Adds adversarial example generation script #11

ellenjiang7 · 2019-08-02T16:30:03Z

Adds the adversarial example generating script (in adversarial_depth.py)
which takes in a DepthModelWrapper instance (in depth_model_wrapper.py),
which has methods to load and call predict on a depth model, and moves
adversarial code into a separate directory.

This change is

Adds the adversarial example generating script (in adversarial_depth.py) which takes in a DepthModelWrapper instance (in depth_model_wrapper.py), which has methods to load and call predict on a depth model, and moves adversarial code into a separate directory.

ellenjiang7

Sorry for the large number of files - most are due to my moving the existing starter project code into a separate directory from this adversarial script I'm adding now. The main code that has been added is all in adversarial_depth.py and depth_model_wrapper.py.

Reviewable status: 0 of 37 files reviewed, all discussions resolved (waiting on @annxingyuan and @EmilyReif)

EmilyReif

Reviewed 1 of 37 files at r1.
Reviewable status: 1 of 37 files reviewed, 5 unresolved discussions (waiting on @annxingyuan, @ellenjiang7, and @EmilyReif)

adversarial/adversarial_depth.py, line 26 at r1 (raw file):

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '5'

Add note for what this means

adversarial/adversarial_depth.py, line 30 at r1 (raw file):

# Image Paths
SINK_IMAGE = "/usr/local/google/home/ellenj/Documents/BigPicture/DenseDepth/examples/1_image.png"

Nit: can you make these local paths? Just to avoid info leaking out in the world (your name, "BigPicture", and "DenseDepth")

adversarial/adversarial_depth.py, line 126 at r1 (raw file):

  for i in range(iterations):
      loss, gradients = retrieve_loss_and_gradients(input_image)
      print('Loss at', i, ':', loss)

FYI: can change to python string formatting if you want:
'Loss at %d : %.2f' % (i, loss)

adversarial/adversarial_depth.py, line 156 at r1 (raw file):

  gradients /= K.maximum(K.mean(K.abs(gradients)), K.epsilon())  # normalize

  global get_loss_and_gradients

In general, avoid python globals: http://go/pystyle#global-variables

Can you pass get_loss_and_gradients into gradient_ascent?

adversarial/depth_model_wrapper.py, line 16 at r1 (raw file):

# ==============================================================================

"""Abstract Wrapper class for the depth model for generating adversarial examples."""

Nice, looks great. Want to add a simple usage example here? (something like what was in the main() function of the depth model that implements this interface)

(lemme know if this doesn't make sense and we can sync in person)

depth_visualizer/static/illusions.77de5100.css, line 1 at r1 (raw file):

/* Copyright 2019 Google LLC

Hm, this looks like a generated file. Can we add static/*.css to the gitignore?

actually, this looks like it happened a few times below too-- there are some generated .js, .map, and image files
https://stackoverflow.com/questions/5241644/using-gitignore-to-ignore-everything-but-specific-directories might be helpful-- not sure what is the most elegant way to deal with the static folder in gitignore

Removes line that suppresses logging, changes image paths to local paths in adversarial_depth.py, changes loss printing to Python string formatting, removes global variable, and adds usage example to depth_model_wrapper.py.

Fixes gitignore paths that have been moved to the depthvisualizer directory.

ellenjiang7

Reviewable status: 0 of 31 files reviewed, 5 unresolved discussions (waiting on @annxingyuan and @EmilyReif)

adversarial/adversarial_depth.py, line 26 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

Add note for what this means

Hmm it suppresses logging, though now that I think about it - perhaps it might be better to remove this and allow the default logging, in case it's helpful for someone troubleshooting when they use the script?

adversarial/adversarial_depth.py, line 30 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

Nit: can you make these local paths? Just to avoid info leaking out in the world (your name, "BigPicture", and "DenseDepth")

Oh yeah, good point. Done.

adversarial/adversarial_depth.py, line 126 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

FYI: can change to python string formatting if you want:
'Loss at %d : %.2f' % (i, loss)

Done.

adversarial/adversarial_depth.py, line 156 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

In general, avoid python globals: http://go/pystyle#global-variables

Can you pass get_loss_and_gradients into gradient_ascent?

Whoops yeah, sounds good. Done.

adversarial/depth_model_wrapper.py, line 16 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

Nice, looks great. Want to add a simple usage example here? (something like what was in the main() function of the depth model that implements this interface)

(lemme know if this doesn't make sense and we can sync in person)

Yeah, sounds great! Does this work?

depth_visualizer/static/illusions.77de5100.css, line 1 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

Hm, this looks like a generated file. Can we add static/*.css to the gitignore?

actually, this looks like it happened a few times below too-- there are some generated .js, .map, and image files
https://stackoverflow.com/questions/5241644/using-gitignore-to-ignore-everything-but-specific-directories might be helpful-- not sure what is the most elegant way to deal with the static folder in gitignore

Oh I just realized I forgot to change the paths of the static folder items in gitignore when I moved the starter project into a subdirectory. Fixed now.

annxingyuan

Ellen this is awesome! Sorry I didn't have more comments - everything looks good to me though :) Would love to get a demo of everything if you get a chance at some point!

annxingyuan · 2019-08-06T21:09:21Z

adversarial/adversarial_depth.py

+BATHTUB_IMAGE = "images/bathtub.png"
+
+
+def get_sink_to_bathtub_inputs(depth_model_wrapper, model):


Maybe add a brief description of the sink to bathtub experiment?

annxingyuan · 2019-08-06T21:47:36Z

adversarial/adversarial_depth.py

+  return input_image
+
+
+def generate_adversarial_example(depth_model_wrapper, iterations = 100,


Maybe make input_image and goal_output configurable?

ellenjiang7

Sweet thanks!

