added tensorflow ssd mobilenet v2 model for packet detection

trials/object detection tf.py

@@ -0,0 +1,126 @@
+# !pip install tensorflow
+# !pip install tensorflow_hub
+
+import tensorflow as tf
+import tensorflow_hub as hub
+import numpy as np
+from PIL import Image, ImageDraw, ImageFont, ImageOps
+import requests
+from io import BytesIO
+
+
+# Load the model from TF Hub
+detector = hub.load("https://tfhub.dev/google/openimages_v4/ssd/mobilenet_v2/1").signatures['default']
+
+# Classes you care about
+TARGET_CLASSES = set(["Food processor", "Fast food", "Food", "Seafood", "Snack"])
+
+
+
+def load_image_from_url(url, size=(640, 480)):
+    response = requests.get(url)
+    img = Image.open(BytesIO(response.content)).convert("RGB")
+    img = ImageOps.fit(img, size, Image.Resampling.LANCZOS)
+    return img
+
+
+
+
+def run_object_detection(image: Image.Image):
+    image_np = np.array(image)
+    # Convert to tensor without specifying dtype
+    input_tensor = tf.convert_to_tensor(image_np)[tf.newaxis, ...]
+    # Convert to float32 and normalize to [0,1]
+    input_tensor = tf.cast(input_tensor, tf.float32) / 255.0
+    results = detector(input_tensor)
+    results = {k: v.numpy() for k, v in results.items()}
+    return results, image_np
+
+def get_filtered_class_boxes(results):
+    # for same class, keep the one with the highest score
+    # and remove duplicates
+    boxes = []
+    classes = []
+    scores = []
+                    
+    for i in range(len(results["detection_scores"])):
+        class_name = results["detection_class_entities"][i].decode("utf-8")
+        box = results["detection_boxes"][i]
+        score = results["detection_scores"][i]
+        if class_name in TARGET_CLASSES:
+            if class_name not in classes:
+                boxes.append(box)
+                classes.append(class_name)
+                scores.append(score)
+            else:
+                index = classes.index(class_name)
+                if score > scores[index]:
+                    boxes[index] = box
+                    classes[index] = class_name
+                    scores[index] = score
+    return boxes, classes, scores
+
+
+
+
+def crop_and_save(image_np, boxes, class_names, scores, min_score=0.3):
+    cropped_images = []
+    for i in range(len(scores)):
+        if scores[i] > min_score:
+            ymin, xmin, ymax, xmax = boxes[i]
+            im_width, im_height = image_np.shape[1], image_np.shape[0]
+            (left, right, top, bottom) = (xmin * im_width, xmax * im_width,
+                                          ymin * im_height, ymax * im_height)
+            cropped_image = image_np[int(top):int(bottom), int(left):int(right)]
+            cropped_images.append((cropped_image, class_names[i], scores[i]))
+            # Save the cropped image
+            pil_image = Image.fromarray(cropped_image)
+            pil_image.save(f"output/{class_names[i]}_{scores[i]:.2f}.jpg")
+    return cropped_images
+
+def draw_boxes(image_np, boxes, class_names, scores, min_score=0.3):
+    image_pil = Image.fromarray(image_np)
+    draw = ImageDraw.Draw(image_pil)
+    font = ImageFont.load_default()
+
+    for i in range(len(scores)):
+        label = class_names[i]
+        print(label, scores[i])
+        if label in TARGET_CLASSES and scores[i] > min_score:
+            ymin, xmin, ymax, xmax = boxes[i]
+            im_width, im_height = image_pil.size
+            (left, right, top, bottom) = (xmin * im_width, xmax * im_width,
+                                          ymin * im_height, ymax * im_height)
+            draw.rectangle([left, top, right, bottom], outline="red", width=2)
+            draw.text((left, top), f"{label}: {scores[i]*100:.1f}%", fill="white", font=font)
+    return image_pil
+
+
+def detect_and_display(image):
+    results, image_np = run_object_detection(image)
+    
+    final_image = draw_boxes(image_np,
+                             results["detection_boxes"],
+                             results["detection_class_entities"],
+                             results["detection_scores"])
+    final_image.show()
+
+
+def detect_and_save(image):
+    results, image_np = run_object_detection(image)
