Upload 6 files

Densenet.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96edb21323de75eadd8b4c10a8900cde72e51fed49fd854338ee14ad53b2f3fc
+size 29224776

app.py

@@ -0,0 +1,89 @@
+import tensorflow as tf 
+from tensorflow.keras.models import Model
+from keras.models import load_model
+import gradio as gr
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
+from tensorflow.keras.applications.densenet import preprocess_input, decode_predictions
+import numpy as np 
+from scipy import ndimage
+from skimage import exposure
+from skimage.transform import resize
+from PIL import Image
+import matplotlib.pyplot as plt
+import cv2
+model = load_model('Densenet.h5')
+model.load_weights("pretrained_model.h5")
+layer_name = 'conv5_block16_concat'
+class_names = ['Cardiomegaly', 'Emphysema', 'Effusion', 'Hernia', 'Infiltration', 'Mass', 'Nodule', 'Atelectasis', 'Pneumothorax', 'Pleural_Thickening', 'Pneumonia', 'Fibrosis', 'Edema', 'Consolidation', 'No Finding']
+def get_gradcam(model, img, layer_name):
+    
+    img_array = img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = preprocess_input(img_array)
+    
+    grad_model = Model(inputs=model.inputs, outputs=[model.get_layer(layer_name).output, model.output])
+
+    with tf.GradientTape() as tape:
+        conv_outputs, predictions = grad_model(img_array)
+        class_idx = tf.argmax(predictions[0])
+
+    output = conv_outputs[0]
+    grads = tape.gradient(predictions, conv_outputs)[0]
+    guided_grads = tf.cast(output > 0, 'float32') * tf.cast(grads > 0, 'float32') * grads
+
+    weights = tf.reduce_mean(guided_grads, axis=(0, 1))
+    cam = tf.reduce_sum(tf.multiply(weights, output), axis=-1)
+    heatmap = np.maximum(cam, 0)
+    heatmap /= tf.reduce_max(heatmap)
+    heatmap_img = plt.cm.jet(heatmap)[..., :3]
+
+    # Load the original image
+    original_img = Image.fromarray(img)
+
+    # Resize the heatmap to match the original image size
+    heatmap_img = Image.fromarray((heatmap_img * 255).astype(np.uint8))
+    heatmap_img = heatmap_img.resize(original_img.size)
+
+    # Overlay the heatmap on the original image
+    overlay_img = Image.blend(original_img, heatmap_img, 0.5)
+
+    # Return the overlayed image
+    return overlay_img
+    
+def custom_decode_predictions(predictions, class_labels):
+    
+    decoded_predictions = []
+    for pred in predictions:
+        # Get indices of top predicted classes
+        top_indices = pred.argsort()[-4:][::-1]  # Change 5 to the number of top classes you want to retrieve
+        # Decode each top predicted class
+        decoded_pred = [(class_labels[i], pred[i]) for i in top_indices]
+        decoded_predictions.append(decoded_pred)
+    return decoded_predictions
+
+def classify_image(img):
+    img = cv2.resize(img, (540, 540), interpolation=cv2.INTER_AREA)
+    img_array = img_to_array(img)
+    #img_array = exposure.equalize_hist(img_array)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = preprocess_input(img_array)                         
+    
+
+
+    predictions1 = model.predict(img_array)
+    decoded_predictions = custom_decode_predictions(predictions1, class_names)
+    overlay_img = get_gradcam(model, img, layer_name)
+
+    # Return the decoded predictions and the overlayed image
+    return decoded_predictions, overlay_img
+# Gradio interface
+iface = gr.Interface(
+    fn=classify_image, 
+    inputs="image", 
+    outputs=["text", "image"],  # Add an "image" output for the overlayed image
+    title="Xray Classification - KIMS",
+    description="Classify cxr into 'Cardiomegaly', 'Emphysema', 'Effusion', 'Hernia', 'Infiltration', 'Mass', 'Nodule', 'Atelectasis', 'Pneumothorax', 'Pleural_Thickening', 'Pneumonia', 'Fibrosis', 'Edema', 'Consolidation', 'No Finding'. Built by Dr Sai Koundinya")
+
+
+# Launch the interface, 
+iface.launch( share=True)

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

pretrained_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065c434e7fddce4f8d8c6b5451a78a2de9e3975f67284acb62a4e5ae83f823e1
+size 29148608

requirements.txt

@@ -0,0 +1,10 @@
+transformers
+numpy
+tensorflow
+keras
+gradio==4.7.1
+pillow
+matplotlib
+scipy
+opencv-python
+scikit-image