raghakot/keras-vis

Activation maximization with InceptionV3

Open

#143 opened on Oct 12, 2018

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (640 forks)github user discovery
help wanted

Repository metrics

Stars
 (2,992 stars)
PR merge metrics
 (PR metrics pending)

Description

From master, I modified the activation_maximization.ipynb notebook to replace VGG16 with InceptionV3. Basically, I only changed the model instantiation to:

from keras.applications.inception_v3 import InceptionV3
model = InceptionV3(include_top=True, weights='imagenet', input_shape=(299, 299, 3))

However, I can't get meaningful images. For example, for the "ouzel" example, I get something very similar to: https://files.slack.com/files-pri/T3JPM5YNB-F7AFPBRGD/image.png (this was reported by a Slack user in September 2017).

Contributor guide

Research direction
Verify that the InceptionV3 model's input shape (299x299) is correctly matched, ensure the preprocessing function (e.g., preprocess input) is applied, and check if the activation maximization algorithm requires adjustments for different layer names or filter indices compared to VGG16.
Tech stack
python
Domain
ai
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonKeras/TensorFlow
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60