PeleeNet
PeleeNet copied to clipboard
A tensorflow implement for PeleeNet:A Real-Time Object Detection System on Mobile Devices
how train my own data
Shouldn't the 'is_training' parameter be passed to batch_norm normalizer via 'normalizer_params' of conv2d? The same applies to the other functions in this file. https://github.com/nnUyi/PeleeNet/blob/60d179101adebd0c5ec9853c2aa09694b3a51b79/layers.py#L19
hi, thank you for your code. when I use these codes, I met some problems: 1. when I test one image , although I expend_dims the image, I can not...
Like you say you only focused on the classification part, is there any plan to build object detection in it and publish the model?
Hi, are there any plans to publish pre-trained models?