Added app.py file

app.py

@@ -0,0 +1,231 @@
+# -*- coding: utf-8 -*-
+"""mp_art_classification.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1mCMy50B9xHW2WdGNlxTq-wObAe-eMsQ5
+"""
+
+import os
+import shutil
+import math 
+import glob
+import json
+import pickle
+import requests
+import time
+import re
+import string
+from datetime import datetime
+
+import pandas as pd
+import numpy as np
+from PIL import Image
+
+import matplotlib.pyplot as plt
+
+import tensorflow as tf
+
+if 'workspace/semantic_search' in os.getcwd():
+    ROOT_FOLDER = os.path.join("./hf", "mp_art_classification")
+else:
+    ROOT_FOLDER = './'
+
+PRE_TRAINED_MODELS_FOLDER = os.path.join(ROOT_FOLDER, "pre_trained_models")
+TRAINED_WEIGHTS_FOLDER = os.path.join(ROOT_FOLDER, "trained_weights")
+
+def clean_directories():
+    shutil.rmtree(PRE_TRAINED_MODELS_FOLDER, ignore_errors=True)
+
+# clean_directories()  
+
+def create_directories():
+    if not os.path.exists(PRE_TRAINED_MODELS_FOLDER):
+        os.mkdir(PRE_TRAINED_MODELS_FOLDER)
+
+create_directories()
+
+from transformers import CLIPTokenizer, CLIPImageProcessor, TFCLIPTextModel, TFCLIPVisionModel
+
+clip_model_id = "openai/clip-vit-large-patch14"
+
+vision_model = TFCLIPVisionModel.from_pretrained(
+    clip_model_id, 
+    cache_dir=PRE_TRAINED_MODELS_FOLDER)
+vision_processor = CLIPImageProcessor.from_pretrained(clip_model_id)
+
+base_learning_rate = 0.0001
+steps_per_execution = 200
+
+def create_classification_model():
+    
+    # Preprocess images
+    inputs = tf.keras.Input(shape=(3, 224, 224))
+    rescaling_layer = tf.keras.layers.Rescaling(1.0/255, offset=0.0)
+    rescaled_input = rescaling_layer(inputs)
+    # processed_inputs = vision_processor(images=[inputs], return_tensors="tf")
+    # print(inputs)
+    
+    vision_model.trainable=False
+    # vision_model.trainable = True
+    # # Fine-tune from this layer onwards
+    # fine_tune_at = 100
+
+    # # Freeze all the layers before the `fine_tune_at` layer
+    # for layer in base_model.layers[:fine_tune_at]:
+    # layer.trainable = False
+    base_model_output = vision_model(rescaled_input)
+    
+    current_layer = base_model_output.pooler_output
+    hidden_layers_nodes = [64]
+    for node_count in hidden_layers_nodes:
+        hidden_layer = tf.keras.layers.Dense(node_count, activation='relu')
+        dropout_layer = tf.keras.layers.Dropout(.2, input_shape=(2,))
+        # hidden_layer.trainable = False
+        current_layer = hidden_layer(dropout_layer(current_layer))
+    
+    prediction_layer = tf.keras.layers.Dense(9, activation='softmax')
+    # prediction_layer.trainable = False
+    outputs = prediction_layer(current_layer)
+    model = tf.keras.Model(inputs, outputs)
+
+        
+    model.compile(
+        # Used leagcy optimizer due to tf 2.11 release issues with MACOS 
+        # optimizer=tf.keras.optimizers.Adam(learning_rate=base_learning_rate),
+        optimizer=tf.keras.optimizers.legacy.Adam(learning_rate=base_learning_rate),
+        loss=tf.keras.losses.SparseCategoricalCrossentropy(),
+        metrics=['accuracy'],
+        steps_per_execution=steps_per_execution
+    )
+
+    return model
+
+
+
+model = create_classification_model()
+model.summary()
+
+latest_weights = tf.train.latest_checkpoint(TRAINED_WEIGHTS_FOLDER)
+model.load_weights(latest_weights)
+
+# image_path = tf.constant('./hf/mp_image_search/examples/e1.jpeg')
+# image = tf.io.read_file("/Users/skoneru/workspace/semantic_search/hf/mp_image_search/examples/e1.jpeg")
+# print(image)
+# decoded_image = tf.io.decode_image(
+#     contents = image,
+#     channels = 3,
+#     expand_animations = False
+# )
+# print(decoded_image.shape)
