Manu
commited on
Commit
·
10e69ed
1
Parent(s):
6f3b453
app without requirements added
Browse files- app.py +98 -3
- image_utils.py +37 -0
- requirements.txt +0 -0
- segmentation_utils.py +371 -0
app.py
CHANGED
|
@@ -1,7 +1,102 @@
|
|
| 1 |
import gradio as gr
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
def
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
demo = gr.Interface(fn=greet, inputs="text", outputs="text")
|
| 7 |
demo.launch()
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
+
import requests
|
| 3 |
+
from image_utils import print_text_on_image_centered, create_background_image
|
| 4 |
+
from hf_utils import hf_validate_api_token
|
| 5 |
+
from segmentation_utils import segment_and_overlay_results
|
| 6 |
|
| 7 |
+
def segment_gradio_image(api_token, model, image):
|
| 8 |
+
|
| 9 |
+
# Validacion del token y la imagen
|
| 10 |
+
|
| 11 |
+
is_token_valid, api_token_message = hf_validate_api_token(api_token)
|
| 12 |
+
if not is_token_valid:
|
| 13 |
+
text_image = print_text_on_image_centered(
|
| 14 |
+
create_background_image(500, 500, "white"),
|
| 15 |
+
'HuggingFace API Token invalid. Please enter a valid token.',
|
| 16 |
+
'red'
|
| 17 |
+
)
|
| 18 |
+
segments_list = "No segments available."
|
| 19 |
+
else:
|
| 20 |
+
if image is None:
|
| 21 |
+
text_image = print_text_on_image_centered(
|
| 22 |
+
create_background_image(500, 500, "white"),
|
| 23 |
+
'No image detected',
|
| 24 |
+
'orange'
|
| 25 |
+
)
|
| 26 |
+
segments_list = "No segments available."
|
| 27 |
+
else:
|
| 28 |
+
text_image = print_text_on_image_centered(
|
| 29 |
+
create_background_image(500, 500, "white"),
|
| 30 |
+
'PROCESANDO',
|
| 31 |
+
'blue'
|
| 32 |
+
)
|
| 33 |
+
segments_list = "No segments available."
|
| 34 |
+
# Assuming segment_image is a placeholder for actual segmentation function
|
| 35 |
+
# Uncomment and modify this part according to your segmentation implementation
|
| 36 |
+
# response = segment_image(api_token, model, image)
|
| 37 |
+
# text_image = response["segmented_image"]
|
| 38 |
+
|
| 39 |
+
text_image, segments = segment_and_overlay_results(image,model,api_token)
|
| 40 |
+
print("app.py segment_gradio_image")
|
| 41 |
+
segments_list = "Segments:\n"
|
| 42 |
+
for segment in segments:
|
| 43 |
+
print(segment['label'] + " " + str(segment['score']))
|
| 44 |
+
segments_list += f"\n{segment['label']}: {segment['score']}"
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
return api_token_message, text_image, segments_list
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
with gr.Blocks() as demo:
|
| 52 |
+
gr.Markdown("# Segment Image")
|
| 53 |
+
gr.Markdown("Upload an image and let the model segment it.")
