pip install -Uq "transformers>=5.9" datasets torchvision

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> from datasets import load_dataset

>>> MODEL_ID = "Roboflow/rf-detr-seg-medium"
>>> DATASET_ID = "merve/satellite-building-segmentation"

>>> ds = load_dataset(DATASET_ID)
>>> train_ds = ds["train"]
>>> valid_ds = ds["validation"]
>>> print(f"Train: {len(train_ds)} images, Valid: {len(valid_ds)} images")
Train: 6764 images, Valid: 1934 images

>>> sample = train_ds[0]
>>> print(f"Image ID: {sample['image_id']}")
Image ID: 0
>>> print(f"Image size: {sample['image'].size}")
Image size: (512, 512)
>>> print(f"Number of instances: {len(sample['objects']['id'])}")
Number of instances: 7
>>> print(f"\nObjects keys: {list(sample['objects'].keys())}")
<BLANKLINE>
Objects keys: ['id', 'area', 'bbox', 'segmentation', 'category', 'iscrowd']
>>> print(f"First bbox: {sample['objects']['bbox'][0]}")
First bbox: [80.0, 0.0, 51.0, 51.5]
>>> print(f"First category: {sample['objects']['category'][0]}")
First category: 0

>>> import numpy as np
>>> import matplotlib.pyplot as plt
>>> from PIL import Image, ImageDraw

>>> sample = train_ds[0]
>>> image = sample["image"].convert("RGB")

>>> fig, axes = plt.subplots(1, 2, figsize=(14, 6))
>>> _ = axes[0].imshow(image)
>>> _ = axes[0].set_title("Original image")
>>> _ = axes[0].axis("off")

>>> overlay = image.copy()
>>> draw = ImageDraw.Draw(overlay, "RGBA")
>>> objects = sample["objects"]
>>> for seg in objects["segmentation"]:
...     for poly in seg:
...         coords = list(zip(poly[0::2], poly[1::2]))
...         color = tuple(np.random.randint(50, 255, 3)) + (100,)
...         draw.polygon(coords, fill=color, outline="red")

>>> _ = axes[1].imshow(overlay)
>>> _ = axes[1].set_title(f"Ground truth ({len(objects['id'])} buildings)")
>>> _ = axes[1].axis("off")
>>> plt.tight_layout()
>>> plt.show()

>>> from transformers import AutoImageProcessor, AutoModelForInstanceSegmentation

>>> id2label = {0: "building"}
>>> label2id = {"building": 0}

>>> image_processor = AutoImageProcessor.from_pretrained(MODEL_ID)
>>> model = AutoModelForInstanceSegmentation.from_pretrained(
...     MODEL_ID,
...     id2label=id2label,
...     label2id=label2id,
...     ignore_mismatched_sizes=True,
... )

>>> from functools import partial
>>> from typing import Any


>>> def transform_batch(examples: dict[str, Any], image_processor) -> dict[str, Any]:
...     """Convert HF dataset rows into COCO-style dicts and pass to the processor."""
...     images, targets = [], []
...     for image, img_id, objects in zip(
...         examples["image"], examples["image_id"], examples["objects"]
...     ):
...         if not objects["id"]:
...             continue
...         annotations = [
...             {
...                 "id": ann_id,
...                 "image_id": img_id,
...                 "category_id": cat,
...                 "bbox": bbox,
...                 "area": area,
...                 "segmentation": seg,
...                 "iscrowd": crowd,
...             }
...             for ann_id, cat, bbox, area, seg, crowd in zip(
...                 objects["id"],
...                 objects["category"],
...                 objects["bbox"],
...                 objects["area"],
...                 objects["segmentation"],
...                 objects["iscrowd"],
...             )
...         ]
...         images.append(image.convert("RGB"))
...         targets.append({"image_id": img_id, "annotations": annotations})
...
...     if not images:
...         return {}
...     return image_processor(
...         images=images, annotations=targets, return_segmentation_masks=True, return_tensors="pt"
...     )


>>> transform = partial(transform_batch, image_processor=image_processor)
>>> train_ds = train_ds.shuffle(seed=42).with_transform(transform)
>>> valid_ds = valid_ds.with_transform(transform)

>>> example = train_ds[0]
>>> print(f"pixel_values shape: {example['pixel_values'].shape}")
pixel_values shape: torch.Size([3, 432, 432])
>>> print(f"pixel_mask shape: {example['pixel_mask'].shape}")
pixel_mask shape: torch.Size([432, 432])
>>> print(f"labels keys: {list(example['labels'].keys())}")
labels keys: ['size', 'image_id', 'class_labels', 'boxes', 'area', 'iscrowd', 'orig_size', 'masks']
>>> print(f"  class_labels: {example['labels']['class_labels']}")
  class_labels: tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
        0, 0])
>>> print(f"  boxes shape: {example['labels']['boxes'].shape}")
  boxes shape: torch.Size([26, 4])
>>> print(f"  masks shape: {example['labels']['masks'].shape}")
  masks shape: torch.Size([26, 432, 432])

