Duplicate from dbmdz/detectron2-model-demo

Co-authored-by: Stefan <stefan-it@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Detectron2 Model Demo
+emoji: 👁
+colorFrom: pink
+colorTo: purple
+sdk: gradio
+sdk_version: 3.1.4
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: dbmdz/detectron2-model-demo
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,74 @@
+try:
+    import detectron2
+except:
+    import os 
+    os.system('pip install git+https://github.com/facebookresearch/detectron2.git')
+
+import cv2
+
+from matplotlib.pyplot import axis
+import gradio as gr
+import requests
+import numpy as np
+from torch import nn
+import requests
+
+import torch
+
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.data import MetadataCatalog
+
+
+model_path = "https://huggingface.co/dbmdz/detectron2-model/resolve/main/model_final.pth"
+
+cfg = get_cfg()
+cfg.merge_from_file("./configs/detectron2/faster_rcnn_R_50_FPN_3x.yaml")
+cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
+cfg.MODEL.WEIGHTS = model_path
+
+my_metadata = MetadataCatalog.get("dbmdz_coco_all")
+my_metadata.thing_classes = ["Illumination", "Illustration"]
+
+if not torch.cuda.is_available():
+    cfg.MODEL.DEVICE = "cpu"
+
+
+def inference(image_url, image, min_score):
+    if image_url:
+        r = requests.get(image_url)
+        if r:
+            im = np.frombuffer(r.content, dtype="uint8")
+            im = cv2.imdecode(im, cv2.IMREAD_COLOR)
+    else:
+        # Model expect BGR!
+        im = image[:,:,::-1]
+
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = min_score
+    predictor = DefaultPredictor(cfg)
+
+    outputs = predictor(im)
+
+    v = Visualizer(im, my_metadata, scale=1.2)
+    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
+
+    return out.get_image()
+
+
+title = "DBMDZ Detectron2 Model Demo"
+description = "This demo introduces an interactive playground for our trained Detectron2 model. <br>The model was trained on manually annotated segments from digitized books to detect Illustration or Illumination segments on a given page."
+article = '<p>Detectron model is available from our repository <a href="">here</a> on the Hugging Face Model Hub.</p>'
+
+gr.Interface(
+    inference,
+    [gr.inputs.Textbox(label="Image URL", placeholder="https://api.digitale-sammlungen.de/iiif/image/v2/bsb10483966_00008/full/500,/0/default.jpg"),
+     gr.inputs.Image(type="numpy", label="Input Image"),
+     gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Minimum score"),
+    ], 
+    gr.outputs.Image(type="pil", label="Output"),
+    title=title,
+    description=description,
+    article=article,
+    examples=[]).launch()

configs/detectron2/Base-RCNN-FPN.yaml

@@ -0,0 +1,42 @@
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  BACKBONE:
+    NAME: "build_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
+  FPN:
+    IN_FEATURES: ["res2", "res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
+    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
+  RPN:
+    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
+    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
+    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
+    # Detectron1 uses 2000 proposals per-batch,
+    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
+    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
+    POST_NMS_TOPK_TRAIN: 1000
+    POST_NMS_TOPK_TEST: 1000
+  ROI_HEADS:
+    NAME: "StandardROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+  ROI_MASK_HEAD:
+    NAME: "MaskRCNNConvUpsampleHead"
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

configs/detectron2/faster_rcnn_R_50_FPN_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "./Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

requirements.txt

@@ -0,0 +1,4 @@
+opencv-python-headless
+pyyaml==5.1
+torch
+torchvision