Added and updated README files for vision models #218 #305

aditkumar72 · 2021-06-13T19:10:12Z

I have added README files for cdcgan_mnist, conv_mnist, dcgan_mnist, mlp_mnist, vgg_cifar10 and updated README file of vae_mnist. I have also added abspath code in the training files of cdcgan_mnist, conv_mnist, dcgan_mnist, mlp_mnist, vgg_cifar10 .

vision/cdcgan_mnist/cGAN_mnist.jl

vision/vae_mnist/README.md

vision/dcgan_mnist/README.md

CarloLucibello · 2021-06-16T06:00:07Z

thanks, this is nice work! just added some minor comments

Co-authored-by: Carlo Lucibello <[email protected]>

aditkumar72 · 2021-06-16T09:15:58Z

I have made all the changes can you please review @CarloLucibello .

ToucheSir

Thanks @aditkumar72! I've done a first pass and left some comments. The main points here are a) determining where the images come from and (assuming we have permission to use them) providing attribution as required, and b) re-formatting the references to be more detailed and structured.

ToucheSir · 2021-06-16T16:37:34Z

vision/conv_mnist/README.md

@@ -0,0 +1,24 @@
+# LeNet-5
+
+![LeNet-5](../conv_mnist/docs/LeNet-5.png)


Where does this image come from? Does it require attribution?

vision/conv_mnist/README.md

ToucheSir · 2021-06-16T16:39:40Z

vision/dcgan_mnist/README.md

+[Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks by Soumith Chintala et al.](https://arxiv.org/pdf/1511.06434v2.pdf)
+
+[pytorch.org/tutorials/beginner/dcgan_faces_tutorial](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html)


Ditto comment about reference format.

vision/dcgan_mnist/README.md

ToucheSir · 2021-06-16T16:43:35Z

vision/mlp_mnist/README.md

@@ -0,0 +1,18 @@
+# Multilayer Perceptron (MLP)
+
+![mlp](../mlp_mnist/docs/mlp.svg)


Similar comments about image sourcing and reference formats for this file.

vision/vae_mnist/README.md

vision/vgg_cifar10/README.md

aditkumar72 · 2021-06-16T17:22:33Z

All the model images except of dcgan are taken from references mentioned in their respective READMEs. The dcgan image is taken from google image. I will add its source in its README file.

aditkumar72 · 2021-06-16T17:39:41Z

Thanks @ToucheSir and @CarloLucibello for reviewing. I will soon come up with the proposed changes.

aditkumar72 · 2021-06-18T20:22:50Z

@ToucheSir I have made all the changes can you please review.

ToucheSir

Pinging @CarloLucibello to have a final look, but I think this is almost ready to go.

vision/cdcgan_mnist/README.md

ToucheSir · 2021-06-18T21:06:00Z

vision/conv_mnist/README.md

+
+* [Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, doi: 10.1109/5.726791.](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf)
+
+* [@book


This doesn't seem to render correctly for me. Can you confirm it's Github compatible?

Looking at the preview it seems like rendering properly. Should I need to change anything?

Maybe that's your local markdown editor, because GitHub renders the raw bibtex. I'd recommend just using the plaintext citation like you have for the reference above.

vision/vae_mnist/README.md

ToucheSir · 2021-06-18T21:09:05Z

vision/dcgan_mnist/README.md

+
+## Model Info
+
+A DC-GAN is a direct extension of the GAN, except that it explicitly uses convolutional and transposed convolutions layers in the discriminator and generator, respectively. _The discriminator is made up of strided convolution layers, batch norm layers, and LeakyReLU activations. The generator is comprised of transposed convolutions layers, batch norm layers, and ReLU activations_.


I think "transposed convolutional" would read better than "transposed convolutions", especially next to "convolutional".

What is the intent of italicizing the text at the end?

The intent of italicizing is to highlight the layers info. Should I remove it?