|
| 54 |
+
|
| 55 |
+
with gr.Row():
|
| 56 |
+
api_token = gr.Textbox(
|
| 57 |
+
label="API Token",
|
| 58 |
+
placeholder="Enter your Hugging Face API token here"
|
| 59 |
+
)
|
| 60 |
+
model_name = gr.Textbox(
|
| 61 |
+
label="AI Segmentation Model",
|
| 62 |
+
placeholder="Enter your Segmentation model here",
|
| 63 |
+
value="facebook/mask2former-swin-tiny-coco-panoptic"
|
| 64 |
+
)
|
| 65 |
+
|
| 66 |
+
image_input = gr.Image(label="Upload Image")
|
| 67 |
+
|
| 68 |
+
with gr.Row():
|
| 69 |
+
api_token_validation = gr.Textbox(label="API Token Validation")
|
| 70 |
+
segmented_image = gr.Image(label="Segmented Image")
|
| 71 |
+
|
| 72 |
+
# New block for segments output
|
| 73 |
+
|
| 74 |
+
with gr.Row():
|
| 75 |
+
segments_output = gr.Textbox(label="Segments")
|
| 76 |
+
|
| 77 |
+
examples = gr.Examples(
|
| 78 |
+
examples=[
|
| 79 |
+
["Your HF API Token", "facebook/mask2former-swin-tiny-coco-panoptic", "https://upload.wikimedia.org/wikipedia/commons/7/74/A-Cat.jpg"]
|
| 80 |
+
],
|
| 81 |
+
inputs=[api_token, model_name, image_input]
|
| 82 |
+
)
|
| 83 |
+
|
| 84 |
+
api_token.change(
|
| 85 |
+
fn=segment_gradio_image,
|
| 86 |
+
inputs=[api_token, model_name, image_input],
|
| 87 |
+
outputs=[api_token_validation, segmented_image, segments_output]
|
| 88 |
+
)
|
| 89 |
+
|
| 90 |
+
model_name.change(
|
| 91 |
+
fn=segment_gradio_image,
|
| 92 |
+
inputs=[api_token, model_name, image_input],
|
| 93 |
+
outputs=[api_token_validation, segmented_image, segments_output]
|
| 94 |
+
)
|
| 95 |
+
|
| 96 |
+
image_input.change(
|
| 97 |
+
fn=segment_gradio_image,
|
| 98 |
+
inputs=[api_token, model_name, image_input],
|
| 99 |
+
outputs=[api_token_validation, segmented_image, segments_output]
|
| 100 |
+
)
|
| 101 |
|
|
|
|
| 102 |
demo.launch()
|
image_utils.py
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from PIL import Image, ImageDraw, ImageFont
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
def print_text_on_image_centered(image, text, color="black"):
|
| 5 |
+
# Crea un objeto Draw para la imagen
|
| 6 |
+
draw = ImageDraw.Draw(image)
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
# Define el tamaño inicial de la fuente
|
| 10 |
+
font_size = 30
|
| 11 |
+
font = ImageFont.load_default().font_variant(size=font_size)
|
| 12 |
+
|
| 13 |
+
# Calcula las dimensiones del texto
|
| 14 |
+
text_bbox = draw.textbbox((0, 0), text, font=font)
|
| 15 |
+
text_width = text_bbox[2] - text_bbox[0]
|
| 16 |
+
text_height = text_bbox[3] - text_bbox[1]
|
| 17 |
+
|
| 18 |
+
# Reduce el tamaño de la fuente hasta que el texto se ajuste dentro de la imagen
|
| 19 |
+
while text_width > image.width:
|
| 20 |
+
font_size -= 1
|
| 21 |
+
font = ImageFont.load_default().font_variant(size=font_size)
|
| 22 |
+
text_bbox = draw.textbbox((0, 0), text, font=font)
|
| 23 |
+
text_width = text_bbox[2] - text_bbox[0]
|
| 24 |
+
|
| 25 |
+
# Calcula la posición del texto
|
| 26 |
+
text_x = (image.width - text_width) / 2
|
| 27 |
+
text_y = (image.height - text_height) / 2
|
| 28 |
+
|
| 29 |
+
# Dibuja el texto en la imagen
|
| 30 |
+
draw.text((text_x, text_y), text, font=font, fill=color)
|
| 31 |
+
return image
|
| 32 |
+
|
| 33 |
+
# Crea una imagen en blanco por defecto
|
| 34 |
+
|
| 35 |
