app.py

# MegaDetector v5 and DLC Demo
import gradio as gr
import torch
import torchvision
import numpy as np
from PIL import Image

#script load
import json
import os
import numpy as np
import tensorflow.compat.v1 as tf 
tf.disable_v2_behavior()
from dlclive import DLCLive, Processor
from numpy import savetxt

# Load MegaDetector v5a model
model = torch.hub.load('ultralytics/yolov5', 'custom', "model_weights/md_v5a.0.0.pt")

def yolo(im, size=640):
    g = (size / max(im.size))  # gain
    im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize
    
    model = torch.hub.load('ultralytics/yolov5', 'custom', "model_weights/md_v5a.0.0.pt")
    
    results = model(im)  # inference
    results.render()  # updates results.imgs with boxes and labels
    return Image.fromarray(results.imgs[0])


def dlclive_pose(model, crop_np, crop, fname, index,dlc_proc):
    model = torch.hub.load('ultralytics/yolov5', 'custom', "model_weights/md_v5a.0.0.pt")
    
    dlc_live = DLCLive(model, processor=dlc_proc) 
    dlc_live.init_inference(crop_np)
    keypts = dlc_live.get_pose(crop_np) 
    savetxt(str(fname)+ '_' + str(index) + '.csv' , keypts, delimiter=',')
    xpose = []
    ypose = []
    for key in keypts[:,2]:
       # if key > 0.05: # which value do we need here?
            i = np.where(keypts[:,2]==key)
            xpose.append(keypts[i,0])
            ypose.append(keypts[i,1])
    plt.imshow(crop)
    plt.scatter(xpose[:], ypose[:], 40, color='cyan')
    plt.savefig(str(fname)+ '_' + str(index) + '.png')
    plt.show()
    plt.clf()
    
 dlc_proc = Processor()
    
#Layouts and descriptions
title = "MegaDetector and DeepLabcutLive"
description = "Interact with MegaDetector and DeeplabCutLive for pose estimation"
article = "<p style='text-align: center'>This app uses MegaDetector YOLOv5x6 model that was trained to detect animals, humans, and vehicles in camera trap images; find out more about the project on <a href='https://github.com/microsoft/CameraTraps'>GitHub</a>. We have also integrated DeepLabCut Live for pose estimation <a href='https://github.com/DeepLabCut/DeepLabCut-live'></a>.</p>"

# input image and output image 
inputs = gr.inputs.Image(type="pil", label="Input Image")
outputs = gr.outputs.Image(type="pil", label="Output Image")

#data images stored
examples = [['data/owl.jpg'], ['data/snake.jpg'],['data/beluga.jpg'],['data/rhino.jpg']]
gr.Interface(yolo, inputs, outputs, title=title, description=description, article=article, examples=examples, theme="huggingface").launch(enable_queue=True)