Add application file and models

app.py

@@ -0,0 +1,98 @@
+import gradio as gr
+import pandas as pd
+import tensorflow as tf
+from keras.models import load_model
+import numpy as np
+import PIL
+from PIL import Image, ImageOps
+import cv2
+
+
+
+def num_to_label(num):
+    alphabets = "ABCDEFGHIJKLMNOPQRSTUVWXYZ-' "  # The set of valid characters
+    max_str_len = 24                             # Maximum length of input labels
+    num_of_characters = len(alphabets) + 1       # Number of unique characters, plus 1 for CTC pseudo-blank
+    num_of_timestamps = 64                       # Maximum length of predicted labels
+    ret = ""  # Initialize an empty string to store the label
+    for ch in num:  # Iterate over each character index in the input list
+        if ch == -1:  # Check for the CTC Blank (a special case)
+            break
+        else:
+            ret += alphabets[ch]  # Append the character from 'alphabets' based on the index
+    return ret
+
+
+# Loading different models
+mnist_cnn_model = load_model('./models/mnist_cnn_model.h5')
+mnist_mcdnn_model = load_model('./models/mnist_mcdnn_model.h5')
+
+
+# Data Preprocessing
+def pre_process(image, model_name):
+    img = image.convert("L")
+    
+    # Select model based on the dropdown selection
+    if model_name == "cnn_model_mnist":
+        model = mnist_cnn_model
+        img = img.resize((28, 28))
+        img = np.array(img) / 255.0
+        final_img = np.expand_dims(img, axis=0)  # Add batch dimension
+        pred = model.predict(final_img)
+        result = np.argmax(pred)
+        return str(result)
+    elif model_name == "mcdnn_model_mnist":
+        model = mnist_mcdnn_model
+        img = img.resize((28, 28))
+        img = np.array(img) / 255.0
+        final_img = np.expand_dims(img, axis=0)  # Add batch dimension
+        pred = model.predict(final_img)
+        result = np.argmax(pred)
+        return str(result)
+    elif model_name == "cnn_model_handwritten_text":
+        model = mnist_mcdnn_model
+        img_array = np.array(img)
+        if len(img_array.shape) > 2:
+            img_array = np.mean(img_array, axis=-1, dtype=np.uint8)
+        (h, w) = img_array.shape
+        final_img = np.ones([64, 256])*255
+        if h > 64:
+            img_array = img_array[:64, :]
+        if w > 256:
+            img_array = img_array[:, :256]
+        final_img[:h, :w] = img_array
+        final_img = cv2.rotate(final_img, cv2.ROTATE_90_CLOCKWISE)
+        final_img = final_img / 255.0
+        pred = model.predict(final_img.reshape(1, 256, 64, 1))
+        num_to_label(pred)
+    else:
+        return "Invalid model selection"
+
+# Defining model options for dropdown
+model_options = ["cnn_model_mnist", "mcdnn_model_mnist", "cnn_model_handwritten_text"]
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        gr.Label("ScriptSense", container=False)
+
+    with gr.Row():
+        with gr.Column():
+            image_file = gr.inputs.Image(type="pil", label="Upload an image")
+            model_select = gr.components.Dropdown(choices=model_options, label="Select Model")
+
+    with gr.Row():
+        predict_btn = gr.Button(value="Predict")
+
+    with gr.Row():
+        Answer = gr.Label("👋 Hello, Let us predict the Result 💁‍♂️", container=False)
+
+    predict_btn.click(
+        pre_process,
+        inputs=[
+            image_file, model_select
+        ],
+        outputs=[Answer],
+    )
+
+demo.launch()

models/mnist_cnn_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7357478eb9b9dcabce4a39e1ac1100658ecb84f2fe9ed1a0f41d07cfa2041bf
+size 642592

models/mnist_mcdnn_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7357478eb9b9dcabce4a39e1ac1100658ecb84f2fe9ed1a0f41d07cfa2041bf
+size 642592