>>> import torch


>>> def collate_fn(batch: list[dict[str, Any]]) -> dict[str, Any]:
...     out = {
...         "pixel_values": torch.stack([x["pixel_values"] for x in batch]),
...         "labels": [x["labels"] for x in batch],
...     }
...     if "pixel_mask" in batch[0]:
...         out["pixel_mask"] = torch.stack([x["pixel_mask"] for x in batch])
...     return out

>>> import torch.nn.functional as F


>>> @torch.no_grad()
... def compute_mean_iou(pred_masks, gt_masks, target_size):
...     """Union-based IoU: merge all instances per image, then compute IoU."""
...     pred_masks = F.interpolate(pred_masks[None], size=target_size, mode="bilinear", align_corners=False)[0]
...     pred_union = (pred_masks.sigmoid() > 0.5).any(dim=0)
...
...     gt_union = gt_masks.any(dim=0).bool()
...
...     intersection = (pred_union & gt_union).sum().float()
...     union = (pred_union | gt_union).sum().float()
...     return (intersection / union.clamp(min=1)).item()


>>> @torch.no_grad()
... def compute_metrics(evaluation_results):
...     predictions, targets = evaluation_results.predictions, evaluation_results.label_ids
...     ious = []
...     for pred_batch, target_batch in zip(predictions, targets):
...         batch_masks = pred_batch[3]
...         for i, gt_label in enumerate(target_batch):
...             gt_masks = torch.as_tensor(gt_label["masks"])
...             if gt_masks.numel() == 0:
...                 continue
...             target_size = gt_masks.shape[-2:]
...             pred_masks = torch.as_tensor(batch_masks[i])
...             ious.append(compute_mean_iou(pred_masks, gt_masks, target_size))
...
...     mean_iou = sum(ious) / len(ious) if ious else 0.0
...     return {"mean_iou": mean_iou}

>>> from transformers import Trainer, TrainingArguments

>>> training_args = TrainingArguments(
...     output_dir="rf-detr-seg-satellite-buildings",
...     num_train_epochs=10,
...     per_device_train_batch_size=16,
...     per_device_eval_batch_size=16,
...     learning_rate=1e-4,
...     weight_decay=1e-4,
...     lr_scheduler_type="cosine",
...     warmup_steps=0.1,
...     fp16=True,
...     dataloader_num_workers=4,
...     eval_strategy="epoch",
...     save_strategy="epoch",
...     save_total_limit=2,
...     load_best_model_at_end=True,
...     metric_for_best_model="eval_mean_iou",
...     greater_is_better=True,
...     remove_unused_columns=False,
...     eval_do_concat_batches=False,
...     push_to_hub=False,
... )

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     train_dataset=train_ds,
...     eval_dataset=valid_ds,
...     processing_class=image_processor,
...     data_collator=collate_fn,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

>>> trainer.push_to_hub(
...     dataset=DATASET_ID,
...     tags=["instance-segmentation", "rf-detr-seg", "vision", "satellite", "building"],
... )

>>> from datasets import load_dataset

>>> test_ds = load_dataset(DATASET_ID, split="test")
>>> sample = test_ds[0]
>>> image = sample["image"].convert("RGB")

>>> device = next(model.parameters()).device
>>> inputs = image_processor(images=image, return_tensors="pt").to(device)

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> results = image_processor.post_process_instance_segmentation(
...     outputs, threshold=0.5, target_sizes=[(image.height, image.width)]
... )[0]

>>> print(f"Detected {len(results['segments_info'])} buildings")
Detected 0 buildings
>>> for seg_info in results["segments_info"][:5]:
...     print(f"  Building (score: {seg_info['score']:.3f})")

>>> fig, axes = plt.subplots(1, 2, figsize=(14, 6))

>>> _ = axes[0].imshow(image)
>>> _ = axes[0].set_title("Input satellite image")
>>> _ = axes[0].axis("off")

>>> seg_map = results["segmentation"].cpu().numpy()
>>> overlay = np.array(image).copy()
>>> for seg_info in results["segments_info"]:
...     mask = seg_map == seg_info["id"]
...     color = np.random.randint(0, 255, 3)
...     overlay[mask] = (overlay[mask] * 0.4 + color * 0.6).astype(np.uint8)

>>> _ = axes[1].imshow(overlay)
>>> _ = axes[1].set_title(f"Predicted masks ({len(results['segments_info'])} buildings)")
>>> _ = axes[1].axis("off")
>>> plt.tight_layout()
>>> plt.show()