Upload 5 files

README.md

@@ -1,12 +1,13 @@
----
-title: Yolotest
-emoji: 🐠
-colorFrom: indigo
-colorTo: red
-sdk: gradio
-sdk_version: 5.37.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: test YOLO
+emoji: 🙄
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 4.40.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,102 @@
+import os
+import spaces
+import gradio as gr
+from functools import partial
+from huggingface_hub import hf_hub_download
+
+@spaces.GPU
+def dummy_gpu():
+    pass
+
+# https://github.com/R3gm/stablepy/blob/main/stablepy/diffusers_vanilla/adetailer.py
+# =====================================
+# Yolo
+# =====================================
+from pathlib import Path
+import numpy as np
+import torch
+from huggingface_hub import hf_hub_download
+from PIL import Image, ImageDraw
+from torchvision.transforms.functional import to_pil_image
+from ultralytics import YOLO
+
+def create_mask_from_bbox(
+    bboxes: np.ndarray, shape: tuple[int, int]
+) -> list[Image.Image]:
+    """
+    Parameters
+    ----------
+        bboxes: list[list[float]]
+            list of [x1, y1, x2, y2]
+            bounding boxes
+        shape: tuple[int, int]
+            shape of the image (width, height)
+
+    Returns
+    -------
+        masks: list[Image.Image]
+        A list of masks
+
+    """
+    masks = []
+    for bbox in bboxes:
+        mask = Image.new("L", shape, "black")
+        mask_draw = ImageDraw.Draw(mask)
+        mask_draw.rectangle(bbox, fill="white")
+        masks.append(mask)
+    return masks
+
+
+def mask_to_pil(masks: torch.Tensor, shape: tuple[int, int]) -> list[Image.Image]:
+    """
+    Parameters
+    ----------
+    masks: torch.Tensor, dtype=torch.float32, shape=(N, H, W).
+        The device can be CUDA, but `to_pil_image` takes care of that.
+
+    shape: tuple[int, int]
+        (width, height) of the original image
+
+    Returns
+    -------
+    images: list[Image.Image]
+    """
+    n = masks.shape[0]
+    return [to_pil_image(masks[i], mode="L").resize(shape) for i in range(n)]
+
+
+def yolo_detector(
+    image: Image.Image, model_path: str | Path | None = None, confidence: float = 0.3
+) -> list[Image.Image] | None:
+    if not model_path:
+        model_path = hf_hub_download("Bingsu/adetailer", "face_yolov8n.pt")
+    model = YOLO(model_path)
+    pred = model(image, conf=confidence)
+
+    bboxes = pred[0].boxes.xyxy.cpu().numpy()
+    if bboxes.size == 0:
+        return None
+
+    if pred[0].masks is None:
+        masks = create_mask_from_bbox(bboxes, image.size)
+    else:
+        masks = mask_to_pil(pred[0].masks.data, image.size)
+
+    return masks
+
+@spaces.GPU
+def infer(text: str):
+    detectors = []
+    person_model_path = hf_hub_download("Bingsu/adetailer", "person_yolov8s-seg.pt")
+    person_detector = partial(yolo_detector, model_path=person_model_path)
+    detectors.append(person_detector)
+    return str(detectors)
+
+with gr.Blocks() as demo:
+    input_text= gr.Textbox(label="Input", value="", show_copy_button=True)
+    run_button = gr.Button("Run", variant="primary")
+    output_text = gr.Textbox(label="Output", value="", show_copy_button=True)
+
+    run_button.click(infer, [input_text], [output_text])
+
+demo.queue().launch()

packages.txt

@@ -0,0 +1 @@
+git-lfs aria2 -y ffmpeg

pre-requirements.txt

@@ -0,0 +1 @@
+pip>=23.0.0

requirements.txt

@@ -0,0 +1,20 @@
+diffusers<=0.32.0
+transformers==4.47.1
+torch==2.4.0
+numpy<2
+gdown
+opencv-python
+torchvision
+accelerate
+optimum[onnxruntime]
+dartrs
+huggingface_hub
+hf_transfer
+hf_xet
+translatepy
+timm
+rapidfuzz
+sentencepiece
+unidecode
+ultralytics>=8.3.47
+pydantic==2.10.6