How to do incremental learning on MobileNet-SSD caffe

Question

I'm training my classifier on 20k images but every week I get more new pictures so I want to incrementally train my previous model(last stopped iteration) instead of retraining 20k+new_images on all the images again which is a waste of time and compute

I figured out incremental training with Yolo but can't seem to find anything for MobileNet-SSD caffe implemented here https://github.com/chuanqi305/MobileNet-SSD

To understand more about what I'm talking about refer to this: How to do incremental training on the basis of yolov3.weights & answer to this mention here:

 darknet.exe partial cfg/yolov3.cfg yolov3.weights yolov3.conv.105 105

score 0 · Accepted Answer · answered Sep 03 '19 at 06:12

You need to pass previous iteration in train.sh instead of 73000 iteration. The new iteration are found in snapshot folder once you are done training

if ! test -f example/MobileNetSSD_train.prototxt ;then
echo "error: example/MobileNetSSD_train.prototxt does not exist."
echo "please use the gen_model.sh to generate your own model."
exit 1
fi
mkdir -p snapshot

#Initiate a new training
$CAFFE_ROOT/build/tools/caffe train -solver="solver_train.prototxt" \
-weights="mobilenet_iter_73000.caffemodel" \
-gpu 0

Quick question. When I do incremental learning in caffe like that, what dataset do I use? (in this example the previous 20k + new data, or just the new data) — Yandi Banyu Karima Waly, Dec 30 '19 at 18:19

How to do incremental learning on MobileNet-SSD caffe

1 Answers1