can pocketflow be used for object detection model about pocketflow HOT 16 CLOSED

Excuse me, what is the fundamental difference between object detection models and image classification models such that the current PocketFlow cannot support object detection models?

from pocketflow.

PocketFlow does not support object detection models (YOLO / Faster R-CNN) for the moment. We are working on this right now. #35

from pocketflow.

Enhancement required: add support for object detection models.

from pocketflow.

@jiaxiangxu
Some object detection models, e.g. Faster R-CNN and R-FCN, require multiple training stages (RPN -> detection model -> RPN with shared conv. layers -> detection model with shared conv. layers). This is not yet supported in PocketFlow.

from pocketflow.

thank you, then why present PocketFlow cannot support SSD and YOLO?

from pocketflow.

@jiaxiangxu
We have not tested on SSD on YOLO yet, so we are not sure whether PocketFlow can be directly used for these two models.

from pocketflow.

SSD models have been supported in the latest master branch.

from pocketflow.

sorry, I don't find the document about pruning on SSD. Can you tell me?

from pocketflow.

@as754770178 Documentation on SSD models is not yet ready. We will publish the corresponding documentation once the channel pruning component can work as expected on SSD models.

from pocketflow.

The compression on SSD is only quantization? Is there document about quantization on SSD？

from pocketflow.

Current code only supports uniform quantization, but we will release the support for channel pruning shortly. The document for uniform quantization and channel pruning will be released together.

from pocketflow.

When you release the document, I hope you can inform me.

from pocketflow.

@as754770178 No problem.

from pocketflow.

@jiaxiang-wu Can you tell me when the document for object detection network compression will be released.

from pocketflow.

@jiaxiang-wu I am curious if channel pruning has been released. I would like to try it for Mobilenet SSD architecture

from pocketflow.

I'm curious to know if channel pruning can be done on SSD model on COCO dataset using Pocketflow. Has anyone tried it and were successful?

from pocketflow.