+    boxes, class_names, scores = get_filtered_class_boxes(results)
+    cropped_images = crop_and_save(image_np, boxes, class_names, scores,0)
+    return cropped_images
+
+
+detect_and_display(
+    image = Image.open("bv.jpg").convert("RGB"))
+
+
+detect_and_save(
+    image = Image.open("bv.jpg").convert("RGB"))
+
+
+
+
+

trials/tf_object_Detection.ipynb

@@ -0,0 +1,458 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "51c8a899",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting tensorflow\n",
+      "  Using cached tensorflow-2.19.0-cp312-cp312-win_amd64.whl.metadata (4.1 kB)\n",
+      "Collecting absl-py>=1.0.0 (from tensorflow)\n",
+      "  Using cached absl_py-2.2.2-py3-none-any.whl.metadata (2.6 kB)\n",
+      "Collecting astunparse>=1.6.0 (from tensorflow)\n",
+      "  Using cached astunparse-1.6.3-py2.py3-none-any.whl.metadata (4.4 kB)\n",
+      "Collecting flatbuffers>=24.3.25 (from tensorflow)\n",
+      "  Downloading flatbuffers-25.2.10-py2.py3-none-any.whl.metadata (875 bytes)\n",
+      "Collecting gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 (from tensorflow)\n",
+      "  Using cached gast-0.6.0-py3-none-any.whl.metadata (1.3 kB)\n",
+      "Collecting google-pasta>=0.1.1 (from tensorflow)\n",
+      "  Using cached google_pasta-0.2.0-py3-none-any.whl.metadata (814 bytes)\n",
+      "Collecting libclang>=13.0.0 (from tensorflow)\n",
+      "  Using cached libclang-18.1.1-py2.py3-none-win_amd64.whl.metadata (5.3 kB)\n",
+      "Collecting opt-einsum>=2.3.2 (from tensorflow)\n",
+      "  Using cached opt_einsum-3.4.0-py3-none-any.whl.metadata (6.3 kB)\n",
+      "Requirement already satisfied: packaging in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (24.2)\n",
+      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.3 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (5.29.4)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (2.32.3)\n",
+      "Requirement already satisfied: setuptools in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (78.1.0)\n",
+      "Requirement already satisfied: six>=1.12.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (1.17.0)\n",
+      "Collecting termcolor>=1.1.0 (from tensorflow)\n",
+      "  Downloading termcolor-3.1.0-py3-none-any.whl.metadata (6.4 kB)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (4.13.1)\n",
+      "Collecting wrapt>=1.11.0 (from tensorflow)\n",
+      "  Using cached wrapt-1.17.2-cp312-cp312-win_amd64.whl.metadata (6.5 kB)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (1.71.0)\n",
+      "Collecting tensorboard~=2.19.0 (from tensorflow)\n",
+      "  Using cached tensorboard-2.19.0-py3-none-any.whl.metadata (1.8 kB)\n",
+      "Collecting keras>=3.5.0 (from tensorflow)\n",
+      "  Using cached keras-3.9.2-py3-none-any.whl.metadata (6.1 kB)\n",
+      "Requirement already satisfied: numpy<2.2.0,>=1.26.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow) (2.1.1)\n",
+      "Collecting h5py>=3.11.0 (from tensorflow)\n",
+      "  Using cached h5py-3.13.0-cp312-cp312-win_amd64.whl.metadata (2.5 kB)\n",
+      "Collecting ml-dtypes<1.0.0,>=0.5.1 (from tensorflow)\n",
+      "  Using cached ml_dtypes-0.5.1-cp312-cp312-win_amd64.whl.metadata (22 kB)\n",
+      "Collecting wheel<1.0,>=0.23.0 (from astunparse>=1.6.0->tensorflow)\n",
+      "  Using cached wheel-0.45.1-py3-none-any.whl.metadata (2.3 kB)\n",
+      "Collecting rich (from keras>=3.5.0->tensorflow)\n",
+      "  Downloading rich-14.0.0-py3-none-any.whl.metadata (18 kB)\n",
+      "Collecting namex (from keras>=3.5.0->tensorflow)\n",
+      "  Downloading namex-0.0.9-py3-none-any.whl.metadata (322 bytes)\n",
+      "Collecting optree (from keras>=3.5.0->tensorflow)\n",
+      "  Using cached optree-0.15.0-cp312-cp312-win_amd64.whl.metadata (49 kB)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (3.4.1)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (3.10)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2.3.0)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2025.1.31)\n",
+      "Collecting markdown>=2.6.8 (from tensorboard~=2.19.0->tensorflow)\n",
