[Task]: Identifying small targets is not effective, are there any measures

[xingfenghaizeiwang]

What is the motivation for this task?

Identify some flaws

Describe the solution you'd like

dataset:
name: mvtec
format: folder
root: D:\project\anomalib\datasets\MVTec
normal_dir: card/train/good
normal_test_dir: card/test/good
abnormal_dir: card/test/ng
task: segmentation
mask_dir: null
extensions: null
train_batch_size: 32
eval_batch_size: 32
num_workers: 8
image_size: 256 # dimensions to which images are resized (mandatory)
center_crop: null # dimensions to which images are center-cropped after resizing (optional)
normalization: imagenet # data distribution to which the images will be normalized: [none, imagenet]
transform_config:
train: null
eval: null
test_split_mode: none # options: [from_dir, synthetic, none]
test_split_ratio: 0.2 # fraction of train images held out testing (usage depends on test_split_mode)
val_split_mode: synthetic # options: [same_as_test, from_test, synthetic]
val_split_ratio: 0.5 # fraction of train/test images held out for validation (usage depends on val_split_mode)
tiling:
apply: false
tile_size: null
stride: null
remove_border_count: 0
use_random_tiling: False
random_tile_count: 16

model:
name: padim
backbone: resnet18
pre_trained: true
layers:
- layer1
- layer2
- layer3
normalization_method: min_max # options: [none, min_max, cdf]

metrics:
image:
- F1Score
- AUROC
pixel:
- F1Score
- AUROC
threshold:
method: adaptive #options: [adaptive, manual]
manual_image: null
manual_pixel: null

visualization:
show_images: False # show images on the screen
save_images: True # save images to the file system
log_images: True # log images to the available loggers (if any)
image_save_path: null # path to which images will be saved
mode: full # options: ["full", "simple"]

project:
seed: 42
path: ./result

logging:
logger: [ ] # options: [comet, tensorboard, wandb, csv] or combinations.
log_graph: false # Logs the model graph to respective logger.

optimization:
export_mode: null # options: torch, onnx, openvino

PL Trainer Args. Don't add extra parameter here.

trainer:
enable_checkpointing: true
default_root_dir: null
gradient_clip_val: 0
gradient_clip_algorithm: norm
num_nodes: 1
devices: 1
enable_progress_bar: true
overfit_batches: 0.0
track_grad_norm: -1
check_val_every_n_epoch: 1 # Don't validate before extracting features.
fast_dev_run: false
accumulate_grad_batches: 1
max_epochs: 1
min_epochs: null
max_steps: -1
min_steps: null
max_time: null
limit_train_batches: 1.0
limit_val_batches: 1.0
limit_test_batches: 1.0
limit_predict_batches: 1.0
val_check_interval: 1.0 # Don't validate before extracting features.
log_every_n_steps: 50
accelerator: auto # <"cpu", "gpu", "tpu", "ipu", "hpu", "auto">
strategy: null
sync_batchnorm: false
precision: 32
enable_model_summary: true
num_sanity_val_steps: 0
profiler: null
benchmark: false
deterministic: false
reload_dataloaders_every_n_epochs: 0
auto_lr_find: false
replace_sampler_ddp: true
detect_anomaly: false
auto_scale_batch_size: false
plugins: null
move_metrics_to_cpu: true
multiple_trainloader_mode: max_size_cycle

Additional context

No response

[samet-akcay]

Hi @xingfenghaizeiwang, you could use tiling to focus on smaller objects. For an example, you could refer to this jupyter notebook
https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/104_tiling.ipynb