app.py

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  3 18:31:26 2022

@author: gabri
"""

import numpy as np
import tensorflow as tf
import gradio as gr
from huggingface_hub import from_pretrained_keras
import cv2
import requests
from PIL import Image
import matplotlib.cm as cm
# import matplotlib.pyplot as plt



models_links = {
    'xception':r'https://huggingface.co/gabri14el/grapevine_classification/resolve/main/experimentos/classificacao/Experimento%205/pesos.h5',
    'resnet':r'https://huggingface.co/gabri14el/grapevine_classification/resolve/main/experimentos/classificacao/Experimento%209/pesos.h5',
    'efficientnet':'https://huggingface.co/gabri14el/grapevine_classification/resolve/main/experimentos/classificacao/Experimento%2010/pesos.h5'}

model_weights = {
    }

model_last_convolutional_layer = {
    'xception':'block14_sepconv2_act',
    'resnet':'conv5_block3_3_conv',
    'efficientnet':'top_conv'}

classes = ['Códega', 'Moscatel Galego', 'Rabigato', 'Tinta Roriz', 'Tinto Cao', 'Touriga Nacional']
# functions for inference                   
target_size_dimension = 300

def define_model(model):
    weights = get_weights(model)
    if model == 'efficientnet':
        preprocessing_function=tf.keras.applications.efficientnet.preprocess_input
        model = tf.keras.applications.EfficientNetB3(
            include_top=False,
            input_shape= (target_size_dimension, target_size_dimension, 3),
            weights='imagenet',
            pooling='avg'
        )
    elif model == 'resnet':
        preprocessing_function=tf.keras.applications.resnet_v2.preprocess_input
        model = tf.keras.applications.resnet_v2.ResNet101V2(
            include_top=False,
            input_shape= (target_size_dimension, target_size_dimension, 3),
            weights='imagenet',
            pooling='avg'
        )
    else:
        preprocessing_function=tf.keras.applications.xception.preprocess_input
        model = tf.keras.applications.Xception(
            include_top=False,
            input_shape= (target_size_dimension, target_size_dimension, 3),
            weights='imagenet',
            pooling='avg'
        )
    
    x = tf.keras.layers.Dense(512, activation='relu')(model.output)
    x = tf.keras.layers.Dropout(0.25)(x)
    x = tf.keras.layers.Dense(512, activation='relu')(x)
    x = tf.keras.layers.Dropout(0.25)(x)
    output = tf.keras.layers.Dense(6, activation='softmax')(x)
    nmodel = tf.keras.models.Model(model.input, output)
    nmodel.load_weights(weights)
    return preprocessing_function, nmodel

def get_weights(model):
    if not model in model_weights: 
        r = requests.get(models_links[model], allow_redirects=True)
        open(model+'.h5', 'wb').write(r.content)
        model_weights[model] = model+'.h5'
    return model_weights[model]




def get_img_array(img_path, size, expand=True):
    # `img` is a PIL image of size 299x299
    img = tf.keras.preprocessing.image.load_img(img_path, target_size=size)
    # `array` is a float32 Numpy array of shape (299, 299, 3)
    array = tf.keras.preprocessing.image.img_to_array(img)
    # We add a dimension to transform our array into a "batch"
    # of size (1, 299, 299, 3)
    
    if expand:
      array = np.expand_dims(array, axis=0)
    return array


def make_gradcam_heatmap(img_array, grad_model, last_conv_layer_name, pred_index=None, tresh=0.1):
    # First, we create a model that maps the input image to the activations
    # of the last conv layer as well as the output predictions
    #grad_model = tf.keras.models.Model(
        #[model.inputs], [model.get_layer(last_conv_layer_name).output, model.output]
    #)

    # Then, we compute the gradient of the top predicted class for our input image
    # with respect to the activations of the last conv layer
    
    with tf.GradientTape() as tape:
        last_conv_layer_output, preds = grad_model(img_array)
        if pred_index is None:
            pred_index = tf.argmax(preds[0])
        class_channel = preds[:, pred_index]

    # This is the gradient of the output neuron (top predicted or chosen)
    # with regard to the output feature map of the last conv layer
    grads = tape.gradient(class_channel, last_conv_layer_output)

