picosankaricpp

I've changed custom_detection.yml to have num_classes: 2 # your dataset classes remap_mscoco_category: False I'm trying to train on custom data with one class. I train using this command: $env:CUDA_VISIBLE_DEVICES="0"; python...

Loss staying high while trying to tune network

3

I'm trying to tune the obj365+coco for my custom dataset. I have 1 class. This is the class information from the coco annotations: "categories": [{"supercategory": "none", "id": 0, "name": "0"}]}....

16 bit gray scale training

2

I'd like to train this model on 16 bit, single channel images. Is there a way to do this?

libuv Use on Windows

1

I'm trying to fine tune with this on Windows. Whenever I try to run it, I get the 'use_libuv was requested but PyTorch was build without libuv support' error. Is...

I'm trying to adapt this for 16 bit single channel images. What changes do I need to make to accomplish that?