app.py

import gradio as gr
import os
os.environ["TORCH_CUDNN_SDPA_ENABLED"] = "1"
import torch
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
from sam2.build_sam import build_sam2
from sam2.sam2_image_predictor import SAM2ImagePredictor

# use bfloat16 for the entire notebook
torch.autocast(device_type="cuda", dtype=torch.bfloat16).__enter__()

if torch.cuda.get_device_properties(0).major >= 8:
    # turn on tfloat32 for Ampere GPUs (https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices)
    torch.backends.cuda.matmul.allow_tf32 = True
    torch.backends.cudnn.allow_tf32 = True
    
def show_mask(mask, ax, random_color=False, borders = True):
    if random_color:
        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
    else:
        color = np.array([30/255, 144/255, 255/255, 0.6])
    h, w = mask.shape[-2:]
    mask = mask.astype(np.uint8)
    mask_image =  mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
    if borders:
        import cv2
        contours, _ = cv2.findContours(mask,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) 
        # Try to smooth contours
        contours = [cv2.approxPolyDP(contour, epsilon=0.01, closed=True) for contour in contours]
        mask_image = cv2.drawContours(mask_image, contours, -1, (1, 1, 1, 0.5), thickness=2) 
    ax.imshow(mask_image)

def show_points(coords, labels, ax, marker_size=375):
    pos_points = coords[labels==1]
    neg_points = coords[labels==0]
    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)   

def show_box(box, ax):
    x0, y0 = box[0], box[1]
    w, h = box[2] - box[0], box[3] - box[1]
    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0, 0, 0, 0), lw=2))    

def show_masks(image, masks, scores, point_coords=None, box_coords=None, input_labels=None, borders=True):
    masks_store = []
    for i, (mask, score) in enumerate(zip(masks, scores)):
        plt.figure(figsize=(10, 10))
        plt.imshow(image)
        show_mask(mask, plt.gca(), borders=borders)
        if point_coords is not None:
            assert input_labels is not None
            show_points(point_coords, input_labels, plt.gca())
        if box_coords is not None:
            # boxes
            show_box(box_coords, plt.gca())
        if len(scores) > 1:
            plt.title(f"Mask {i+1}, Score: {score:.3f}", fontsize=18)
        plt.axis('off')
        # plt.show()

        # Save the figure as a JPG file
        filename = f"masked_image_{i+1}.jpg"
        plt.savefig(filename, format='jpg', bbox_inches='tight')

        masks_store.append(filename)
        
        # Close the figure to free up memory
        plt.close()

        return masks_store

def sam_process(input_image):
    image = Image.open(input_image)
    image = np.array(image.convert("RGB"))

    sam2_checkpoint = "./checkpoints/sam2_hiera_tiny.pt"
    model_cfg = "sam2_hiera_t.yaml"

    sam2_model = build_sam2(model_cfg, sam2_checkpoint, device="cuda")
    
    predictor = SAM2ImagePredictor(sam2_model)

    predictor.set_image(image)

    input_point = np.array([[539, 384]])
    input_label = np.array([1])

    print(predictor._features["image_embed"].shape, predictor._features["image_embed"][-1].shape)

    masks, scores, logits = predictor.predict(
        point_coords=input_point,
        point_labels=input_label,
        multimask_output=True,
    )
    sorted_ind = np.argsort(scores)[::-1]
    masks = masks[sorted_ind]
    scores = scores[sorted_ind]
    logits = logits[sorted_ind]

    print(masks.shape)

    results = show_masks(image, masks, scores, point_coords=input_point, input_labels=input_label, borders=True)
    print(results)

    return results

with gr.Blocks() as demo:
    with gr.Column():
        input_image = gr.Image(label="input image", type="filepath")
        submit_btn = gr.Button("Submit")
        output_result = gr.Textbox()
    submit_btn.click(
        fn = sam_process,
        inputs = [input_image],
        outputs = [output_result]
    )
demo.launch()