Aman Goyal

TypeError : Resnet : __init__() got an unexpected keyword argument 'init_cfg'

12

Greetings, I am currently using qdtrack in python 3.8, Cuda 11 based environment for RTX 3090 GPU. While training as well as testing, I am getting this error. All required...

I have been getting this warning. I had copied the pretrained code snippet from backbone and added it to neck and head modules. When I am training the model, I...

Greetings, Is it possible to initialize neck and heads with pre-trained weights just like how it is possible for backbone ? If not, then how can I modify the config/scripts...

I had put the model on training for BDD100K dataset. I wanted to know what is the accuracy metric which appears after every epoch when model is trained on BDD100K?...

Backbone pre-trained on BDD100K dataset

2

Greetings, How can I access the backbone pre-trained weights on BDD100K dataset ? Thanks

Possibility of using pre-trained weights for neck and head and only customizing backbone ?

1

Greetings, So I wanted to know the possibility of using pre-trained weights for only neck and head components of qdtrack? I would like to use my own backbone network but...

Use pretrained TCN model in nncf

2

Use pretrained TCN model in nncf to create compression version of it

Greetings, Is it possible to use your codebase on BDD100K dataset ? I want to use teacher as Resnet-50 and my own architecture for Student. Thanks