Train on images without boxes

[andraugust]

Thanks for the great package!

Is it possible to train on images that don't have boxes in them?

I have several images without boxes that serve as background examples. I'd like the model to learn from these. I believe the dataloader is set up to only load images with boxes, is this true?

[qfgaohao]

Hi @andraugust , therectically, yes. The background images will only provide negative samples. You just need to make sure there is at least one image with bounding boxes (positie samples) in every batch during training.

[lyyiangang]

I succeed make the training support background images. you need modify hard_negative_mining to support it.

[Barath19]

How can we reduce the number of default boxes per feature map?
can it be done by having single aspect ratio and size per map?

[ZHuiLBo]

I succeed make the training support background images. you need modify hard_negative_mining to support it.

Could you be more specific？

[ChetanPatil28]

@Barath19 we can do that.
For that, u need to make changes in three files.

Following changes are with-respect-to SSD-Mobilenet-V2-Lite

1. ~\pytorchssd\vision\ssd\config\mobilenetv1_ssd_config.py
If you see inside this file,
there is a variable specs and it consists of four parameters,
there is a last parameter which is basically a List, and this parameter is aspect ratio.
Make this list with a single item of your desired aspect ratio.
For example, u want an asapect ratio of 0.49, do it this way,
SSDSpec(10, 32, SSDBoxSizes(105, 150), [ 0.490]).
Similarly u need to change the last paramter as a single-item list of your desired aspect ratio for the rest 5 as well.

2. ~\pytorch-ssd\vision\utils\box_utils.py

Inside the function generate_ssd_priors, the author generates 2 square boxes + 2-variable-sized boxes of a given aspect ratio.
In-order for your code to work, comment out the small box and bigger-box and one of the variable-sized box.
Now you are left with just one anchor box.

3. ~pytorch-ssd\vision\ssd\mobilenet_v2_ssd_lite.py

In this file, there are two lists called classification_headers and regression_headers,
inside these two, you see a lot of conv2d layers, and in the out_channels parameters, there is something like (64num_channels) for regression_headers and (61num_channels) for classification_headers.
Replace the "6" with "1".
Thats it.

[gracecocks]

Was there ever an answer to how to train on negative images?