+      "  Using cached markdown-3.8-py3-none-any.whl.metadata (5.1 kB)\n",
+      "Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard~=2.19.0->tensorflow)\n",
+      "  Using cached tensorboard_data_server-0.7.2-py3-none-any.whl.metadata (1.1 kB)\n",
+      "Collecting werkzeug>=1.0.1 (from tensorboard~=2.19.0->tensorflow)\n",
+      "  Using cached werkzeug-3.1.3-py3-none-any.whl.metadata (3.7 kB)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard~=2.19.0->tensorflow) (3.0.2)\n",
+      "Collecting markdown-it-py>=2.2.0 (from rich->keras>=3.5.0->tensorflow)\n",
+      "  Using cached markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from rich->keras>=3.5.0->tensorflow) (2.19.1)\n",
+      "Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich->keras>=3.5.0->tensorflow)\n",
+      "  Using cached mdurl-0.1.2-py3-none-any.whl.metadata (1.6 kB)\n",
+      "Using cached tensorflow-2.19.0-cp312-cp312-win_amd64.whl (376.0 MB)\n",
+      "Using cached absl_py-2.2.2-py3-none-any.whl (135 kB)\n",
+      "Using cached astunparse-1.6.3-py2.py3-none-any.whl (12 kB)\n",
+      "Downloading flatbuffers-25.2.10-py2.py3-none-any.whl (30 kB)\n",
+      "Using cached gast-0.6.0-py3-none-any.whl (21 kB)\n",
+      "Using cached google_pasta-0.2.0-py3-none-any.whl (57 kB)\n",
+      "Using cached h5py-3.13.0-cp312-cp312-win_amd64.whl (3.0 MB)\n",
+      "Using cached keras-3.9.2-py3-none-any.whl (1.3 MB)\n",
+      "Using cached libclang-18.1.1-py2.py3-none-win_amd64.whl (26.4 MB)\n",
+      "Using cached ml_dtypes-0.5.1-cp312-cp312-win_amd64.whl (210 kB)\n",
+      "Using cached opt_einsum-3.4.0-py3-none-any.whl (71 kB)\n",
+      "Using cached tensorboard-2.19.0-py3-none-any.whl (5.5 MB)\n",
+      "Downloading termcolor-3.1.0-py3-none-any.whl (7.7 kB)\n",
+      "Using cached wrapt-1.17.2-cp312-cp312-win_amd64.whl (38 kB)\n",
+      "Using cached markdown-3.8-py3-none-any.whl (106 kB)\n",
+      "Using cached tensorboard_data_server-0.7.2-py3-none-any.whl (2.4 kB)\n",
+      "Using cached werkzeug-3.1.3-py3-none-any.whl (224 kB)\n",
+      "Using cached wheel-0.45.1-py3-none-any.whl (72 kB)\n",
+      "Downloading namex-0.0.9-py3-none-any.whl (5.8 kB)\n",
+      "Using cached optree-0.15.0-cp312-cp312-win_amd64.whl (307 kB)\n",
+      "Downloading rich-14.0.0-py3-none-any.whl (243 kB)\n",
+      "Using cached markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n",
+      "Using cached mdurl-0.1.2-py3-none-any.whl (10.0 kB)\n",
+      "Installing collected packages: namex, libclang, flatbuffers, wrapt, wheel, werkzeug, termcolor, tensorboard-data-server, optree, opt-einsum, ml-dtypes, mdurl, markdown, h5py, google-pasta, gast, absl-py, tensorboard, markdown-it-py, astunparse, rich, keras, tensorflow\n",
+      "Successfully installed absl-py-2.2.2 astunparse-1.6.3 flatbuffers-25.2.10 gast-0.6.0 google-pasta-0.2.0 h5py-3.13.0 keras-3.9.2 libclang-18.1.1 markdown-3.8 markdown-it-py-3.0.0 mdurl-0.1.2 ml-dtypes-0.5.1 namex-0.0.9 opt-einsum-3.4.0 optree-0.15.0 rich-14.0.0 tensorboard-2.19.0 tensorboard-data-server-0.7.2 tensorflow-2.19.0 termcolor-3.1.0 werkzeug-3.1.3 wheel-0.45.1 wrapt-1.17.2\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
+      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install tensorflow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "48087332",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting tensorflow_hub\n",
+      "  Downloading tensorflow_hub-0.16.1-py2.py3-none-any.whl.metadata (1.3 kB)\n",
+      "Requirement already satisfied: numpy>=1.12.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow_hub) (2.1.1)\n",
+      "Requirement already satisfied: protobuf>=3.19.6 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow_hub) (5.29.4)\n",
+      "Collecting tf-keras>=2.14.1 (from tensorflow_hub)\n",
+      "  Downloading tf_keras-2.19.0-py3-none-any.whl.metadata (1.8 kB)\n",
+      "Requirement already satisfied: tensorflow<2.20,>=2.19 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tf-keras>=2.14.1->tensorflow_hub) (2.19.0)\n",
+      "Requirement already satisfied: absl-py>=1.0.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (2.2.2)\n",