Co-authored-by: Brian Chen <[email protected]>

aditkumar72 · 2021-06-21T18:25:05Z

@ToucheSir I have made all the changes can you please review.

ToucheSir

Apologies for not getting back to you on this @aditkumar72! Just some very minor changes around reference formats and I think it's good to go. I'd make them myself, but I'm not sure what citation format you used so it'd be great if you could do it :)

ToucheSir · 2021-09-17T16:03:30Z

vision/dcgan_mnist/README.md

+
+## Results
+
+2000 training step


"steps" should be plural here as well.

ToucheSir · 2021-09-17T16:04:50Z

vision/conv_mnist/README.md

+
+* [Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, doi: 10.1109/5.726791.](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf)
+
+* [@book


Maybe that's your local markdown editor, because GitHub renders the raw bibtex. I'd recommend just using the plaintext citation like you have for the reference above.

ToucheSir · 2021-09-17T16:05:18Z

vision/mlp_mnist/README.md

+
+## Reference
+
+* [@book


Same comment as above about this just rendering as bibtex.

ToucheSir · 2021-09-17T16:05:55Z

vision/vgg_cifar10/README.md

+* [Simonyan, K. and Zisserman, A., “Very Deep Convolutional Networks for Large-Scale Image Recognition”, <i>arXiv e-prints</i>, 2015.
+](https://arxiv.org/pdf/1409.1556v4.pdf)
+
+* [@book


Ditto here RE the link text being raw bibtex.

aditkumar72 · 2021-09-27T17:20:19Z

@ToucheSir I have made all the needed changes can you please review.

ToucheSir

Wonderful, thanks for your patience through this!

