Delete 3_object_skeleton.py

3_object_skeleton.py

@@ -1,43 +0,0 @@
-import torch
-from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection
-from PIL import Image, ImageDraw
-
-# Specify the checkpoint name or identifier for the pre-trained model
-checkpoint = "google/owlvit-base-patch32"
-
-# Initialize the pre-trained model and processor
-model = AutoModelForZeroShotObjectDetection.from_pretrained(checkpoint)
-processor = AutoProcessor.from_pretrained(checkpoint)
-
-image = Image.open('/content/drive/MyDrive/img3.jpg')
-
-# Convert image to PIL Image format if not already
-if isinstance(image, str):
-	image = Image.open(image)
-
-text_queries = ["hat", "book", "sunglasses"]
-
-# Prepare inputs for zero-shot object detection
-inputs = processor(images=image, text=text_queries, return_tensors="pt")
-
-# Perform inference with the model
-with torch.no_grad():
-        outputs = model(**inputs)
-        target_sizes = torch.tensor([image.size[::-1]])
-        results = processor.post_process_object_detection(outputs, threshold=0.1, target_sizes=target_sizes)[0]
-
-# Create a drawing object for the image
-draw = ImageDraw.Draw(image)
-
-# Extract detection results (scores, labels, and bounding boxes)
-scores = results["scores"].tolist()
-labels = results["labels"].tolist()
-boxes = results["boxes"].tolist()
-
-# Iterate over detected objects and draw bounding boxes and labels
-for box, score, label in zip(boxes, scores, labels):
-        xmin, ymin, xmax, ymax = box
-        draw.rectangle((xmin, ymin, xmax, ymax), outline="red", width=1)
-        draw.text((xmin, ymin), f"{text_queries[label]}: {round(score, 2)}", fill="black")
-
-return image