Create app.py

app.py

@@ -0,0 +1,140 @@
+from huggingface_hub import from_pretrained_keras
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+import tensorflow_hub as hub
+import tensorflow_text as text
+from tensorflow import keras
+import gradio as gr
+
+
+def make_bert_preprocessing_model(sentence_features, seq_length=128):
+    """Returns Model mapping string features to BERT inputs.
+
+      Args:
+        sentence_features: A list with the names of string-valued features.
+        seq_length: An integer that defines the sequence length of BERT inputs.
+
+      Returns:
+        A Keras Model that can be called on a list or dict of string Tensors
+        (with the order or names, resp., given by sentence_features) and
+        returns a dict of tensors for input to BERT.
+    """
+    
+    input_segments = [
+        tf.keras.layers.Input(shape=(), dtype=tf.string, name=ft)
+        for ft in sentence_features
+    ]
+    
+    # tokenize the text to word pieces
+    bert_preprocess = hub.load(bert_preprocess_path)
+    tokenizer = hub.KerasLayer(bert_preprocess.tokenize,
+                              name="tokenizer")
+    
+    segments = [tokenizer(s) for s in input_segments]
+    
+    truncated_segments = segments
+    
+    packer = hub.KerasLayer(bert_preprocess.bert_pack_inputs,
+                           arguments=dict(seq_length=seq_length),
+                           name="packer")
+    model_inputs = packer(truncated_segments)
+    return keras.Model(input_segments, model_inputs)
+
+
+def preprocess_image(image_path, resize):
+    extension = tf.strings.split(image_path)[-1]
+    
+    image = tf.io.read_file(image_path)
+    if extension == b"jpg":
+        image = tf.image.decode_jpeg(image, 3)
+    else:
+        image = tf.image.decode_png(image, 3)
+        
+    image = tf.image.resize(image, resize)
+    return image
+
+def preprocess_text(text_1, text_2):
+    
+    text_1 = tf.convert_to_tensor([text_1])
+    text_2 = tf.convert_to_tensor([text_2])
+    
+    output = bert_preprocess_model([text_1, text_2])
+    
+    output = {feature: tf.squeeze(output[feature]) for feature in bert_input_features}
+    
+    return output
+
+def preprocess_text_and_image(sample, resize):
+    
+    image_1 = preprocess_image(sample['image_1_path'], resize)
+    image_2 = preprocess_image(sample['image_2_path'], resize)
+    
+    text = preprocess_text(sample['text_1'], sample['text_2'])
+    
+    return {"image_1": image_1, "image_2": image_2, "text": text}
+
+
+def classify_info(image_1, text_1, image_2, text_2):
+
+    sample = dict()
+    sample['image_1_path'] = image_1
+    sample['image_2_path'] = image_2
+    sample['text_1'] = text_1
+    sample['text_2'] = text_2
+
+    dataframe = pd.DataFrame(sample, index=[0])
+
+    ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), [0]))
+    ds = ds.map(lambda x, y: (preprocess_text_and_image(x, resize), y)).cache()
+    batch_size = 1
+    auto = tf.data.AUTOTUNE
+    ds = ds.batch(batch_size).prefetch(auto)
+    output = model.predict(ds)
+
+    outputs = dict()
+    
+    outputs[labels[0]] = float(output[0][0])
+    outputs[labels[1]] = float(output[0][1])
+    outputs[labels[2]] = float(output[0][2])
+    #label = np.argmax(output)
+    return outputs #labels[label]
+
+
+model = from_pretrained_keras("keras-io/multimodal-entailment")
+resize = (128, 128)
+bert_input_features = ["input_word_ids", "input_type_ids", "input_mask"]
+bert_model_path = ("https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-2_H-256_A-4/1")
+bert_preprocess_path = "https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3"
+bert_preprocess_model = make_bert_preprocessing_model(['text_1', 'text_2'])
+
+labels = {0: "Contradictory", 1: "Implies", 2: "No Entailment"}
+
+block = gr.Blocks()
+
+examples = [['examples/image_1.png', '#IndiaFightsCorona:\n\nNearly 4.5 million beneficiaries vaccinated against #COVID19 in 19 days.\n\nIndia is the fastest country to cross landmark of vaccinating 4 million beneficiaries in merely 18 days.\n\n#StaySafe #IndiaWillWin #Unite2FightCorona https://t.co/beGDQfd06S', 'examples/image_2.jpg', '#IndiaFightsCorona:\n\nIndia has become the fastest nation to reach 4 million #COVID19 vaccinations ; it took only 18 days to administer the first 4 million #vaccines\n\n:@MoHFW_INDIA Secretary\n\n#StaySafe #IndiaWillWin #Unite2FightCorona https://t.co/9GENQlqtn3']]
+
+
+with block:
+  gr.Markdown("Multimodal Entailment")
+  with gr.Tab("Hypothesis"):
+      with gr.Row():  
+        gr.Markdown("Upload hypothesis image:")
+        image_1 = gr.inputs.Image(type="filepath")
+        text_1 = gr.inputs.Textbox(lines=5)
+        
+  with gr.Tab("Premise"):
+      with gr.Row(): 
+        gr.Markdown("Upload premise image:")
+        image_2 = gr.inputs.Image(type="filepath")
+        text_2 = gr.inputs.Textbox(lines=5)
+
+          xray_results = gr.outputs.JSON()
+      xray_run = gr.Button("Run")
+      xray_run.click(xray_model, inputs=[disease, xray_scan], outputs=xray_results)
+
+  run = gr.Button("Run")
+  label = gr.outputs.Label()
+  run.click(model, inputs=[image_1, text_1, image_2, text_2], outputs=label)
+
+block.launch()