+
def create_background_image(width, height, color="white"):
|
| 36 |
+
return Image.new("RGB", (width, height), color)
|
| 37 |
+
|
requirements.txt
ADDED
|
File without changes
|
segmentation_utils.py
ADDED
|
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import requests
|
| 2 |
+
from pycocotools import mask
|
| 3 |
+
import matplotlib.pyplot as plt
|
| 4 |
+
from PIL import Image, ImageDraw, ImageOps, ImageFont
|
| 5 |
+
from dotenv import find_dotenv, load_dotenv
|
| 6 |
+
import os
|
| 7 |
+
import base64
|
| 8 |
+
import io
|
| 9 |
+
import random
|
| 10 |
+
import numpy as np
|
| 11 |
+
import cv2
|
| 12 |
+
from image_utils import print_text_on_image_centered, create_background_image
|
| 13 |
+
from icecream import ic
|
| 14 |
+
import traceback
|
| 15 |
+
from pprint import pprint
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
load_dotenv(find_dotenv())
|
| 19 |
+
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
|
| 20 |
+
|
| 21 |
+
API_URL = "https://api-inference.huggingface.co/models/facebook/mask2former-swin-tiny-coco-panoptic"
|
| 22 |
+
headers = {"Authorization": f"Bearer {HUGGINGFACEHUB_API_TOKEN}"}
|
| 23 |
+
|
| 24 |
+
# Función para transformar la entrada en un array de numpy
|
| 25 |
+
# Si la entrada es una URL, descarga la imagen y la convierte en un array de numpy
|
| 26 |
+
# Si la entrada es una ruta de archivo, carga la imagen y la convierte en un array de numpy
|
| 27 |
+
# Si la entrada ya es un array de numpy, devuélvela tal cual
|
| 28 |
+
# Si la entrada no es ninguna de las anteriores, lanza un ValueError
|
| 29 |
+
|
| 30 |
+
def transform_image_to_numpy_array(input):
|
| 31 |
+
if isinstance(input, np.ndarray):
|
| 32 |
+
# Si la entrada es un array de numpy, devuélvela tal cual
|
| 33 |
+
h, w = input.shape[:2]
|
| 34 |
+
new_height = int(h * (500 / w))
|
| 35 |
+
return cv2.resize(input, (500, new_height))
|
| 36 |
+
elif isinstance(input, str):
|
| 37 |
+
# Si la entrada es una cadena, podría ser una URL o una ruta de archivo
|
| 38 |
+
if input.startswith('http://') or input.startswith('https://'):
|
| 39 |
+
# Si la entrada es una URL, descarga la imagen y conviértela en un array de numpy
|
| 40 |
+
# se necesita un header para evitar el error 403
|
| 41 |
+
headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36"}
|
| 42 |
+
response = requests.get(input, headers=headers)
|
| 43 |
+
ic(response.status_code)
|
| 44 |
+
image_array = np.frombuffer(response.content, dtype=np.uint8)
|
| 45 |
+
image = cv2.imdecode(image_array, -1)
|
| 46 |
+
|
| 47 |
+
# Si la imagen tiene 3 canales (es decir, es una imagen en color),
|
| 48 |
+
# convertirla de BGR a RGB
|
| 49 |
+
if image.ndim == 3:
|
| 50 |
+
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
| 51 |
+
image = Image.fromarray(image).convert("RGBA")
|
| 52 |
+
image = np.array(image)
|
| 53 |
+
else:
|
| 54 |
+
# Si la entrada es una ruta de archivo, carga la imagen y conviértela en un array de numpy
|
| 55 |
+
image = cv2.imread(input)
|
| 56 |
+
|
| 57 |
+
h, w = image.shape[:2]
|
| 58 |
+
new_height = int(h * (500 / w))
|
| 59 |
+
return cv2.resize(image, (500, new_height))
|
| 60 |
+
else:
|
| 61 |
+
raise ValueError("La entrada no es un array de numpy, una URL ni una ruta de archivo.")
