app.py

# -*- coding: utf-8 -*-
"""Deploy OceanApp demo.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1j0T8gdLIa0X8fzkIgFpXDoU27BF49RUz?usp=sharing

![   ](https://i.pinimg.com/564x/3e/b8/f7/3eb8f7c348dffd7b3dffcafe81fbf2a6.jpg)

# Modelo

YOLO es una familia de modelos de detección de objetos a escala compuesta entrenados en COCO dataset, e incluye una funcionalidad simple para Test Time Augmentation (TTA), model ensembling, hyperparameter evolution, and export to ONNX, CoreML and TFLite.


## Gradio Inferencia

![](https://i.ibb.co/982NS6m/header.png)

Este Notebook se acelera opcionalmente con un entorno de ejecución de GPU


----------------------------------------------------------------------

 YOLOv5 Gradio demo

*Author: Ultralytics LLC and Gradio*

# Código
"""

#!pip install -qr https://raw.githubusercontent.com/ultralytics/yolov5/master/requirements.txt gradio # install dependencies

import gradio as gr
import pandas as pd
import torch
import logging
import json
from PIL import Image

# Images
torch.hub.download_url_to_file('https://i.pinimg.com/564x/18/0b/00/180b00e454362ff5caabe87d9a763a6f.jpg', 'ejemplo1.jpg')
torch.hub.download_url_to_file('https://i.pinimg.com/564x/3b/2f/d4/3b2fd4b6881b64429f208c5f32e5e4be.jpg', 'ejemplo2.jpg')

# Model
#model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # force_reload=True to update

#model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt')  # local model  o google colab
model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt', force_reload=True, autoshape=True)  # local model  o google colab
#model = torch.hub.load('path/to/yolov5', 'custom', path='/content/yolov56.pt', source='local')  # local repo

def listJSON(a,b,c,d,e,f):
      #for n in 
      if d =='Pelicano\nSp':
        d = 'Pelicano'
      if f!='Pelicano':
        strlista = '"detail":[{"quantity":"'+str(c)+'","description":"'+str(d)+'"}]'
      else:
        strlista = '"detail":[{"quantity":"'+str(c)+'","description":"'+str(d)+'"},{"quantity":"'+str(e)+'","description":"'+str(f)+'"}]'
      strlist = '{"image":"'+str(a)+'","size":"'+str(b)+'",'+strlista+'}'
      json_string = json.loads(strlist)
      return json_string

def arrayLista(a,b,c,d):
      strlist =[]
      strlist2 =[]
      strlist.append(a)
      if b =='Pelicano\nSp':
        strlist.append('Pelicano')
      else:
        strlist.append(b)
      if d=='Pelicano':
        strlist2.append(c)
        strlist2.append(d)
      strlista = [strlist,strlist2]
      df = pd.DataFrame(strlista,columns=['Cantidad','Especie'])
      return df

def yolo(size, iou, conf, im):
    try:
        '''Wrapper fn for gradio'''
        g = (int(size) / max(im.size))  # gain
        im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize

        model.iou = iou
        
        model.conf = conf

        results2 = model(im)  # inference
        results2.render()  # updates results.imgs with boxes and labels
        results3 = str(results2)
        lista = listJSON(results3[0:9], results3[11:18] ,results3[19:20],results3[21:32], results3[35:36], results3[37:45])
        lista2 = arrayLista(results3[19:20],results3[21:32], results3[35:36], results3[37:45])
        return Image.fromarray(results2.ims[0]), lista2, lista
    except Exception as e:
        logging.error(e, exc_info=True)

#------------ Interface-------------

in1 = gr.inputs.Radio(['640', '1280'], label="Tamaño de la imagen", default='640', type='value')
in2 = gr.inputs.Slider(minimum=0, maximum=1, step=0.05, default=0.45, label='NMS IoU threshold')
in3 = gr.inputs.Slider(minimum=0, maximum=1, step=0.05, default=0.50, label='Umbral o  threshold')
in4 = gr.inputs.Image(type='pil', label="Original Image")

out2 = gr.outputs.Image(type="pil", label="Identificación con Yolov5")
out3 = gr.outputs.Dataframe(label="Descripción", headers=['Cantidad','Especie'])  
out4 = gr.outputs.JSON(label="JSON")
#-------------- Text-----
title = 'OceanApp'
description = """
<p>
<center>
<p>Sistema para el reconocimiento de las especies en la pesca acompañante de cerco, utilizando redes neuronales convolucionales para una empresa del sector pesquero en los puertos de callao y paracas.</p>
<p><b>Nota</b>: Este modelo solo acepta imagenes de <b>Lobos marinos</b> o <b>Pelicanos</b> proporcionados por empresas peruanas.</p>
<center>
<img src="https://i.pinimg.com/564x/3e/b8/f7/3eb8f7c348dffd7b3dffcafe81fbf2a6.jpg" alt="logo" width="250"/>
</center>
</center>
</p>
"""
article ="<p style='text-align: center'><a href='' target='_blank'>Para mas info, clik para ir al white paper</a></p><p style='text-align: center'><a href='https://colab.research.google.com/drive/1j0T8gdLIa0X8fzkIgFpXDoU27BF49RUz?usp=sharing' target='_blank'>Google Colab Demo</a></p><p style='text-align: center'><a href='https://github.com/MssLune/OceanApp-Model' target='_blank'>Repo Github</a></p></center></p>"
          
examples = [['640',0.45, 0.75,'ejemplo1.jpg'], ['640',0.45, 0.75,'ejemplo2.jpg']]

iface = gr.Interface(yolo, inputs=[in1, in2, in3, in4], outputs=[out2,out3,out4], title=title, description=description, article=article, examples=examples,theme="huggingface", analytics_enabled=False).launch(
    debug=True)

iface.launch()

"""For YOLOv5 PyTorch Hub inference with **PIL**, **OpenCV**, **Numpy** or **PyTorch** inputs please see the full [YOLOv5 PyTorch Hub Tutorial](https://github.com/ultralytics/yolov5/issues/36).


## Citation

[![DOI](https://zenodo.org/badge/264818686.svg)](https://zenodo.org/badge/latestdoi/264818686)

"""