Reviewable status: 0 of 28 files reviewed, 6 unresolved discussions (waiting on @annxingyuan and @EmilyReif)

adversarial/adversarial_depth.py, line 31 at r2 (raw file):

Previously, annxingyuan (Ann Yuan) wrote…

Maybe add a brief description of the sink to bathtub experiment?

Done.

adversarial/adversarial_depth.py, line 128 at r2 (raw file):

Previously, annxingyuan (Ann Yuan) wrote…

Maybe make input_image and goal_output configurable?

Ah yea good idea! Done.

EmilyReif · 2019-08-08T19:09:57Z

adversarial/adversarial_depth.py, line 26 at r1 (raw file):

Previously, ellenjiang7 wrote…

Hmm it suppresses logging, though now that I think about it - perhaps it might be better to remove this and allow the default logging, in case it's helpful for someone troubleshooting when they use the script?

sure, sgtm

EmilyReif · 2019-08-08T19:11:08Z

adversarial/depth_model_wrapper.py, line 16 at r1 (raw file):

Previously, ellenjiang7 wrote…

Yeah, sounds great! Does this work?

Looks perfect!

EmilyReif · 2019-08-08T19:14:35Z

depth_visualizer/static/escher-trippy.5b69c0dc.jpg, line 0 at r3 (raw file):
wait, I think this is a generated file? Or maybe reviewable is just showing me this cause it was in the PR at one point... (just check to make sure that in your current branch, there's no more generated files)

EmilyReif

Reviewed 23 of 37 files at r1, 12 of 16 files at r2, 1 of 1 files at r3.
Reviewable status: all files reviewed, 5 unresolved discussions (waiting on @annxingyuan, @ellenjiang7, and @EmilyReif)

EmilyReif · 2019-08-08T19:16:23Z

Looks good to me!

EmilyReif · 2019-08-08T19:16:29Z

EmilyReif · 2019-08-08T19:16:39Z

depth_visualizer/static/illusions.77de5100.css, line 1 at r1 (raw file):

Previously, ellenjiang7 wrote…

Oh I just realized I forgot to change the paths of the static folder items in gitignore when I moved the starter project into a subdirectory. Fixed now.

gotcha, sounds good!

ellenjiang7

Reviewable status: 22 of 25 files reviewed, 5 unresolved discussions (waiting on @annxingyuan and @EmilyReif)

adversarial/adversarial_depth.py, line 26 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

sure, sgtm

Done.

depth_visualizer/static/escher-trippy.5b69c0dc.jpg, line at r3 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

wait, I think this is a generated file? Or maybe reviewable is just showing me this cause it was in the PR at one point... (just check to make sure that in your current branch, there's no more generated files)

Done.

depth_visualizer/static/illusions.77de5100.css, line 1 at r1 (raw file):

Previously, EmilyReif (Emily Reif) wrote…

gotcha, sounds good!

Done.

ellenjiang7 requested review from annxingyuan and EmilyReif August 2, 2019 16:30

ellenjiang7 commented Aug 2, 2019

View reviewed changes

EmilyReif requested changes Aug 4, 2019

View reviewed changes

ellenjiang7 added 4 commits August 6, 2019 10:30

Addresses comments and removes static files

15eebb4

Removes line that suppresses logging, changes image paths to local paths in adversarial_depth.py, changes loss printing to Python string formatting, removes global variable, and adds usage example to depth_model_wrapper.py.

Removes more static files and fixes gitignore.

550db5a

Fixes gitignore paths that have been moved to the depthvisualizer directory.

Removes static/images.

35e6a12

Readded Escher images.

33bb7d8

ellenjiang7 commented Aug 6, 2019

View reviewed changes

annxingyuan approved these changes Aug 6, 2019

View reviewed changes

Made experiment input and target images configurable.

5e7e15d

ellenjiang7 commented Aug 8, 2019

View reviewed changes

EmilyReif approved these changes Aug 8, 2019

View reviewed changes

Deletes more static files

cda8980

ellenjiang7 commented Aug 8, 2019

View reviewed changes

ellenjiang7 merged commit ff8ebca into master Aug 8, 2019

ellenjiang7 deleted the adversarial branch August 8, 2019 19:27

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Adds adversarial example generation script #11

Adds adversarial example generation script #11

ellenjiang7 commented Aug 2, 2019 •

edited by EmilyReif

ellenjiang7 left a comment

EmilyReif left a comment

ellenjiang7 left a comment

annxingyuan left a comment

annxingyuan Aug 6, 2019

annxingyuan Aug 6, 2019

ellenjiang7 left a comment

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

EmilyReif left a comment

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

ellenjiang7 left a comment

		BATHTUB_IMAGE = "images/bathtub.png"


		def get_sink_to_bathtub_inputs(depth_model_wrapper, model):

		return input_image


		def generate_adversarial_example(depth_model_wrapper, iterations = 100,

Adds adversarial example generation script #11

Adds adversarial example generation script #11

Conversation

ellenjiang7 commented Aug 2, 2019 • edited by EmilyReif

ellenjiang7 left a comment

Choose a reason for hiding this comment

EmilyReif left a comment

Choose a reason for hiding this comment

ellenjiang7 left a comment

Choose a reason for hiding this comment

annxingyuan left a comment

Choose a reason for hiding this comment

annxingyuan Aug 6, 2019

Choose a reason for hiding this comment

annxingyuan Aug 6, 2019

Choose a reason for hiding this comment

ellenjiang7 left a comment

Choose a reason for hiding this comment

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

EmilyReif left a comment

Choose a reason for hiding this comment

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

EmilyReif commented Aug 8, 2019

ellenjiang7 left a comment

Choose a reason for hiding this comment

ellenjiang7 commented Aug 2, 2019 •

edited by EmilyReif