|
| 62 |
+
|
| 63 |
+
def transform_image_to_numpy_array2(input):
|
| 64 |
+
if isinstance(input, np.ndarray):
|
| 65 |
+
# Si la entrada es un array de numpy, devuélvela tal cual
|
| 66 |
+
return cv2.resize(input, (500, 500))
|
| 67 |
+
elif isinstance(input, str):
|
| 68 |
+
# Si la entrada es una cadena, podría ser una URL o una ruta de archivo
|
| 69 |
+
if input.startswith('http://') or input.startswith('https://'):
|
| 70 |
+
# Si la entrada es una URL, descarga la imagen y conviértela en un array de numpy
|
| 71 |
+
# se necesita un header para evitar el error 403
|
| 72 |
+
headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36"}
|
| 73 |
+
response = requests.get(input, headers=headers)
|
| 74 |
+
ic(response.status_code)
|
| 75 |
+
image_array = np.frombuffer(response.content, dtype=np.uint8)
|
| 76 |
+
image = cv2.imdecode(image_array, -1)
|
| 77 |
+
|
| 78 |
+
# Si la imagen tiene 3 canales (es decir, es una imagen en color),
|
| 79 |
+
# convertirla de BGR a RGB
|
| 80 |
+
if image.ndim == 3:
|
| 81 |
+
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
| 82 |
+
image = Image.fromarray(image).convert("RGBA")
|
| 83 |
+
image = np.array(image)
|
| 84 |
+
else:
|
| 85 |
+
# Si la entrada es una ruta de archivo, carga la imagen y conviértela en un array de numpy
|
| 86 |
+
image = cv2.imread(input)
|
| 87 |
+
|
| 88 |
+
return cv2.resize(image, (500, 500))
|
| 89 |
+
else:
|
| 90 |
+
raise ValueError("La entrada no es un array de numpy, una URL ni una ruta de archivo.")
|
| 91 |
+
|
| 92 |
+
def segment_image_from_numpy(image_array):
|
| 93 |
+
# Convert the image to bytes
|
| 94 |
+
is_success, im_buf_arr = cv2.imencode(".jpg", image_array)
|
| 95 |
+
data = im_buf_arr.tobytes()
|
| 96 |
+
response = requests.post(API_URL, headers=headers, data=data)
|
| 97 |
+
pprint(response.json())
|
| 98 |
+
return response.json()
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
def segment_image_from_path(image_path):
|
| 102 |
+
with open(image_path, "rb") as f:
|
| 103 |
+
data = f.read()
|
| 104 |
+
response = requests.post(API_URL, headers=headers, data=data)
|
| 105 |
+
return response.json()
|
| 106 |
+
|
| 107 |
+
def segment_image_from_image(image):
|
| 108 |
+
# Convert the image to bytes
|
| 109 |
+
is_success, im_buf_arr = cv2.imencode(".jpg", image)
|
| 110 |
+
data = im_buf_arr.tobytes()
|
| 111 |
+
|
| 112 |
+
response = requests.post(API_URL, headers=headers, data=data)
|
| 113 |
+
return response.json()
|
| 114 |
+
|
| 115 |
+
def decode_mask(mask_str, size):
|
| 116 |
+
mask_data = base64.b64decode(mask_str)
|
| 117 |
+
mask_image = Image.open(io.BytesIO(mask_data))
|
| 118 |
+
mask_image = mask_image.resize(size).convert("L")
|
| 119 |
+
return mask_image
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
def overlay_masks_on_image(image, segments, transparency=0.4):
|
| 123 |
+
if isinstance(image, np.ndarray):
|
| 124 |
+
image = Image.fromarray(image)
|
| 125 |
+
|
| 126 |
+
original_image = image
|
| 127 |
+
if original_image.mode != 'RGBA':
|
| 128 |
+
original_image = original_image.convert('RGBA')
|
| 129 |
+
|
| 130 |
+
overlay = Image.new("RGBA", original_image.size, (255, 255, 255, 0))
|
| 131 |
+
text_layer = Image.new("RGBA", original_image.size, (255, 255, 255, 0))
