Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[modeling] Add SSD model on dev branch #31

Open
hngskj opened this issue Oct 12, 2019 · 4 comments
Open

[modeling] Add SSD model on dev branch #31

hngskj opened this issue Oct 12, 2019 · 4 comments
Assignees
Labels

Comments

@hngskj
Copy link
Collaborator

hngskj commented Oct 12, 2019

Add SSD model on dev branch

Github repo: ssd_keras by @pierluigiferrari

@hngskj hngskj self-assigned this Oct 14, 2019
@hngskj
Copy link
Collaborator Author

hngskj commented Oct 16, 2019

WIP : Converting a model

Goal

(boxes, scores, labels) = model.predict_detection('sample.jpg')

Working on

Tasks

  • model = ssd_300() is for training
  • When model.predict_detection() is called, the DecodeDetections layer will be added at the end of the model.

@hngskj
Copy link
Collaborator Author

hngskj commented Oct 16, 2019

To run the test file, the pretrained model weights are needed. Download files from here, and put them in KerasObjectDetector/keras_ssd/pretraind/ folder.

@parkjh688 parkjh688 self-assigned this Oct 18, 2019
@parkjh688
Copy link
Collaborator

Starting to add SSD model with @hngskj

@parkjh688
Copy link
Collaborator

Use the weights below.
PASCAL VOC models: 07+12: SSD300*, SSD512*

hngskj pushed a commit to hngskj/KerasObjectDetector that referenced this issue Oct 20, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants