Duplicate from adirik/image-guided-owlvit

Co-authored-by: Alara Dirik <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.ckpt 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
+*.mlmodel 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
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Image-Guided OWL-ViT Demo
+emoji: 🔥
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.10.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: adirik/image-guided-owlvit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,79 @@
+import torch
+import cv2
+import gradio as gr
+import numpy as np
+from transformers import OwlViTProcessor, OwlViTForObjectDetection
+
+
+# Use GPU if available
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+else:
+    device = torch.device("cpu")
+
+model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32").to(device)
+model.eval()
+processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
+
+
+def image_guided_detection(img, query_img, score_threshold, nms_threshold):
+    target_sizes = torch.Tensor([img.size[::-1]])
+    inputs = processor(query_images=query_img, images=img, return_tensors="pt").to(device)
+
+    with torch.no_grad():
+        outputs = model.image_guided_detection(**inputs)
+    
+    outputs.logits = outputs.logits.cpu()
+    outputs.pred_boxes = outputs.target_pred_boxes.cpu() 
+
+    results = processor.post_process_image_guided_detection(
+        outputs=outputs, 
+        threshold=score_threshold, 
+        nms_threshold=nms_threshold,
+        target_sizes=target_sizes
+    )
+  
+    boxes, scores = results[0]["boxes"], results[0]["scores"]
+    img = np.asarray(img)
+
+    for box, score in zip(boxes, scores):
+        box = [int(i) for i in box.tolist()]
+
+        if score >= score_threshold:
+            img = cv2.rectangle(img, box[:2], box[2:], (255,0,0), 5)
+            if box[3] + 25 > 768:
+                y = box[3] - 10
+            else:
+                y = box[3] + 25
+    return img
+
+
+description = """
+Gradio demo for image-guided / one-shot object detection with OWL-ViT - 
+<a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>, 
+introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
+with Vision Transformers</a>. 
+
+\n\nYou can use OWL-ViT to query images with text descriptions of any object or alternatively with an 
+example / query image of the target object. To use it, simply upload an image and a query image that only contains the object
+ you're looking for. You can also use the score and non-maximum suppression threshold sliders to set a threshold to filter out 
+ low probability and overlapping bounding box predictions.
+
+\n\nFor an in-depth tutorial on how to use OWL-ViT with transformers, check out our 
+<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb">Colab notebook</a>
+ and our HF spaces <a href="https://huggingface.co/spaces/adirik/OWL-ViT">demo </a>for zero-shot / text-guided object detection. 
+"""
+
+demo = gr.Interface(
+    image_guided_detection, 
+    inputs=[gr.Image(type="pil"), gr.Image(type="pil"), gr.Slider(0, 1, value=0.6), gr.Slider(0, 1, value=0.3)], 
+    outputs="image",
+    title="Image-Guided Object Detection with OWL-ViT",
+    description=description,
+    examples=[
+        ["assets/image2.jpeg", "assets/query2.jpeg", 0.7, 0.3],
+        ["assets/image1.jpeg", "assets/query1.jpeg", 0.6, 0.3]
+    ]
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+# pip install -r requirements.txt
+
+torch==1.13.0
+git+https://github.com/huggingface/transformers.git
+opencv-python>=4.5.0
+Pillow