ResNet - Live Coding in PyTorch - Wed Sep 15, 9pm IST

In this session, we will live code ResNets from scratch using PyTorch.

Live stream: Live Coding Session on ResNet - YouTube

14 Likes

Hello Aman! Eagerly waiting for the session

2 Likes

Could we please make sure to carry on our conversation here?

6 Likes

can you bump up your font size a touch…

2 Likes

good morning :slight_smile: increase font please

1 Like

Is it fine now? I am at 125%

thanks. it is good now.

1 Like

Thank you for taking this session
Really needed it

thanks for this…i needed this session for resnet.

yes. 3am … I am dedicated.

5 Likes

Will you also take up coding from scratch and setting up the ecc2 instance
jeremy did discuss it but very briefly

1 Like

It would be really helpful if you could help us in setting up ec2 instance in a session.

2 Likes

I have tried to keep up with the PyTorch group, but the coding part takes time
How should one use the notebooks?
Should one try to replicate them?

1 Like

(with respect to pytorch and fast.ai)

sharing the repo referred to in the beginning

how to know when to have the fully connected layer, pooling layer and convolution layer?

3 Likes

Shouldn’t downsample be a conv2d instance?

Do we not need to add Padding to the Conv2d operations?
Also do we want to set self.downsample = 1 (Identify) if inchannels and out_channels are same?

I think you need need super.init() ??

Doesn’t conv1d introduce new parameters while resnet is supposed to be f(x) + x ? sorry for a stupid question

why is it needed ? never got this