|
| 132 |
+
|
| 133 |
+
for segment in segments:
|
| 134 |
+
mask_str = segment['mask']
|
| 135 |
+
mask_image = decode_mask(mask_str, original_image.size)
|
| 136 |
+
color = generate_random_color()
|
| 137 |
+
|
| 138 |
+
color_mask = ImageOps.colorize(mask_image, black="black", white=color)
|
| 139 |
+
color_mask.putalpha(mask_image)
|
| 140 |
+
|
| 141 |
+
overlay = Image.alpha_composite(overlay, color_mask)
|
| 142 |
+
|
| 143 |
+
# Calcula el centroide de la mascara
|
| 144 |
+
x, y = np.where(np.array(mask_image) > 0)
|
| 145 |
+
centroid_x = x.mean()
|
| 146 |
+
centroid_y = y.mean()
|
| 147 |
+
|
| 148 |
+
# Imprime la etiqueta y la puntuación en la capa de texto
|
| 149 |
+
font_size = 30
|
| 150 |
+
draw = ImageDraw.Draw(text_layer)
|
| 151 |
+
font = ImageFont.load_default().font_variant(size=font_size)
|
| 152 |
+
label = segment['label']
|
| 153 |
+
score = segment['score']
|
| 154 |
+
text =f"{label}: {score}"
|
| 155 |
+
|
| 156 |
+
# Calcula el tamaño del texto
|
| 157 |
+
text_bbox = draw.textbbox((0, 0), text, font=font)
|
| 158 |
+
text_width = text_bbox[2] - text_bbox[0]
|
| 159 |
+
text_height = text_bbox[3] - text_bbox[1]
|
| 160 |
+
|
| 161 |
+
# Asegúrate de que las coordenadas del texto están dentro de los límites de la imagen
|
| 162 |
+
text_x = max(0, min(centroid_x - text_width / 2, original_image.size[0] - text_width))
|
| 163 |
+
text_y = max(0, min(centroid_y - text_height / 2, original_image.size[1] - text_height))
|
| 164 |
+
|
| 165 |
+
draw.text((text_x, text_y), text, fill=(255, 255, 255, 255), font=font)
|
| 166 |
+
|
| 167 |
+
# Ajusta la transparencia de la capa de superposición
|
| 168 |
+
overlay = Image.blend(original_image, overlay, transparency)
|
| 169 |
+
|
| 170 |
+
# Combina la capa de superposición con la capa de texto
|
| 171 |
+
final_image = Image.alpha_composite(overlay, text_layer)
|
| 172 |
+
|
| 173 |
+
return final_image
|
| 174 |
+
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
def overlay_masks_on_image2(image, segments, transparency=0.4):
|
| 183 |
+
# Convert numpy array to PIL Image
|
| 184 |
+
#original_image = Image.fromarray(image).convert("RGBA")
|
| 185 |
+
#original_image = image
|
| 186 |
+
#original_image = Image.open(image).convert("RGBA")
|
| 187 |
+
# para file es str
|
| 188 |
+
# para url es numpy.ndarray
|
| 189 |
+
# para cv.imread es numpy.ndarray
|
| 190 |
+
|
| 191 |
+
# Convertir el array de numpy a una imagen PIL si es necesario
|
| 192 |
+
if isinstance(image, np.ndarray):
|
| 193 |
+
image = Image.fromarray(image)
|
| 194 |
+
|
| 195 |
+
print(type(image))
|
| 196 |
+
print(image)
|
| 197 |
+
original_image = image
|
| 198 |
+
|
| 199 |
+
if original_image.mode != 'RGBA':
|
| 200 |
+
original_image = original_image.convert('RGBA')
|
| 201 |
+
|
| 202 |
+
print(original_image.size)
|
| 203 |
+
overlay = Image.new("RGBA", original_image.size, (255, 255, 255, 0))
|
| 204 |
+
print(overlay.size)
|
| 205 |
+
# Nueva capa para el texto
|
| 206 |
+
|
| 207 |
+
text_layer = Image.new("RGBA", original_image.size, (255, 255, 255, 0))
|
| 208 |
+
|
| 209 |
+
for segment in segments:
|
| 210 |
+
|
| 211 |
+
|
| 212 |
+
print(segment['label'] + " " + str(segment['score']))
|
| 213 |
+
