Train sam2 on SA-1B

I see the config in another issue, and i have a try, but..
> Hi @hpichlerbio, thanks for your interest. One way to finetune on your custom **image** only dataset is to follow the last [section](https://github.com/facebookresearch/sam2/tree/main/training#training-on-images-and-videos) in the training README but remove the video dataset from the mix. The config would look something like this (removing the video dataset from the mix):
>
> ```yaml
> data:
> train:
> _target_: training.dataset.sam2_datasets.TorchTrainMixedDataset
> phases_per_epoch: ${phases_per_epoch} # Chunks a single epoch into smaller phases
> batch_sizes: # List of batch sizes corresponding to each dataset
> - ${bs1} # Batch size of dataset 1
> datasets:
> # Custom Image dataset
> - _target_: training.dataset.vos_dataset.VOSDataset
> training: true
> video_dataset:
> _target_: training.dataset.vos_raw_dataset.CustomImageDataset # Your custom Dataset class
> img_folder: ${path_to_img_folder}
> gt_folder: ${path_to_gt_folder}
> file_list_txt: ${path_to_train_filelist} # Optional
> sampler:
> _target_: training.dataset.vos_sampler.RandomUniformSampler
> num_frames: 1
> max_num_objects: ${max_num_objects_per_image}
> transforms: ${image_transforms}
> shuffle: True
> num_workers: ${num_train_workers}
> pin_memory: True
> drop_last: True
> collate_fn:
> _target_: training.utils.data_utils.collate_fn
> _partial_: true
> dict_key: all
> ```
>
> Note that if you'd like to use your custom dataset, you should implement your own dataset class (similar to [`SA1BRawDataset`](https://github.com/facebookresearch/sam2/blob/52198ead0eb13ae8270bea6ca768ef175f5bf167/training/dataset/vos_raw_dataset.py#L148)). If your dataset is in SA1B format, you can directly use `SA1BRawDataset`. Please let me know if you have further questions

I write like this, the program will output an error, i think you miss the multiplier, after i fix the bug, i run the program on SA-1B, the program will always out a warnning, like this:
```text
INFO 2024-11-02 19:49:22,049 train_utils.py: 271: Train Epoch: [0][ 100/2796] | Batch Time: 0.91 (1.31) | Data Time: 0.00 (0.44) | Mem (GB): 52.00 (52.77/54.00) | Time Elapsed: 00d 00h 02m | Losses/train_all_loss: 5.03e-01 (7.52e-01)
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
WARNING:root:Skip RandomAffine for zero-area mask in first frame after 1 tentatives
```
What should I do to reduce this warnning？
My hyperparameters:
```yaml
scratch:
resolution: 1024
train_batch_size: 4
num_train_workers: 10
num_frames: 1
max_num_objects: 5
base_lr: 5.0e-6
vision_lr: 3.0e-06
phases_per_epoch: 1
num_epochs: 40

dataset:
# PATHS to Dataset
img_folder: ./SA-1B
gt_folder: ./SA-1B
multiplier: 2
```
My dataset config:
```yaml
data:
train:
_target_: training.dataset.sam2_datasets.TorchTrainMixedDataset
phases_per_epoch: ${scratch.phases_per_epoch} # Chunks a single epoch into smaller phases
batch_sizes: # List of batch sizes corresponding to each dataset
- ${scratch.train_batch_size}
datasets:
# Custom Image dataset
- _target_: training.dataset.vos_dataset.VOSDataset
training: true
video_dataset:
_target_: training.dataset.vos_raw_dataset.SA1BRawDataset # Your custom Dataset class
img_folder: ${dataset.img_folder}
gt_folder: ${dataset.gt_folder}
sampler:
_target_: training.dataset.vos_sampler.RandomUniformSampler
num_frames: ${scratch.num_frames}
max_num_objects: 5
transforms: ${vos.train_transforms}
multiplier: ${dataset.multiplier}
shuffle: True
num_workers: ${scratch.num_train_workers}
pin_memory: True
drop_last: True
collate_fn:
_target_: training.utils.data_utils.collate_fn
_partial_: true
dict_key: all
```

Start in training/dataset/vos_raw_dataset.py at SA1BRawDataset and follow the configured VOSDataset path into vos.train_transforms, focusing on the RandomAffine warning for zero-area masks. Reproduce it with the shown SA-1B configuration and determine whether the input masks or transform behavior causes the skips; done means training runs with an understood, appropriately reduced warning rate.

Written by the indexing model from the issue text.