Update

app.py

@@ -1,5 +1,9 @@
 import gradio as gr
 import predict as predict
+from googletrans import Translator, constants
+from pprint import pprint
+
+translator = Translator()
 
 
 def upload_file(files):
@@ -29,11 +33,19 @@ def process_file(webcam_filepath, upload_filepath):
         return result
 
 
+def generate_description(request: gr.Request):
+    translation = translator.translate(
+        "SqueezeNet-Based Deep Learning for Early Detection of Movement Disorders via Handwriting Assessment",
+        dest=str(request.request.headers["Accept-Language"].split(",")[0].lower()[0:2]),
+    )
+    return translation.text
+
+
 demo = gr.Interface(
     theme="gradio/soft",
     fn=process_file,
     title="HANDETECT",
-    description="An innovative AI-powered system that facilitates early detection and monitoring of movement disorders through handwriting assessment",
+    description=generate_description,
     inputs=[
         gr.components.Image(type="filepath", label="Choose Image", source="upload"),
     ],

augment.py

@@ -46,6 +46,7 @@ for task in ["1"]:
             p.random_brightness(probability=0.8, min_factor=0.5, max_factor=1.5)
             p.random_contrast(probability=0.8, min_factor=0.5, max_factor=1.5)
             p.random_color(probability=0.8, min_factor=0.5, max_factor=1.5)
+            p.rotate_random_90(probability=0.8)
             # Generate 100 - total of original images so that the total number of images in each class is 100
             p.sample(100 - len(p.augmentor_images))
             # Move the folder to data/train/Task 1/augmented

configs.py

@@ -14,11 +14,11 @@ from torchvision.models import squeezenet1_0
 
 # Constants
 RANDOM_SEED = 123
-BATCH_SIZE = 32
+BATCH_SIZE = 16
 NUM_EPOCHS = 40
-LEARNING_RATE = 0.005873024218838728
+LEARNING_RATE = 5.488903014780378e-05
 STEP_SIZE = 10
-GAMMA = 0.9
+GAMMA = 0.3
 DEVICE = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 NUM_PRINT = 100
 TASK = 1
@@ -37,7 +37,7 @@ CLASSES = [
     "Huntington Disease",
     "Parkinson Disease",
 ]
-MODEL_SAVE_PATH = "output/checkpoints/model.pth"
+MODEL_SAVE_PATH = r"output/checkpoints/model.pth"
 
 
 class SqueezeNet1_0WithDropout(nn.Module):

train.py

@@ -155,9 +155,6 @@ def main_training_loop():
             )
             break
 
-    # Save the model
-    MODEL_SAVE_PATH = "output/checkpoints/model.pth"
-
     # Ensure the parent directory exists
     os.makedirs(os.path.dirname(MODEL_SAVE_PATH), exist_ok=True)
     torch.save(model.state_dict(), MODEL_SAVE_PATH)