mask_str = segment['mask']
|
| 214 |
+
mask_image = decode_mask(mask_str, original_image.size)
|
| 215 |
+
|
| 216 |
+
|
| 217 |
+
|
| 218 |
+
# Convierte la imagen de la máscara a un array de numpy
|
| 219 |
+
mask_array = np.array(mask_image)
|
| 220 |
+
|
| 221 |
+
# Encuentra los píxeles blancos
|
| 222 |
+
y, x = np.where(mask_array > 0)
|
| 223 |
+
|
| 224 |
+
# Calcula el cuadro delimitador de los píxeles blancos
|
| 225 |
+
x_min, y_min, width, height = cv2.boundingRect(np.array(list(zip(x, y))))
|
| 226 |
+
|
| 227 |
+
|
| 228 |
+
# Crea un objeto ImageDraw para dibujar en la imagen original
|
| 229 |
+
draw = ImageDraw.Draw(original_image)
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
# Dibuja el cuadro delimitador en la imagen original
|
| 233 |
+
draw.rectangle([(x_min, y_min), (x_min + width, y_min + height)], outline=(0, 255, 0), width=2)
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
color = generate_random_color()
|
| 237 |
+
|
| 238 |
+
color_mask = ImageOps.colorize(mask_image, black="black", white=color)
|
| 239 |
+
color_mask.putalpha(mask_image)
|
| 240 |
+
|
| 241 |
+
overlay = Image.alpha_composite(overlay, color_mask)
|
| 242 |
+
|
| 243 |
+
|
| 244 |
+
# Calcula el centroide de la mascara
|
| 245 |
+
|
| 246 |
+
x, y = np.where(np.array(mask_image) > 0)
|
| 247 |
+
centroid_x = x.mean()
|
| 248 |
+
centroid_y = y.mean()
|
| 249 |
+
|
| 250 |
+
# Imprime la etiqueta y la puntuación en la capa de texto
|
| 251 |
+
|
| 252 |
+
font_size = 30
|
| 253 |
+
draw = ImageDraw.Draw(text_layer)
|
| 254 |
+
font_path = "/System/Library/Fonts/Arial.ttf" # Path to Arial font on macOS
|
| 255 |
+
font = ImageFont.truetype(font_path, font_size)
|
| 256 |
+
label = segment['label']
|
| 257 |
+
score = segment['score']
|
| 258 |
+
text =f"{label}: {score}"
|
| 259 |
+
|
| 260 |
+
# Estima el tamaño del texto hard rockandroll way
|
| 261 |
+
|
| 262 |
+
text_width = 500
|
| 263 |
+
text_height = 100
|
| 264 |
+
|
| 265 |
+
|
| 266 |
+
# Asegúrate de que las coordenadas del texto están dentro de los límites de la imagen
|
| 267 |
+
text_x = max(0, min(centroid_x - text_width / 2, original_image.size[0] - text_width))
|
| 268 |
+
text_y = max(0, min(centroid_y - text_height / 2, original_image.size[1] - text_height))
|
| 269 |
+
# Asegúrate de que las coordenadas del texto están dentro de los límites de la imagen
|
| 270 |
+
text_x = max(0, min(centroid_x, original_image.size[0] - text_width))
|
| 271 |
+
text_y = max(0, min(centroid_y, original_image.size[1] - text_height))
|
| 272 |
+
|
| 273 |
+
|
| 274 |
+
# Calcula las coordenadas del texto
|
| 275 |
+
text_x = centroid_x - text_width / 2
|
| 276 |
+
text_y = centroid_y - text_height / 2
|
| 277 |
+
|
| 278 |
+
|
| 279 |
+
# Asegúrate de que las coordenadas del texto están dentro de los límites de la imagen
|
| 280 |
+
text_x = max(0, min(text_x, original_image.size[0] - text_width))
|
| 281 |
+
text_y = max(0, min(text_y, original_image.size[1] - text_height))
|
| 282 |
+
|
| 283 |
+
|
| 284 |
+
draw.text((centroid_x - text_width / 2, centroid_y - text_height / 2), text, fill=(255, 255, 255, 255), font=font)
|
| 285 |
+
|
| 286 |
+
#draw.text((text_x, text_y), text, fill=(255, 255, 255, 255), font=font)
|
| 287 |
+
|
