Nvidia GTX 1050 2GB not enough to run object detection on Batch size 1

I have been trying to run simple object detection model but gives different errors all the time for now i have encountered error code 1, -11 and out of memory
I have downloaded dataset images from MS COCO classes which also provides labels. Training images 306 and Val images 24 while I have made I have same number of labels with same names as images. I am following this guide https://github.com/dusty-nv/jetson-inference/blob/master/docs/detectnet-training.md just the difference I am training my model with less images and batch size: 1, batch accumulation 2 or 3. Passing dontcare, bottle in custom class option for dataset training. I ain’t sure is the hardware GTX 1050 2GB is not enough for training model even with less image resolution on batch size 1. I tried training couple of times but it fails most of the time. I am still trying to solve my problem and I know I will find someway. I tried to look it up on internet but could’n’t find any relevant solution .if anyone had such issue before or has any suggestion please feel free to drop in. Thanks and cheers

Here is the forum which I posted on google forums in digits group regarding my most common error
ERROR: error code 1 Object Detection detectnet Nvidia Digits training custom model using custom dataset