Fine-tuning Rotated-RTMDET on a Custom DOTA Dataset:
i) Can you provide a detailed guide on fine-tuning the Rotated-RTMDET model for a custom dataset formatted similar to the DOTA dataset?
Configuration File Selection for Custom Dataset Fine-tuning:
i) When fine-tuning Rotated-RTMDET on a custom dataset, which config file is recommended to use?
Pre-trained Weight Selection for Fine-tuning:
i) For fine-tuning Rotated-RTMDET on custom DOTA-like dataset, which pre-trained weights should be advisable to use? Should I use DOTA pre-trained weights, COCO pre-trained weights, or ImageNet pre-trained weights?
Prerequisite
Task
I have modified the scripts/configs, or I'm working on my own tasks/models/datasets.
Branch
1.x branch https://github.com/open-mmlab/mmrotate/tree/1.x
Environment
sys.platform: linux Python: 3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0] CUDA available: True MUSA available: False numpy_random_seed: 2147483648 GPU 0: Tesla T4 CUDA_HOME: /usr NVCC: Cuda compilation tools, release 9.1, V9.1.8 GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.8.0 PyTorch compiling details: PyTorch built with:
TorchVision: 0.9.0 OpenCV: 4.9.0 MMEngine: 0.10.3 MMRotate: 1.0.0rc1+
Reproduces the problem - code sample
*
Reproduces the problem - command or script
*
Reproduces the problem - error message
*
Additional information
Fine-tuning Rotated-RTMDET on a Custom DOTA Dataset:
i) Can you provide a detailed guide on fine-tuning the Rotated-RTMDET model for a custom dataset formatted similar to the DOTA dataset?
Configuration File Selection for Custom Dataset Fine-tuning:
i) When fine-tuning Rotated-RTMDET on a custom dataset, which config file is recommended to use?
Pre-trained Weight Selection for Fine-tuning:
i) For fine-tuning Rotated-RTMDET on custom DOTA-like dataset, which pre-trained weights should be advisable to use? Should I use DOTA pre-trained weights, COCO pre-trained weights, or ImageNet pre-trained weights?