Create RetinaNet object detection guide #2069
Conversation
sachinprasadhs
requested review from
fchollet,
MarkDaoust and
pcoet
as code owners
sachinprasadhs
requested review from
mattdangerw and
divyashreepathihalli
and removed request for
MarkDaoust and
pcoet
There was a problem hiding this comment.
Thanks for the PR @sachinprasadhs - since this is a guide - we should have more detailed explanations that would help users understand our framework better. Lets add more of that.
Thanks!
| object_detector.summary() | ||
|
|
||
| """ | ||
| ## Preprocessing Layers |
There was a problem hiding this comment.
add a single line or a few lines of description of what this section will be about
|
|
||
| """ | ||
| ### Predict and Visualize | ||
| Next, let's get some predictions from our object detector: |
There was a problem hiding this comment.
add a bit more of description on what you will be doing here
| backbones here https://keras.io/keras_hub/presets/ | ||
| """ | ||
|
|
||
| object_detector = keras_hub.models.ImageObjectDetector.from_preset( |
There was a problem hiding this comment.
provide just the preset name here - `keras_hub.models.ImageObjectDetector.from_preset('retinanet_resnet50_fpn_coco')
| ) | ||
|
|
||
| """ | ||
| ### Prediction on evaluation data |
There was a problem hiding this comment.
In general for all the heading please add more description.
| rows=2, | ||
| cols=2, | ||
| class_mapping=INDEX_TO_CLASS, | ||
| ) |
There was a problem hiding this comment.
write conclusion, point to further resource links to explore etc
No description provided.