and Torch. Start by examining the model definition files in the project to understand the architecture. Then research how to export or visualize Torch models in Python, possibly using tools like torchviz or ONNX. The goal is to produce a complete, labeled diagram of the 2D face alignment network.

Rédigé par le modèle d'indexation à partir du texte de l'issue.

Évaluation

Stack technique
lua, python
Domaine
computer-vision, data-visualization, machine-learning
Type d'issue
Fonctionnalité
Difficulté
4/5
Temps estimé
3-5 jours
Activité
À l'abandon
Clarté
Plutôt claire
Accessibilité débutants
30/100

Recevez les nouvelles issues par e-mail

Un résumé court des issues GitHub adaptées aux débutants.