| 288 |
+
# Ajusta la transparencia de la capa de superposición
|
| 289 |
+
print(original_image.size)
|
| 290 |
+
print(overlay.size)
|
| 291 |
+
overlay = Image.blend(original_image, overlay, transparency)
|
| 292 |
+
|
| 293 |
+
# Combina la capa de superposición con la capa de texto
|
| 294 |
+
|
| 295 |
+
final_image = Image.alpha_composite(overlay, text_layer)
|
| 296 |
+
|
| 297 |
+
#final_image = print_text_on_image_centered(final_image, 'SEGMENTING OK', 'green')
|
| 298 |
+
|
| 299 |
+
return final_image
|
| 300 |
+
|
| 301 |
+
def generate_random_color():
|
| 302 |
+
return (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
|
| 303 |
+
|
| 304 |
+
|
| 305 |
+
def segment_and_overlay_results(image_path, api_token, model):
|
| 306 |
+
#segments = segment_image_from_image(image)
|
| 307 |
+
#final_image = overlay_masks_on_image(image, segments)
|
| 308 |
+
#return final_image
|
| 309 |
+
processed_image = None # Initialize processed_image
|
| 310 |
+
segments = []
|
| 311 |
+
#image_type = None
|
| 312 |
+
#if isinstance(image_path, str):
|
| 313 |
+
# image_type = 'FILE'
|
| 314 |
+
# image = cv2.imread('cats.jpg')
|
| 315 |
+
#elif isinstance(image_path, np.ndarray):
|
| 316 |
+
# image_type = 'NUMPY ARRAY'
|
| 317 |
+
#else:
|
| 318 |
+
# raise ValueError("The image is neither a Image nor a local file.")
|
| 319 |
+
|
| 320 |
+
#ic(image_type)
|
| 321 |
+
image = transform_image_to_numpy_array(image_path)
|
| 322 |
+
# imprime tres primeros pixeles
|
| 323 |
+
print(type(image))
|
| 324 |
+
ic(image[0, 0:3])
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
|
| 328 |
+
|
| 329 |
+
try:
|
| 330 |
+
#segments = segment_image_from_image(image)
|
| 331 |
+
#processed_image = overlay_masks_on_image(image, segments)
|
| 332 |
+
|
| 333 |
+
# debug image contents
|
| 334 |
+
|
| 335 |
+
#if os.path.isfile(image):
|
| 336 |
+
# ic ("--- image is a file ---")
|
| 337 |
+
# image = Image.open(image)
|
| 338 |
+
# if image is None:
|
| 339 |
+
# ic("image is None")
|
| 340 |
+
# return None, []
|
| 341 |
+
|
| 342 |
+
ic("--- calling segment_image_from_path ---")
|
| 343 |
+
segments = segment_image_from_numpy(image)
|
| 344 |
+
#if image_type == 'FILE':
|
| 345 |
+
# segments = segment_image_from_path(image_path)
|
| 346 |
+
#if image_type == 'NUMPY ARRAY':
|
| 347 |
+
# segments = segment_image_from_image(image_path)
|
| 348 |
+
|
| 349 |
+
ic("--- printing segments ---")
|
| 350 |
+
for segment in segments:
|
| 351 |
+
ic(segment['label'] ,segment['score'])
|
| 352 |
+
processed_image = print_text_on_image_centered(
|
| 353 |
+
create_background_image(500, 500, "white"),
|
| 354 |
+
'SEGMENTING OK',
|
| 355 |
+
'green'
|
| 356 |
+
)
|
| 357 |
+
ic("--- calling overlay_masks_on_image ---")
|
| 358 |
+
processed_image = overlay_masks_on_image(image, segments)
|
| 359 |
+
except Exception as e:
|
| 360 |
+
print("EXCEPTION")
|
| 361 |
+
ic(e)
|
| 362 |
+
print(traceback.format_exc())
|
| 363 |
+
processed_image = print_text_on_image_centered(
|
| 364 |
+
create_background_image(500, 500, "white"),
|
| 365 |
+
e,
|
| 366 |
+
'green'
|
| 367 |
+
)
|
| 368 |
+
segments = []
|
| 369 |
+
return processed_image, segments
|
| 370 |
+
finally:
|
| 371 |
+
return processed_image, segments
|