squeezeDet

squeezeDet copied to clipboard

Hello! Number of FLOPS for conv layer is calculated as `num_flops = (1+2*int(channels)*size*size)*filters*out_shape[1]*out_shape[2]` "1+" I assume is for bias, correct? What's the reason for 2x in the formula above: Do...

emezh

How about combining object detection and image classification in a single network?

1

In addition to do object detection using SqueezeDet, I tried adding another branch to do image classification, as follows, ######################################################### # One more fire module that is not trained before...

centosrhel

Interrupt and resume training from checkpoint

4

Is it possible to interrupt the training and resume it from a specific checkpoint? My train dir and checkpoint dir are the same, but when I restarted the training it...

andreapiso

Hello! First of all, thanks for the great work and ongoing support! Is it possible that the detection of objects with a large surface (say above 50% of the image...

milan0092

Hi @BichenWuUCB, If I want to do ROI Pooling, I just need the pred_box_delta right?.

pribadihcr

util is not used in this script.

villanuevab

make labels for custom dataset

1

does anyone know how to make labels for new dataset, thanks in advance.

faithfulnguyen

If I apply in voc datasets, what should I change the parameter of anchor

wm901115nwpu

PascalVOC implementation

4

Apart from config file and anchor size changes, what do I have to keep in mind if I want to implement this for PascalVOC? Please guide.

vhtrivedi

Do anyone who knows how to use my own datasets to train this network. If possible, could you give me some suggestions? Thank you very much.

YangBain