Add application file

app.py

@@ -1,29 +1,27 @@
+import os
 import gradio as gr
-import subprocess
+from fastai.learner import load_learner
+from fastai.vision.all import *
 
 # Install fastai
 subprocess.run(["pip", "install", "fastai"])
 
-
-from fastai.vision.all import *
-
-im =PILImage.create('Sphynx.jpg')
-im.thumbnail((192,192))
-im
-# Construct the absolute path to the file
+# Construct the absolute path to the large data file
 # Get the absolute path to the current script's directory
-from fastai.learner import load_learner
-
-file_path = os.path.join('/Users', 'scaspary', 'Desktop', 'fastai', 'large', 'sphynx.pkl')
-learn= load_learner(file_path)
+current_directory = os.path.abspath(os.path.dirname(__file__))
+parent_directory = os.path.abspath(os.path.join(current_directory, os.pardir))
+file_path = os.path.join(parent_directory, 'large', 'sphynx.pkl')
 
+# Load the learner using the absolute file path
+learn = load_learner(file_path)
 
 categories = ('cat', 'sphinx cat')
+
 def classify_image(im):
-    pred,idx, probs = learn.predict(im)
-    return dict(zip(categories, map(float,probs)))
+    pred, idx, probs = learn.predict(im)
+    return dict(zip(categories, map(float, probs)))
 
-    # Define the input component
+# Define the input component
 image = "image"
 
 # Define the output component
@@ -31,4 +29,4 @@ label_output = "label"
 
 # Create the Gradio interface
 intf = gr.Interface(fn=classify_image, inputs=image, outputs=label_output, examples=["Sphynx.jpg", "cat.jpg"])
-intf.launch(share=False)
+intf.launch(share=False)