aditkumar72 added 15 commits June 12, 2021 23:20

Added abspath for terminal support

e02cfe4

Added README files and abspath support to code

936871c

Added README files

bd62093

Updated README.md for cdcgan_mnist

3215e2b

Added image for readme

ce19dca

created docs file for readme imgs

dbba92c

Updated Readme.md for conv_mnist

83edc50

Updated dcgan_mnist readme

0bfef8d

Added mlp img in docs folder

ce52bba

Updated README.md for mlp_mnist

b67e5d2

Added vgg img in docs folder

35996b7

Updated README.md for vgg_cifar10

bc29baa

Addes vae img in docs folder

04c0d83

Updated README.md for vae_mnist

0116bc9

Updated vae_mnist README

cd686c4

aditkumar72 mentioned this pull request Jun 16, 2021

Refresh Model Zoo FluxML/FluxML-Community-Call-Minutes#9

Open

19 tasks

CarloLucibello requested changes Jun 16, 2021

View reviewed changes

aditkumar72 and others added 12 commits June 16, 2021 12:00

Update vision/cdcgan_mnist/cGAN_mnist.jl

7f8a3da

Co-authored-by: Carlo Lucibello <[email protected]>

Update vision/vae_mnist/README.md

8a5b7e6

Co-authored-by: Carlo Lucibello <[email protected]>

Update cdcgan_mnist README

3466de1

Update conv_mnist README

20e5bb9

Update dcgan_mnist README

0b3ecdb

Update mlp_mnist README

f9a42fe

Update vgg_cifar10 README

4790b63

Removed cd from cGAN_mnist.jl

69c3897

Added newline in cGAN_mnist

f1c9c02

Added newline to conv_mnist

48fc214

Added dcgan_generator_discriminator.png for readme

83571b6

Updated dcgan_mnist README

9cc9250

Updated model info of VAE

3289e2f

ToucheSir requested changes Jun 16, 2021

View reviewed changes

aditkumar72 added 10 commits June 19, 2021 00:11

Updated vae_mnist README

170fefe

Updated vae_mnist README

64c8ac5

Updated cdcgan_mnist README

7064bbf

Updated conv_mnist README

8f0d12d

Updated dcgan_mnist README

5de75fa

Updated mlp_mnist README

87e70f1

Updated mlp_mnist README

944a8d3

Updated mlp_mnist README

7d1b846

Updated conv_mnist README

823b274

Updated vgg_cifar10 README

8021b8f

ToucheSir reviewed Jun 18, 2021

View reviewed changes

aditkumar72 and others added 4 commits June 21, 2021 22:31

Update vision/vae_mnist/README.md

b35c585

Co-authored-by: Brian Chen <[email protected]>

corrected path in cdcgan_mnist

b7bb761

updated dcgan_mnist readme

7930c10

updated dcgan_mnist README

390692f

ToucheSir requested changes Sep 17, 2021

View reviewed changes

aditkumar72 and others added 2 commits September 27, 2021 22:45

made needed changes

ebcd810

made needed changes

d7ad415

ToucheSir approved these changes Sep 28, 2021

View reviewed changes

ToucheSir merged commit 2bd86ff into FluxML:master Sep 28, 2021

ToucheSir mentioned this pull request Sep 28, 2021

Many models are missing README files #218

Open

aditkumar72 deleted the readmes branch September 29, 2021 05:53

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Added and updated README files for vision models #218 #305

Added and updated README files for vision models #218 #305

aditkumar72 commented Jun 13, 2021

CarloLucibello commented Jun 16, 2021

aditkumar72 commented Jun 16, 2021 •

edited

Loading

ToucheSir left a comment

ToucheSir Jun 16, 2021

ToucheSir Jun 16, 2021

ToucheSir Jun 16, 2021

aditkumar72 commented Jun 16, 2021

aditkumar72 commented Jun 16, 2021 •

edited

Loading

aditkumar72 commented Jun 18, 2021

ToucheSir left a comment

ToucheSir Jun 18, 2021

aditkumar72 Jun 20, 2021

ToucheSir Sep 17, 2021

ToucheSir Jun 18, 2021

aditkumar72 Jun 20, 2021

aditkumar72 commented Jun 21, 2021

ToucheSir left a comment •

edited

Loading

ToucheSir Sep 17, 2021

ToucheSir Sep 17, 2021

ToucheSir Sep 17, 2021

ToucheSir Sep 17, 2021

aditkumar72 commented Sep 27, 2021

ToucheSir left a comment

		@@ -0,0 +1,24 @@
		# LeNet-5

		![LeNet-5](../conv_mnist/docs/LeNet-5.png)

		[Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks by Soumith Chintala et al.](https://arxiv.org/pdf/1511.06434v2.pdf)

		[pytorch.org/tutorials/beginner/dcgan_faces_tutorial](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html)

		@@ -0,0 +1,18 @@
		# Multilayer Perceptron (MLP)

		![mlp](../mlp_mnist/docs/mlp.svg)


		* [Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, doi: 10.1109/5.726791.](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf)

		* [@book


		## Model Info

		A DC-GAN is a direct extension of the GAN, except that it explicitly uses convolutional and transposed convolutions layers in the discriminator and generator, respectively. _The discriminator is made up of strided convolution layers, batch norm layers, and LeakyReLU activations. The generator is comprised of transposed convolutions layers, batch norm layers, and ReLU activations_.

Added and updated README files for vision models #218 #305

Added and updated README files for vision models #218 #305

Conversation

aditkumar72 commented Jun 13, 2021

CarloLucibello commented Jun 16, 2021

aditkumar72 commented Jun 16, 2021 • edited Loading

ToucheSir left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

aditkumar72 commented Jun 16, 2021

aditkumar72 commented Jun 16, 2021 • edited Loading

aditkumar72 commented Jun 18, 2021

ToucheSir left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

aditkumar72 commented Jun 21, 2021

ToucheSir left a comment • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

aditkumar72 commented Sep 27, 2021

ToucheSir left a comment

Choose a reason for hiding this comment

aditkumar72 commented Jun 16, 2021 •

edited

Loading

aditkumar72 commented Jun 16, 2021 •

edited

Loading

ToucheSir left a comment •

edited

Loading