+      "Requirement already satisfied: astunparse>=1.6.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (1.6.3)\n",
+      "Requirement already satisfied: flatbuffers>=24.3.25 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (25.2.10)\n",
+      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.6.0)\n",
+      "Requirement already satisfied: google-pasta>=0.1.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.2.0)\n",
+      "Requirement already satisfied: libclang>=13.0.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (18.1.1)\n",
+      "Requirement already satisfied: opt-einsum>=2.3.2 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.4.0)\n",
+      "Requirement already satisfied: packaging in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (24.2)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (2.32.3)\n",
+      "Requirement already satisfied: setuptools in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (78.1.0)\n",
+      "Requirement already satisfied: six>=1.12.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (1.17.0)\n",
+      "Requirement already satisfied: termcolor>=1.1.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.1.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (4.13.1)\n",
+      "Requirement already satisfied: wrapt>=1.11.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (1.17.2)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (1.71.0)\n",
+      "Requirement already satisfied: tensorboard~=2.19.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (2.19.0)\n",
+      "Requirement already satisfied: keras>=3.5.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.9.2)\n",
+      "Requirement already satisfied: h5py>=3.11.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.13.0)\n",
+      "Requirement already satisfied: ml-dtypes<1.0.0,>=0.5.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.5.1)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from astunparse>=1.6.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.45.1)\n",
+      "Requirement already satisfied: rich in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from keras>=3.5.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (14.0.0)\n",
+      "Requirement already satisfied: namex in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from keras>=3.5.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.0.9)\n",
+      "Requirement already satisfied: optree in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from keras>=3.5.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.15.0)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.4.1)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.10)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (2.3.0)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (2025.1.31)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorboard~=2.19.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.8)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorboard~=2.19.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.7.2)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from tensorboard~=2.19.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.1.3)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard~=2.19.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.0.2)\n",
+      "Requirement already satisfied: markdown-it-py>=2.2.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from rich->keras>=3.5.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (3.0.0)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from rich->keras>=3.5.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (2.19.1)\n",
+      "Requirement already satisfied: mdurl~=0.1 in d:\\be project\\foodanalyzer-api\\venv\\lib\\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.5.0->tensorflow<2.20,>=2.19->tf-keras>=2.14.1->tensorflow_hub) (0.1.2)\n",
+      "Downloading tensorflow_hub-0.16.1-py2.py3-none-any.whl (30 kB)\n",
+      "Downloading tf_keras-2.19.0-py3-none-any.whl (1.7 MB)\n",
+      "   ---------------------------------------- 0.0/1.7 MB ? eta -:--:--\n",
+      "   ------------------------ --------------- 1.0/1.7 MB 6.3 MB/s eta 0:00:01\n",
