app.py

#!/usr/bin/env python
# coding: utf-8

# In[1]:


#export
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam, Adamax
from tensorflow.keras.metrics import categorical_crossentropy
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Activation, Dropout, BatchNormalization
from tensorflow.keras import regularizers
from keras.callbacks import EarlyStopping, LearningRateScheduler
import numpy as np
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.efficientnet import preprocess_input
import gradio as gr
# In[2]:


# Create Model Structure
class_labels = ['Angry', 'Other', 'Sad', 'Happy']


img_size = (224, 224)
channels = 3
img_shape = (img_size[0], img_size[1], channels)
class_count = len(class_labels) # to define number of classes in dense layer

# create pre-trained model (you can built on pretrained model such as :  efficientnet, VGG , Resnet )
# we will use efficientnetb3 from EfficientNet family.
base_model = tf.keras.applications.efficientnet.EfficientNetB5(include_top= False, weights= "imagenet", input_shape= img_shape, pooling= 'max')
base_model.trainable = False

model = Sequential([
    base_model,
    BatchNormalization(axis= -1, momentum= 0.99, epsilon= 0.001),
    Dense(256, activation='relu'),
    Dense(128, kernel_regularizer= regularizers.l2(l= 0.016), activity_regularizer= regularizers.l1(0.006),
                bias_regularizer= regularizers.l1(0.006), activation= 'relu'),
    Dropout(rate= 0.45, seed= 123),
    Dense(class_count, activation= 'softmax')
])

model.trainable = False

# model.compile(Adamax(learning_rate= 0.001), loss= 'categorical_crossentropy', metrics= ['accuracy'])

model.summary()

# In[6]:


from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.efficientnet import preprocess_input
import matplotlib.pyplot as plt

class_labels = ['Angry', 'Other', 'Sad', 'Happy']
model.load_weights('my_model_weights.h5')


def predict_and_display(img_array):
    
    # img = image.load_img(image_path, target_size=(224, 224))
    # img_array = image.img_to_array(img)
    # print(imimg_arrayg)
    img_array = np.expand_dims(img_array, axis=0)
    img_array = preprocess_input(img_array)

    prediction = model.predict(img_array)
    predicted_class_index = np.argmax(prediction)
    
    # class_indices = train_gen.class_indices
    # class_labels = list(class_indices.keys())
    predicted_class_label = class_labels[predicted_class_index]
    
    # plt.imshow(img)
    # plt.axis('off')
    # if predicted_class_label == 'Other':
    #     plt.title(f"The pet is normal")
    # else:
    #     plt.title(f"The Pet is {predicted_class_label}")
    # plt.show()
    return f"This pet is {predicted_class_label}"

    
# In[11]:

# In[ ]:

iface = gr.Interface(fn=predict_and_display, 
                     inputs=gr.Image(shape=(224, 224)), 
                     outputs="label",
                     title="Pet Emotion Detection",
                     description="Fine tune EfficientNet on Pet's emotion datasets",
                     examples=[["examples/happy_cat.jpeg"], ["examples/happy_dog.jpeg"], ["examples/cats.jpg"]]
                     )
iface.launch()

# %%