+# resized_image = tf.image.resize_with_pad(
+#     image = decoded_image, 
+#     target_height = 224,
+#     target_width = 224,
+# )
+# print(resized_image.shape)
+# # constant_new = tf.constant(
+# #     resized_image, dtype=tf.float32, shape=(224,224,3), name='input_image'
+# # )
+# transposed_image = tf.transpose(
+#     resized_image)
+# print(transposed_image.shape)
+# # constant = tf.constant(
+# #     transposed_image, value_index=(3,224,224)
+# # )
+# # constant_new = tf.constant(
+# #     transposed_image, dtype=tf.float32, shape=(3,224,224), name='input_image'
+# # )
+# ndarray = tf.make_ndarray(
+#      tf.Variable(transposed_image, shape=(3,224,224))
+# )
+# # variable = tf.Variable(constant_new)
+# # print(constant_new)     
+# # print(inputs)
+
+# image_path = './hf/mp_image_search/examples/e1.jpeg'
+# img = Image.open(image_path).convert('RGB')
+# desired_size =224
+# old_size = img.size  # old_size[0] is in (width, height) format
+# ratio = float(desired_size)/max(old_size)
+# new_size = tuple([int(x*ratio) for x in old_size])
+
+# img.thumbnail((desired_size, desired_size), Image.ANTIALIAS)
+
+# new_im = Image.new("RGB", (desired_size, desired_size))
+# new_im.paste(img, ((desired_size-new_size[0])//2,
+#                     (desired_size-new_size[1])//2))
+
+# # new_im.show()
+# np_array = np.array(img)
+# print(np_array.shape)
+# transposed_np_array = np.transpose(np_array)
+# print(transposed_np_array.shape)
+# images_list = []
+# images_list.append(transposed_np_array)
+# np_input = np.asarray(images_list)
+# print(np_input.shape)
+# result = model.predict(np_input)
+# print(result.flatten())
+
+genre_classes_path = os.path.join(ROOT_FOLDER,'genre_class.txt')
+# TSV headers [id, class]
+genre_classes_df = pd.read_csv(genre_classes_path, sep = ' ',  header=None)
+# print(genre_train_df.iloc[:,1])
+genre_classes = []
+for index, row in genre_classes_df.iterrows():
+    genre_classes.append(row[1])
+# print(genre_classes)
+
+import gradio as gr
+
+def process_image(input_image):
+    desired_size =224
+    old_size = input_image.size  # old_size[0] is in (width, height) format
+    ratio = float(desired_size)/max(old_size)
+    new_size = tuple([int(x*ratio) for x in old_size])
+
+    input_image.thumbnail((desired_size, desired_size), Image.ANTIALIAS)
+
+    new_im = Image.new("RGB", (desired_size, desired_size))
+    new_im.paste(input_image, ((desired_size-new_size[0])//2,
+                        (desired_size-new_size[1])//2))
+
+    # new_im.show()
+    np_array = np.array(input_image)
+    # print(np_array.shape)
+    transposed_np_array = np.transpose(np_array)
+    # print(transposed_np_array.shape)
+    images_list = []
+    images_list.append(transposed_np_array)
+    np_input = np.asarray(images_list)
+    # print(np_input.shape)
+    return model.predict(np_input).flatten()
+
+def predict(input_image):
+    # print(input_image)
+    # img = Image.create(input_image)
+    pil_image_object = Image.fromarray(input_image)
+    probs = process_image(pil_image_object)
+    return {genre_classes[i]: float(probs[i]) for i in range(len(genre_classes)-1)}
+
+image_path_prefx = os.path.join(ROOT_FOLDER,'examples')
+examples = [f"{image_path_prefx}/e{n}.jpeg" for n in range(4)]
+interpretation='shap'
+title = "MP Art Classifier"
+description = "<b>Classifies Art into 10 Genres</b>"
+theme = 'grass'
+
+gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(shape=((512,512))),
+    outputs=gr.outputs.Label(num_top_classes=5),
+    title = title,
+    examples =  examples,
+    theme = theme,
+    interpretation = interpretation,
+    description = description
+).launch(share=True,  debug=True)
+
+clean_directories()