Upload 10 files

app.py

@@ -0,0 +1,54 @@
+import gradio as gr
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+import joblib
+from sklearn.ensemble import AdaBoostClassifier
+from sklearn.ensemble import GradientBoostingClassifier
+from sklearn.neighbors import KNeighborsClassifier
+import numpy as np 
+
+import gradio as gr
+# define image data type
+input_image = gr.inputs.Image(label = "Input Image")
+select_algorithm = gr.inputs.Dropdown(choices=["Decision Tree", "Random Forest", "AdaBoost", "Gradient Tree Boosting", "KNN"], label = "Select Algorithm")
+
+out_classify = gr.outputs.Textbox(label = "Predict Class")
+out_prob = gr.outputs.Textbox(label = "Predict Probability")
+
+"""
+gradio interface
+"""
+def predict_interface(input_image, select_algorithm):
+  """
+  evaluate model
+  """
+  # Convert image to NumPy array
+  print(input_image.shape)
+  input_image2 = input_image.mean(axis=2)
+  print(input_image2.shape)
+  img_array = input_image2.reshape(1, 28*28)
+
+
+  model_dict = {"Decision Tree":"best_dt_model.joblib",
+                "Random Forest":"best_rf_model.joblib",
+                "AdaBoost":"best_ada_model.joblib",
+                "Gradient Tree Boosting":"best_gbc_model.joblib",
+                "KNN":"best_knn_model.joblib"}
+  # Reload the best trained model from disk using joblib
+  loaded_model = joblib.load(model_dict[select_algorithm])
+
+  # Use the reloaded model to make predictions on the validation data
+  out_classify = loaded_model.predict(img_array)
+  out_prob = loaded_model.predict_proba(img_array)
+  class_names = ["T-shirt/top", "Trouser", "Pullover", "Dress", "Coat",
+"Sandal", "Shirt", "Sneaker", "Bag", "Ankle boot"]
+  out_prob2 = '\n'.join([f"{name}\t\t\t{np.round(pro,2)}" for name, pro in zip(class_names, out_prob[0])])
+  return class_names[out_classify[0]], out_prob2 
+
+gr.Interface(fn=predict_interface, inputs=[input_image, select_algorithm], 
+             outputs=[out_classify, out_prob],
+             examples=[["fashion_1.png", "Random Forest"], 
+                       ["fashion_2.png", "Random Forest"], 
+                       ["fashion_3.png", "Random Forest"]]
+             ).launch(debug=True) 
+  

best_ada_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a05a9e23f943f0a12bbf6890f7ef8781d8498da0f17fee0dee4d381c981efec
+size 131340

best_dt_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed195418d7fd560f6877e84b497e419ce85e6990ee34a338bf1e0ae96902ea1
+size 32329

best_gbc_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a36fc928b73970b618ddc709d8a3c6b6d425a886abee322b9775cf27a1425b4
+size 1541752

best_knn_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d89e9199b92c58534594d33c8db5f397f221c74a13462f9c2028e5c87f27d1
+size 792724

best_rf_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2754f6aa4dcf53e98f9948d8d9b53b1e2ec4f7670866e8d9b3c3919b64617ac1
+size 2477821

requirements (1).txt

@@ -0,0 +1,4 @@
+gradio==3.18.0
+joblib==1.1.1
+scikit-learn==1.2.2
+