Update app.py

app.py

@@ -1,30 +1,23 @@
-import gradio as gr
 import matplotlib.pyplot as plt
 import numpy as np
+from six import BytesIO
+from PIL import Image
+import tensorflow as tf
+from object_detection.utils import label_map_util
+from object_detection.utils import visualization_utils as viz_utils
+from object_detection.utils import ops as utils_op
 import tarfile
 import wget 
+import gradio as gr
 from huggingface_hub import snapshot_download
 import os 
-from object_detection.utils import label_map_util
-from object_detection.utils import visualization_utils as viz_utils
-from object_detection.utils import ops as utils_op
-from six import BytesIO
-from PIL import Image
-import tensorflow as tf
-from huggingface_hub import from_pretrained_keras
-
-model = from_pretrained_keras("23A066X/23A066X_model")
-
-
-
 
 PATH_TO_LABELS = 'label_map.pbtxt'   
 category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)
 
 
-
 def pil_image_as_numpy_array(pilimg):
-    
+
     img_array = tf.keras.utils.img_to_array(pilimg)
     img_array = np.expand_dims(img_array, axis=0)
     return img_array
@@ -38,6 +31,7 @@ def load_image_into_numpy_array(path):
 
 def load_model():
     download_dir = snapshot_download(REPO_ID)
+    # download_dir = os.path.join(download_dir, "saved_model")
     saved_model_dir = os.path.join(download_dir, "saved_model")
     detection_model = tf.saved_model.load(saved_model_dir)
     return detection_model
@@ -49,6 +43,9 @@ def load_model2():
     detection_model = tf.saved_model.load(str(model_dir))
     return detection_model    
 
+# samples_folder = 'test_samples
+# image_path = 'test_samples/sample_balloon.jpeg
+# 
 
 def predict(pilimg):
 
@@ -58,10 +55,13 @@ def predict(pilimg):
 def predict2(image_np):
 
     results = detection_model(image_np)
+
     # different object detection models have additional results
     result = {key:value.numpy() for key,value in results.items()}
+    
     label_id_offset = 0
     image_np_with_detections = image_np.copy()
+
     viz_utils.visualize_boxes_and_labels_on_image_array(
         image_np_with_detections[0],
         result['detection_boxes'][0],
@@ -69,29 +69,32 @@ def predict2(image_np):
         result['detection_scores'][0],
         category_index,
         use_normalized_coordinates=True,
-        max_boxes_to_draw=300,
-        min_score_thresh=0.50,
+        max_boxes_to_draw=200,
+        min_score_thresh=0.60,
         agnostic_mode=False,
         line_thickness=3)
+
     result_pil_img = tf.keras.utils.array_to_img(image_np_with_detections[0])
     
     return result_pil_img
 
 
-REPO_ID = "23A066X/23A066X_model"
-detection_model = from_pretrained_keras("23A066X/23A066X_model")
-# detection_model = load_model()
-
+REPO_ID = "A23066X/A23066X_model"
+detection_model = load_model()
 # pil_image = Image.open(image_path)
 # image_arr = pil_image_as_numpy_array(pil_image)
 
 # predicted_img = predict(image_arr)
 # predicted_img.save('predicted.jpg')
 
-gr.Interface(fn=predict,
-             inputs=gr.Image(type="pil"),
-             outputs=gr.Image(type="pil"),
-             title="Cauliflower and Beetroot Detection.",
-             description="Using Model :  ssd_resnet50_v1_fpn_640x640_coco17_tpu-8",
-             ).launch(share=True)
+title = "Cauliflower and Beetroot Detection"
+description = "Using ssd_resnet50_v1_fpn_640x640_coco17_tpu-8"
+
 
+gr.Interface(fn=predict,
+             title = title,
+             description = description,
+             css=css_code,
+             inputs=gr.Image(type="pil", height=309),
+             outputs=gr.Image(type="pil", height=350)
+             ).launch(share=True)