Yurushia1998

Cannot get embedding

1

When I test on env with python 3.6 and torch 1.6, there is an error when I try to get embedding: Traceback (most recent call last): File "test.py", line 14,...

Supposed I want to get benchmark using GCNet but only object detection on my custom dataset, do I need to have mask for trainging or just bounding box is enough?

Change of config

2

Does the github code require us to change the config of models? In the other github with similar config for YoloV4, they said we need to change something, like number...

In file generate_nosi_cifar_data.py, there are some issues I don't understand: 1. The paper claim using 10 images per class, but in fact the code choose randomly first 100 images, so...

This happens when I run the command python -m cifar.cifar_train_background cifar-resnet-32.prototxt. Anyone know how to solve this issue?

AttributeError: 'MagicModule' object has no attribute '_forward_impl'

1

When I run weighting_imb01.sh this error occurs. Is there anyone know how to fix this?

GPU and training

1

I'm testing DetectoRS training using only 1 GPU with 1 image per gpu, 1 worker per gpu and the cuda memory is full already. My GPU has 11GB in memory....

Index xxx is out of bounds for dimension 4 with size 1

1

I try to follow the instruction after a lot of effort trying to debug. I only download val2014 and use as both training and testing since train2014 is quite big,...

YoLoV3

3

Can we run YoloV3 on this github repository?

I'm getting frustrated when trying to create a custom dataloader for this models. is there any instruction about this? I'm not familiar with COCO format