Update app.py

app.py

@@ -1,28 +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 
-
-def greet(name):
-    return "Hello " + name + "!!"
-
-#iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-#iface.launch()
-
+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
 
 
 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)
@@ -38,34 +33,62 @@ def load_image_into_numpy_array(path):
 
 def load_model():
     download_dir = snapshot_download(REPO_ID)
-    saved_model_dir = os.path.join(download_dir, "saved_model.pb")
+    saved_model_dir = os.path.join(download_dir, "saved_model")
     detection_model = tf.saved_model.load(saved_model_dir)
     return detection_model
 
+def load_model2():
+    wget.download("https://nyp-aicourse.s3-ap-southeast-1.amazonaws.com/pretrained-models/balloon_model.tar.gz")
+    tarfile.open("balloon_model.tar.gz").extractall()
+    model_dir = 'saved_model'    
+    detection_model = tf.saved_model.load(str(model_dir))
+    return detection_model    
+
 
 def predict(pilimg):
 
     image_np = pil_image_as_numpy_array(pilimg)
     return predict2(image_np)
 
+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],
+        (result['detection_classes'][0] + label_id_offset).astype(int),
+        result['detection_scores'][0],
+        category_index,
+        use_normalized_coordinates=True,
+        max_boxes_to_draw=300,
+        min_score_thresh=0.50,
+        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 = 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')
 
-REPO_ID = "23A066X/23A066X_model"
 gr.Interface(fn=predict,
-             inputs=[gr.Image(type="pil",label="Input Image")],
-             outputs=gr.Image(type="pil",label="Output Image"), 
-             title="Cauliflower and Beetroot Detection",
-             description="Model: ssd_resnet50_v1_fpn_640x640_coco17_tpu-8",
-             theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky")
+             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)
 
-
-
-
-
-
-