from transformers import AutoProcessor, AutoModelForCausalLM
import matplotlib.pyplot as plt
import matplotlib.patches as patches

model_id = "Nikhil-aka-Nick/florence2-finalV13"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, device_map="cuda") # load the model on GPU
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

def run_example(task_prompt, image, max_new_tokens=128):
    prompt = task_prompt
    inputs = processor(text=prompt, images=image, return_tensors="pt")
    generated_ids = model.generate(
      input_ids=inputs["input_ids"].cuda(),
      pixel_values=inputs["pixel_values"].cuda(),
      max_new_tokens=max_new_tokens,
      early_stopping=False,
      do_sample=False,
      num_beams=3,
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
    parsed_answer = processor.post_process_generation(
        generated_text,
        task=task_prompt,
        image_size=(image.width, image.height)
    )
    return parsed_answer

import matplotlib.pyplot as plt
import matplotlib.patches as patches

def plot_bbox(image, data, figsize=(12, 12)):  # Add figsize as a parameter with default size
    fig, ax = plt.subplots(figsize=figsize)

    # Display the image
    ax.imshow(image)

    # Plot each bounding box
    for bbox, label in zip(data['bboxes'], data['labels']):
        # Unpack the bounding box coordinates
        x1, y1, x2, y2 = bbox
        # Create a Rectangle patch
        rect = patches.Rectangle((x1, y1), x2-x1, y2-y1, linewidth=1, edgecolor='r', facecolor='none')
        # Add the rectangle to the Axes
        ax.add_patch(rect)
        # Annotate the label
        plt.text(x1, y1, label, color='white', fontsize=8, bbox=dict(facecolor='red', alpha=0.5))

    # Remove the axis ticks and labels
    ax.axis('off')

    # Show the plot
    plt.show()


from datasets import load_dataset

dataset = load_dataset("Nikhil-aka-Nick/My_data_for_test")



example_id = 5
image = dataset["train"][example_id]["image"]

parsed_answer = run_example("<OD>", image=image)
plot_bbox(image, parsed_answer["<OD>"])