+      "   ---------------------------------------- 1.7/1.7 MB 5.9 MB/s eta 0:00:00\n",
+      "Installing collected packages: tf-keras, tensorflow_hub\n",
+      "Successfully installed tensorflow_hub-0.16.1 tf-keras-2.19.0\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
+      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install tensorflow_hub"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c0b03c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf\n",
+    "import tensorflow_hub as hub\n",
+    "import numpy as np\n",
+    "from PIL import Image, ImageDraw, ImageFont, ImageOps\n",
+    "import requests\n",
+    "from io import BytesIO"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3a51cfb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load the model from TF Hub\n",
+    "detector = hub.load(\"https://tfhub.dev/google/openimages_v4/ssd/mobilenet_v2/1\").signatures['default']\n",
+    "\n",
+    "# Classes you care about\n",
+    "TARGET_CLASSES = set([\"Food processor\", \"Fast food\", \"Food\", \"Seafood\", \"Snack\"])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_image_from_url(url, size=(640, 480)):\n",
+    "    response = requests.get(url)\n",
+    "    img = Image.open(BytesIO(response.content)).convert(\"RGB\")\n",
+    "    img = ImageOps.fit(img, size, Image.Resampling.LANCZOS)\n",
+    "    return img\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "252c3890",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "def run_object_detection(image: Image.Image):\n",
+    "    image_np = np.array(image)\n",
+    "    # Convert to tensor without specifying dtype\n",
+    "    input_tensor = tf.convert_to_tensor(image_np)[tf.newaxis, ...]\n",
+    "    # Convert to float32 and normalize to [0,1]\n",
+    "    input_tensor = tf.cast(input_tensor, tf.float32) / 255.0\n",
+    "    results = detector(input_tensor)\n",
+    "    results = {k: v.numpy() for k, v in results.items()}\n",
+    "    return results, image_np\n",
+    "\n",
+    "def get_filtered_class_boxes(results):\n",
+    "    # for same class, keep the one with the highest score\n",
+    "    # and remove duplicates\n",
+    "    boxes = []\n",
+    "    classes = []\n",
+    "    scores = []\n",
+    "                    \n",
+    "    for i in range(len(results[\"detection_scores\"])):\n",
+    "        class_name = results[\"detection_class_entities\"][i].decode(\"utf-8\")\n",
+    "        box = results[\"detection_boxes\"][i]\n",
+    "        score = results[\"detection_scores\"][i]\n",
+    "        if class_name in TARGET_CLASSES:\n",
+    "            if class_name not in classes:\n",
+    "                boxes.append(box)\n",
+    "                classes.append(class_name)\n",
+    "                scores.append(score)\n",
+    "            else:\n",
+    "                index = classes.index(class_name)\n",
+    "                if score > scores[index]:\n",
+    "                    boxes[index] = box\n",
+    "                    classes[index] = class_name\n",
+    "                    scores[index] = score\n",
+    "    return boxes, classes, scores\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "78a3a69e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "def crop_and_save(image_np, boxes, class_names, scores, min_score=0.3):\n",
+    "    cropped_images = []\n",
+    "    for i in range(len(scores)):\n",
+    "        if scores[i] > min_score:\n",
+    "            ymin, xmin, ymax, xmax = boxes[i]\n",
+    "            im_width, im_height = image_np.shape[1], image_np.shape[0]\n",
+    "            (left, right, top, bottom) = (xmin * im_width, xmax * im_width,\n",
+    "                                          ymin * im_height, ymax * im_height)\n",
+    "            cropped_image = image_np[int(top):int(bottom), int(left):int(right)]\n",
+    "            cropped_images.append((cropped_image, class_names[i], scores[i]))\n",
+    "            # Save the cropped image\n",
+    "            pil_image = Image.fromarray(cropped_image)\n",
+    "            pil_image.save(f\"output/{class_names[i]}_{scores[i]:.2f}.jpg\")\n",
+    "    return cropped_images\n",
+    "\n",