    # This is a vector where each entry is the mean intensity of the gradient
    # over a specific feature map channel
    pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))

    # We multiply each channel in the feature map array
    # by "how important this channel is" with regard to the top predicted class
    # then sum all the channels to obtain the heatmap class activation
    last_conv_layer_output = last_conv_layer_output[0]
    heatmap = last_conv_layer_output @ pooled_grads[..., tf.newaxis]
    heatmap = tf.squeeze(heatmap)

    # For visualization purpose, we will also normalize the heatmap between 0 & 1
    heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
    heatmap = heatmap.numpy()
    return heatmap

def save_and_display_gradcam(img, heatmap, cam_path="cam.jpg", alpha=0.4):

    # Rescale heatmap to a range 0-255
    heatmap = np.uint8(255 * heatmap)
    im = Image.fromarray(heatmap)
    im = im.resize((img.shape[1], img.shape[0]))
    
    im = np.asarray(im)
    im = np.where(im > 0, 1, im)

    # Use jet colormap to colorize heatmap
    jet = cm.get_cmap("jet")

    # Use RGB values of the colormap
    jet_colors = jet(np.arange(256))[:, :3]
    jet_heatmap = jet_colors[heatmap]

 

    # Create an image with RGB colorized heatmap
    jet_heatmap = tf.keras.preprocessing.image.array_to_img(jet_heatmap)
    jet_heatmap = jet_heatmap.resize((img.shape[1], img.shape[0]))
    jet_heatmap = tf.keras.preprocessing.image.img_to_array(jet_heatmap)

    # Superimpose the heatmap on original image
    superimposed_img = jet_heatmap * alpha + img
    superimposed_img = tf.keras.preprocessing.image.array_to_img(superimposed_img)

    # Save the superimposed image
    #superimposed_img.save(cam_path)

    # Display Grad CAM
    #display(Image(cam_path))
    return superimposed_img, im
        

def infer(model_name, input_image):
    print('#$$$$$$$$$$$$$$$$$$$$$$$$$ IN INFER $$$$$$$$$$$$$$$$$$$$$$$')
    print(model_name, type(input_image))
    preprocess, model = define_model(model_name)
    
    #img = get_img_array(input_image, (target_size_dimension, target_size_dimension))
    img_processed = preprocess(np.expand_dims(input_image, axis=0))
    
    predictions = model.predict(img_processed)
    predictions = np.squeeze(predictions)
    
    
    result = {}
    
    
    for i in range(len(classes)):
        result[classes[i]] = float(predictions[i])
    #predictions = np.argmax(predictions) # , axis=2
    #predicted_label = classes[predictions.item()]
    print(input_image.shape)
    model.layers[-1].activation = None
    grad_model = tf.keras.models.Model([model.inputs], [model.get_layer(model_last_convolutional_layer[model_name]).output, model.output])
    
    print(result)
    heatmap = make_gradcam_heatmap(img_processed, grad_model,model_last_convolutional_layer[model_name])
    heat, mask = save_and_display_gradcam(input_image, heatmap)
    
    return result, heat
    
    gr.outputs.Image()
# get the inputs
css = css = ".output-image, .input-image, .image-preview {height: 300px !important}"
inputs = [gr.Radio(["resnet", "efficientnet", "xception"], label='Choose a model'), gr.inputs.Image(shape=(target_size_dimension, target_size_dimension), label='Select an image')]
# the app outputs two segmented images
output = [gr.outputs.Label(label="Result"), gr.outputs.Image(type="numpy", label="Heatmap (Grad-CAM)")]
# it's good practice to pass examples, description and a title to guide users
examples = [["./content/examples/Frog.jpg"], ["./content/examples/Truck.jpg"]] 
title = "Grapevine image classification"
description = "Upload an image to classify it. The allowed classes are - Códega, Moscatel Galego, Rabigato, Tinta Roriz, Tinto Cao, Touriga Nacional <p><b>Space author: Gabriel Carneiro</b> <br><b> [email protected] </b> </p>"

gr_interface = gr.Interface(infer, inputs, output, allow_flagging=False, analytics_enabled=False, css=css, title=title, description=description).launch(enable_queue=True, debug=False)
#gr_interface.launch()