uvipen/ssd-pytorch

SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity

WELCOME TO MY PAGE 👋👋👋

My name is Viet Nguyen. I am an M.Sc. in Computer Science, majoring in Artificial Intelligence and Robotics. I am interested in the following topics: Deep Learning in NLP and Computer Vision. Reinforcement Learning.

📫 How to reach me:

LinkedIn GitHub Youtube

ssd-pytorch's Issues

how to use my own dataset

I want to use this model to train on my own dataset. If I use my dataset instead of COCO dataset with the same directory format will it work?

training with a custom dataset

I have two questions, how can I use this code to train the SSD with my own custom dataset? and after finishing the training process, how can I use the model for inference tasks on real-time camera applications?
thank you for simplifying the SSD idea, I'm a beginner and I'm finding the existing implementations really complicated.

Default Bounding Box Priors

Hi,

Thanks for your implementation. This makes understanding the model much more easier.
I did notice one thing though. In the paper, the authors mention about defining default bounding boxes as priors and define different aspect ratios and scales for the same as well. Then during training they calculate the offset values between the priors with the overlap greater than a threshold w.r.t the ground truth bounding boxes and use that to calculate the localization loss.
Although, this implementation trains and works well, but I couldn't find the use of default bounding boxes anywhere.
Am I missing something here?

Thanks.

Thank you for the repo and some questions

First of all, thanks for the repo. Was trying to find something like this. It will help me a lot.
There are a few questions that I want to ask.

1. The trained model that you are providing, is trained for 50 epochs, right?
2. Also, any possibility to get trained weight for the SSDLite version anytime soon?

Thanks again.

Mobilenet_SSD weight

Hi, thank you for your work,
Can you provide the pretrained weight for Mobilenetv2_SSD ?

pytorch_version

Hello there,
Which pytorch version is used for this repository ?
I am using pytorch 1.0,
I am getting the error "No module named box_convert" from the ops/boxes.py .
Could you please provide the solution ? Thank you !

Best regards

how to generate coco evaluation

like the example you show

export the coco predictions in json file

Hello Viet, thanks for this repo!
I noticed that you used the coco eval API to evaluate the the trained model and the results are clear and impressive. I am wondering if the coco eval API also can be used in the test_dataset.py to evaluate the prediction results on coco dataset, such as coco eval2017 dataset? Any suggestion will be appreciated ! : )