Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
Multi-task Deep Learning Experiment using fastai Pytorch
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@Light--
Copy link

Light-- commented Jul 10, 2020

thanks for sharing....but, is that really a multi-task model? what's the architecture of the network really? Does it have a classical MTL structure which including a backbone and multi-head? or just only use resnet50.....sorry, could you explanin a little bit more...?

@icmpnorequest
Copy link

icmpnorequest commented Aug 10, 2020

thanks for sharing....but, is that really a multi-task model? what's the architecture of the network really? Does it have a classical MTL structure which including a backbone and multi-head? or just only use resnet50.....sorry, could you explanin a little bit more...?

It's a classical multi-task learning architecture, which uses hard parameters sharing method. For example, $loss_{total} = \lambda_{age} * loss_{age} + \lambda_{gender} * loss_{gender}$. Hope it may help you

@Light--
Copy link

Light-- commented Aug 11, 2020

$loss_{total} = \lambda_{age} * loss_{age} + \lambda_{gender} * loss_{gender}$

@icmpnorequest
as far as i know, only calculating the loss together doesn't make the model to have a multi-task structure, you are doing the multi-objective learning without a multi-task model structure, right?
if the model structure is really using the classical multi-task structure as you said, could you tell me which paper/webpage you refer to?
thanks.

@icmpnorequest
Copy link

icmpnorequest commented Aug 12, 2020

$loss_{total} = \lambda_{age} * loss_{age} + \lambda_{gender} * loss_{gender}$

@icmpnorequest
as far as i know, only calculating the loss together doesn't make the model to have a multi-task structure, you are doing the multi-objective learning without a multi-task model structure, right?
if the model structure is really using the classical multi-task structure as you said, could you tell me which paper/webpage you refer to?
thanks.

Maybe you could refer to the paper [19 CVPR] Multimodal Age and Gender Classification Using Ear and Profile Face Images

@Mohamed-Khalil67
Copy link

Mohamed-Khalil67 commented Jan 24, 2022

Hi , i have errors in imageCLassificationDataset ( function not defined) and ImageDatabunch ( flase argument for size , non existent ). Is there anyway to correct them ?

@apssouza22
Copy link

apssouza22 commented Feb 28, 2022

If anyone else is facing issues when running this example I have run through hell to build a multitask model. I hope I save some people time with this ready to run on Colab example https://github.com/apssouza22/cnn-for-devs/blob/master/i-multitask-model.ipynb

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment