MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.
I am using transfer learning with Re-training SSD-Mobilenet like here.
My dataset contains 8000+ images (annotated sport players) (I have grayscale camera so all images are in grayscale (edit: turned into RGB by copying channel)).
I see that until 100 epochs loss is going down but then it is spiking and after exactly 200 epochs reaches new minimum.
1) I am wondering what does it mean (overfitting? or maybe that's just normal optimization)?
2) After each spike there is new minimum (100 - 1.47, 300 - 1.41, 500 - 1.39, 700 - 1.38) - Which one should I use? The lowest (at 700)? or at 100 (because later it may actually be not improving or even breaking)?
Hi,
I am using transfer learning with Re-training SSD-Mobilenet like here. My dataset contains 8000+ images (annotated sport players) (I have grayscale camera so all images are in grayscale (edit: turned into RGB by copying channel)).
EDIT - learning size:
I used this script to generate test data with:
I see that until 100 epochs loss is going down but then it is spiking and after exactly 200 epochs reaches new minimum. 1) I am wondering what does it mean (overfitting? or maybe that's just normal optimization)? 2) After each spike there is new minimum (100 - 1.47, 300 - 1.41, 500 - 1.39, 700 - 1.38) - Which one should I use? The lowest (at 700)? or at 100 (because later it may actually be not improving or even breaking)?
I would be glad for some help! Regards