Skip to content
This repository was archived by the owner on Dec 17, 2022. It is now read-only.

Conversation

@DnPlas
Copy link

@DnPlas DnPlas commented Jan 7, 2020

Adding the Handwritten Digit Recognition based on DLRS, Pytorch and MNIST.
This series introduces the following changes:

  • Creates kubeflow/ in root directory with files for running the mentioned example on kubeflow pipelines
  • Creates handwritten_digit_recog/ in root directory with files for running the mentioned example on Docker containers

@DnPlas DnPlas requested a review from unrahul January 7, 2020 17:07
@DnPlas DnPlas force-pushed the mnist-example branch 3 times, most recently from a8fd2dd to 17d9abf Compare January 7, 2020 17:18
x = self.conv1(x)
x = F.relu(x)
x = self.conv2(x)
x = F.max_pool2d(x, 2)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is there are reason why no activation fn is given here?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey @DnPlas does this network perform well, without a non linear activation here?

Copy link
Contributor

@unrahul unrahul left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

some comments, please see.

help="number of epochs to train (default: 10)",
)
parser.add_argument(
"--lr", type=float, default=1.0, metavar="LR", help="learning rate (default: 0.01)"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: change default=0.01 :)

parser.add_argument(
"--test-batch-size",
type=int,
default=1000,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

may be make it same as the training batch, 64 ?

Copy link
Contributor

@unrahul unrahul left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

minor nits, otherwise looks okay to me, thank you @DnPlas

Daniela Plascencia added 3 commits January 15, 2020 13:29
* Python scripts for training, classifying and model serving
* Docker images for all tasks mentioned above

Signed-off-by: Daniela Plascencia <daniela.plascencia@linux.intel.com>
Signed-off-by: Daniela Plascencia <daniela.plascencia@linux.intel.com>
Signed-off-by: Daniela Plascencia <daniela.plascencia@linux.intel.com>
Copy link
Contributor

@unrahul unrahul left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @DnPlas merging .

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants