Update app.py

app.py

@@ -4,8 +4,17 @@ from transformers import pipeline, DetrForObjectDetection, DetrConfig, DetrImage
 import numpy as np
 import cv2
 from PIL import Image
+import warnings
+import logging
+# To suppress all warnings entries
+warnings.filterwarnings('ignore')
+
+# To ignore specific loggings from the Transformers library
+logging.getLogger("transformers").setLevel(logging.ERROR)
+
 def model_is_panoptic(model_name):
     return "panoptic" in model_name
+
 def load_model(model_name, threshold):
     config = DetrConfig.from_pretrained(model_name, threshold=threshold)
     model = DetrForObjectDetection.from_pretrained(model_name, config=config)
@@ -13,6 +22,7 @@ def load_model(model_name, threshold):
     return pipeline(task='object-detection', model=model, image_processor=image_processor)
 # Initial model with default threshold
 od_pipe = load_model("facebook/detr-resnet-101", 0.25)
+
 def draw_detections(image, detections, model_name):
     np_image = np.array(image)
     np_image = cv2.cvtColor(np_image, cv2.COLOR_RGB2BGR)
@@ -38,6 +48,7 @@ def draw_detections(image, detections, model_name):
     final_image = cv2.cvtColor(np_image, cv2.COLOR_BGR2RGB)
     final_pil_image = Image.fromarray(final_image)
     return final_pil_image
+    
 def get_pipeline_prediction(model_name, threshold, pil_image):
     global od_pipe
     od_pipe = load_model(model_name, threshold)
@@ -66,4 +77,5 @@ with gr.Blocks() as demo:
             with gr.Tab("Description"):
                 description_output = gr.Textbox()
     run_button.click(get_pipeline_prediction, inputs=[model_dropdown, threshold_slider, inp_image], outputs=[output_image, output_data, description_output])
+    
 demo.launch()