Upload 3 files

Nutrient-Model (2).h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2ad242e6c6fa31b44c6ece988f11bd18677feb17e23d226db8ffe747835c9f
+size 516595296

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+# Load the model
+model = tf.keras.models.load_model('Nutrient-Model.h5')
+
+# Define the class names
+class_names = ['Magnesium','Nitrogen','Potassium','Phosphorus','Sulfur']
+
+# Function to classify the image
+def classify_image(image):
+    # Convert the numpy array to a PIL Image object
+    pil_image = Image.fromarray(np.uint8(image)).convert('RGB')
+
+    # Resize the image
+    pil_image = pil_image.resize((224, 224))
+
+    # Convert the PIL Image object to a numpy array
+    image_array = np.array(pil_image)
+
+    # Normalize the image
+    normalized_image_array = (image_array.astype(np.float32) / 255.0)
+
+    # Reshape the image
+    data = normalized_image_array.reshape((1, 224, 224, 3))
+
+    # Make the prediction
+    prediction = model.predict(data)[0]
+
+    # Get the predicted class name
+    predicted_class = class_names[np.argmax(prediction)]
+
+    # Get the confidence score for the predicted class
+    confidence_score = np.max(prediction)
+
+    # Return the predicted class and confidence score
+    return f"{predicted_class} ({confidence_score*100:.2f}%)"
+
+# Define the Gradio interface
+inputs = gr.inputs.Image()
+outputs = gr.outputs.Textbox()
+interface = gr.Interface(fn=classify_image, inputs=inputs, outputs=outputs, title="Image Classification", description="Classify an image into one of six classes: Phosphorus, Magnesium, Nitrogen,Potassium, Calcium, Sulfur.")
+
+# Launch the interface
+interface.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio==3.28.1
+numpy==1.23.4
+Pillow==9.5.0
+Requests==2.29.0
+tensorflow==2.10.0
+tensorflow_gpu==2.10.1