initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dogs_emotion_model_weights.h5 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,63 @@
+import os 
+import numpy as np
+from timeit import default_timer as timer
+import cv2 as cv
+import gradio as gr
+from model_instance_function import get_pretrained_dog_emotion_classifier
+
+
+# normalize function
+def image_preprocessing(img):
+  img = np.array(img)
+  img = cv.resize(img,(224,224))
+  img = img.reshape(1,224,224,3)
+  return img / 255.0
+
+# instance the model
+model = get_pretrained_dog_emotion_classifier()
+
+# gradio predict function
+def predict(img):
+
+  # class to map the indices to the classes
+  class_2_index = {0: 'happy', 1: 'sad'}
+
+  # measure execution time
+  start_time = timer()
+
+  # preprocess the image
+  img = image_preprocessing(img)
+
+  # make a prediction (prob of sad dog)
+  pred_probability = model.predict(img)[0]
+
+  # convert to an index
+  pred_index = 1 if pred_probability > 0.5 else 0
+
+  # label 
+  pred_label = class_2_index[pred_index]
+
+  end_time = timer()
+  total_time = end_time - start_time
+
+  return pred_probability, pred_label,round(total_time,5)
+
+
+title = "Dog Emotions Vision Classifier"
+description = "A vision classifier that distinguishes between sad and happy dogs."
+article = "The model was trained in the [Dogs Emotions Dataset](https://huggingface.co/datasets/Q-b1t/Dogs_Emotions_Dataset) using the pretrained convolutional blocks of the VGG16 architecture and a custom classifier."
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+demo = gr.Interface(
+    fn = predict,
+    inputs = gr.Image(type = "pil"),
+    outputs = [gr.Number(label = "Probability of a sad dog"),gr.Textbox(max_lines = 2,label = "Most likely class"),gr.Number(label = "Prediction time (s)")],
+    examples = example_list,
+    title = title,
+    description = description,
+    article = article
+)
+
+demo.launch()
+

dogs_emotion_model_weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a371a36b8d1a9fec0cefe589899e8b26b1e5fd93a958a33b0c61f1752616a24c
+size 125312320

model_instance_function.py

@@ -0,0 +1,39 @@
+from tensorflow.keras.models import Model,Sequential
+from tensorflow.keras.layers import Dense, Flatten, Dropout
+from tensorflow.keras.applications import VGG16
+from tensorflow.keras.regularizers import L2
+
+def get_pretrained_dog_emotion_classifier(weights_path = "dogs_emotion_model_weights.h5"):
+  # images input shape
+  MODEL_INPUT_SHAPE = (224,224,3)
+
+  # instance the pretrained convolutional blocks
+  pretrained_vgg_model = VGG16(include_top = False, input_shape = MODEL_INPUT_SHAPE)
+
+  # freeze the first four pretrained layer
+  target_freeze_blocks = ["block1","block2","block3","block4"]
+  for layer in pretrained_vgg_model.layers:
+    if layer.name.split("_")[0] in target_freeze_blocks:
+      layer.trainable = False
+
+  # create the model's classifier
+  classifier = Sequential(
+      [
+          Flatten(),
+          Dense(32,activation = "relu",name = "classifier_dense1"),
+          Dropout(0.2,name = "classifier_dropout1"),
+          Dense(64,activation = "relu",kernel_regularizer = L2(),name = "classifier_dense2"),
+          Dense(64,activation = "relu",name = "classifier_dense3"),
+          Dropout(0.2,name = "classifier_dropout2"),
+          Dense(1,activation = "sigmoid",name = "classifier_dense4")
+      ],name = "classifier"
+  )
+
+  # connect the two models
+  output = classifier(pretrained_vgg_model.layers[-1].output)
+  model = Model(inputs = pretrained_vgg_model.layers[0].input,outputs = output)
+
+  # load the model_weights  
+  model.load_weights(weights_path)
+
+  return model

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow==2.12.0
+gradio==3.31.0
+numpy==1.22.4
+opencv-python==4.7.0.68