+    "def draw_boxes(image_np, boxes, class_names, scores, min_score=0.3):\n",
+    "    image_pil = Image.fromarray(image_np)\n",
+    "    draw = ImageDraw.Draw(image_pil)\n",
+    "    font = ImageFont.load_default()\n",
+    "\n",
+    "    for i in range(len(scores)):\n",
+    "        label = class_names[i]\n",
+    "        print(label, scores[i])\n",
+    "        if label in TARGET_CLASSES and scores[i] > min_score:\n",
+    "            ymin, xmin, ymax, xmax = boxes[i]\n",
+    "            im_width, im_height = image_pil.size\n",
+    "            (left, right, top, bottom) = (xmin * im_width, xmax * im_width,\n",
+    "                                          ymin * im_height, ymax * im_height)\n",
+    "            draw.rectangle([left, top, right, bottom], outline=\"red\", width=2)\n",
+    "            draw.text((left, top), f\"{label}: {scores[i]*100:.1f}%\", fill=\"white\", font=font)\n",
+    "    return image_pil"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "ca9b4269",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def detect_and_display(image):\n",
+    "    results, image_np = run_object_detection(image)\n",
+    "    \n",
+    "    final_image = draw_boxes(image_np,\n",
+    "                             results[\"detection_boxes\"],\n",
+    "                             results[\"detection_class_entities\"],\n",
+    "                             results[\"detection_scores\"])\n",
+    "    final_image.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "9c01a9b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def detect_and_save(image):\n",
+    "    results, image_np = run_object_detection(image)\n",
+    "    boxes, class_names, scores = get_filtered_class_boxes(results)\n",
+    "    cropped_images = crop_and_save(image_np, boxes, class_names, scores,0)\n",
+    "    return cropped_images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf36b5e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "detect_and_display(\n",
+    "    image = Image.open(\"bv.jpg\").convert(\"RGB\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "e519e2f9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[(array([[[122, 113, 108],\n",
+       "          [123, 114, 109],\n",
+       "          [123, 114, 109],\n",
+       "          ...,\n",
+       "          [150, 141, 136],\n",
+       "          [150, 141, 136],\n",
+       "          [151, 142, 137]],\n",
+       "  \n",
+       "         [[122, 113, 108],\n",
+       "          [123, 114, 109],\n",
+       "          [123, 114, 109],\n",
+       "          ...,\n",
+       "          [150, 141, 136],\n",
+       "          [150, 141, 136],\n",
+       "          [151, 142, 137]],\n",
+       "  \n",
+       "         [[122, 113, 108],\n",
+       "          [123, 114, 109],\n",
+       "          [123, 114, 109],\n",
+       "          ...,\n",
+       "          [150, 141, 136],\n",
+       "          [150, 141, 136],\n",
+       "          [151, 142, 137]],\n",
+       "  \n",
+       "         ...,\n",
+       "  \n",
+       "         [[ 68,  31,  25],\n",
+       "          [ 69,  31,  28],\n",
+       "          [ 66,  31,  27],\n",
+       "          ...,\n",
+       "          [128, 119, 114],\n",
+       "          [128, 119, 114],\n",
+       "          [126, 117, 112]],\n",
+       "  \n",
+       "         [[ 64,  29,  23],\n",
+       "          [ 64,  29,  25],\n",
+       "          [ 62,  28,  26],\n",
+       "          ...,\n",
+       "          [127, 120, 114],\n",
+       "          [126, 119, 113],\n",
+       "          [126, 119, 113]],\n",
+       "  \n",
+       "         [[ 62,  29,  24],\n",
+       "          [ 58,  27,  24],\n",
+       "          [ 58,  27,  24],\n",
+       "          ...,\n",
+       "          [125, 118, 112],\n",
+       "          [125, 118, 112],\n",
+       "          [122, 115, 109]]], dtype=uint8),\n",
+       "  'Snack',\n",
+       "  np.float32(0.2383132))]"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "detect_and_save(\n",
+    "    image = Image.open(\"bv.jpg\").convert(\"RGB\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a84975ba",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}