sup

README.md

@@ -4,7 +4,7 @@ emoji: 📷
 colorFrom: gray
 colorTo: yellow
 sdk: gradio
-sdk_version: 4.12.0
+sdk_version: 5.1.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -34,6 +34,26 @@ SVM_PATH_RBF = "models/fashion_mnist_svm_model_rbf.pkl"
 svm_clf_rbf = joblib.load(SVM_PATH_RBF)
 
 
+# Required for the classifier
+from sklearn.linear_model import LogisticRegression
+
+LR_PATH = "models/fashion_mnist_lr_model.pkl"
+lr_clf = joblib.load(LR_PATH)
+
+# Required for the classifier
+
+from sklearn.neighbors import KNeighborsClassifier
+
+KNN_PATH = "models/fashion_mnist_knn_model.pkl"
+knn_clf = joblib.load(KNN_PATH)
+
+# Required for the classifier
+from xgboost import XGBClassifier
+
+XGB_PATH = "models/fashion_mnist_xgb_model.pkl"
+xgb_clf = joblib.load(XGB_PATH)
+
+
 LABELS = [
     "T-shirt/top",
     "Trouser",
@@ -56,40 +76,76 @@ def classify(img: str):
     img = np.array(img).reshape(-1, 1, 28, 28)
     img = torch.from_numpy(img).float()
 
+    # CNN Classifier
     cnn_output = simple_classifier(img)
     cnn_output = torch.nn.functional.softmax(cnn_output, dim=1)
     cnn_output_pred = torch.argmax(cnn_output)
     cnn_output_label = LABELS[cnn_output_pred.item()]
-    cnn_output_str = f"Simple CNN: {cnn_output_label} with {round(torch.max(cnn_output).item()*100, 2)}% confidence"
+    cnn_confidence = round(torch.max(cnn_output).item() * 100, 2)
+    cnn_output_str = (
+        f"{'CNN:':<35} {cnn_output_label:<15} with {cnn_confidence:.2f}% confidence"
+    )
 
+    # Feed Forward Classifier
     feed_forward_output = feed_forward_classifier(img)
     feed_forward_output = torch.nn.functional.softmax(feed_forward_output, dim=1)
     feed_forward_output_pred = torch.argmax(feed_forward_output)
     feed_forward_output_label = LABELS[feed_forward_output_pred.item()]
-    feed_forward_output_str = f"Feed Forward: {feed_forward_output_label} with {round(torch.max(feed_forward_output).item()*100, 2)}% confidence"
+    feed_forward_confidence = round(torch.max(feed_forward_output).item() * 100, 2)
+    feed_forward_output_str = f"{'Feed Forward:':<35} {feed_forward_output_label:<15} with {feed_forward_confidence:.2f}% confidence"
+
+    # XGBoost Classifier
+    xgb_output = xgb_clf.predict(img.reshape(1, -1))
+    xgb_output_label = LABELS[xgb_output[0]]
+    xgb_confidence = round(
+        float(np.max(xgb_clf.predict_proba(img.reshape(1, -1))[0])) * 100, 2
+    )
+    xgb_output_str = (
+        f"{'XGBoost:':<35} {xgb_output_label:<15} with {xgb_confidence:.2f}% confidence"
+    )
 
+    # Random Forest Classifier
     rf_output = rf_clf.predict(img.reshape(1, -1))
     rf_output_label = LABELS[rf_output[0]]
-    rf_output_str = f"Random Forest: {rf_output_label}"
+    rf_output_str = f"{'Random Forest:':<35} {rf_output_label:<15}"
 
+    # SVM with Linear Kernel Classifier
     svm_output = svm_clf.predict(img.reshape(1, -1))
     svm_output_label = LABELS[svm_output[0]]
-    svm_output_str = f"SVM with linear kernel: {svm_output_label}"
+    svm_output_str = f"{'SVM with Linear kernel:':<35} {svm_output_label:<15}"
 
+    # SVM with RBF Kernel Classifier
     svm_output_rbf = svm_clf_rbf.predict(img.reshape(1, -1))
     svm_output_label_rbf = LABELS[svm_output_rbf[0]]
-    svm_output_str_rbf = f"SVM with RBF kernel: {svm_output_label_rbf}"
+    svm_output_str_rbf = f"{'SVM with RBF kernel:':<35} {svm_output_label_rbf:<15}"
+
+    # Logistic Regression Classifier
+    lr_output = lr_clf.predict(img.reshape(1, -1))
+    lr_output_label = LABELS[lr_output[0]]
+    lr_output_str = f"{'Logistic Regression:':<35} {lr_output_label:<15}"
 
+    # KNN Classifier
+    knn_output = knn_clf.predict(img.reshape(1, -1))
+    knn_output_label = LABELS[knn_output[0]]
+    knn_output_str = f"{'KNN:':<35} {knn_output_label:<15}"
+
+    # Combine output
     output = (
         cnn_output_str
         + "\n"
         + feed_forward_output_str
         + "\n"
+        + xgb_output_str
+        + "\n"
         + rf_output_str
         + "\n"
         + svm_output_str
         + "\n"
         + svm_output_str_rbf
+        + "\n"
+        + lr_output_str
+        + "\n"
+        + knn_output_str
     )
     return output
 
@@ -106,11 +162,11 @@ random.shuffle(examples)
 iface = gr.Interface(
     fn=classify,
     title="Fashion MNIST Classifier - TAECAC @ FEUP",
-    description="Use an image to classify using the different Fashion MNIST model.",
+    description="Simple Proof of Concept.",
     inputs=gr.Image(label="Image", type="filepath"),
     outputs=gr.Textbox(label="Classification output"),
     examples=examples,
-    examples_per_page=100,  
+    examples_per_page=100,
     theme=gr.themes.Soft(
         primary_hue=gr.themes.colors.indigo,
         secondary_hue=gr.themes.colors.gray,

models/fashion_mnist_knn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb976fbeb5cd6b96fa2e352cb76abc759fdb28bfa6a6e734154776dffda86b1d
+size 188640868

models/fashion_mnist_lr_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39ebb79140b7fad5f4b6aa4c84faa063299b9f99f9c0fb201ddcdb615e81432
+size 32319

models/fashion_mnist_xgb_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949b5f3cdf0ce1b64b609a2f70ce56f39dcdb6a8005a7475ddf96e45308d965c
+size 9915808

requirements.txt

@@ -5,4 +5,5 @@ watchdog
 scikit-learn
 opencv-python
 isort==5.13.2
-black==24.8.0
+black==24.8.0
+xgboost