Training on a custom dataset (Fine tuning) about squeezedet HOT 5 OPEN

Standard training already uses pre-trained SqueezeNet trained on Imagenet to start, you should be able to use your 1060 if you are patient enough... especially since the GPU is starved during training with the current code.

from squeezedet.

Download the one from classification, not the one from detection, the detection model is based on the classification squeeze net so it is a good way to initialise it.

You can use it on as many classes you want just change the classes on the right model config file

from squeezedet.

Thank you for the reply,

1. Where should I change to train the model for different number of classes?

2. How many classes do the pre-trained model support? I think for example if you have trained it for 2 classes, we can not use it for 3 and should have the same or lower number of classes, am I right?

3. in the readme you mentioned:

Download SqueezeDet model parameters from here, untar it, and put it under $SQDT_ROOT/data/ If you are using command line, type:

Should I use this to find-tune isn't it? Then why I should download the pre-trained classification model also?

Next, download the CNN model pretrained for ImageNet classification:

from squeezedet.

last question:

Have you tested the mAP on VOC also?

from squeezedet.

@andreapiso I have the same question: if I train the SqueezeDet model, i.e. the detector, can I - in a second moment - have its weights as an initial starting point to begin my training?
And if yes, how do I do it?

from squeezedet.