Merge pull request #266 from roboflow/add-classification-upload

Add YOLOv8 classification model weight upload instructions

notebooks/train-yolov8-classification-on-custom-dataset.ipynb

@@ -1173,11 +1173,33 @@
         "import glob\n",
         "from IPython.display import Image, display\n",
         "\n",
-        "for image_path in glob.glob(f'{HOME}/runs/classify/predict2/*.jpg')[:3]:\n",
+        "for image_path in glob.glob(f'{HOME}/runs/classify/predict/*.jpg')[:3]:\n",
         "      display(Image(filename=image_path, width=600))\n",
         "      print(\"\\n\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Save and Deploy model\n",
+        "\n",
+        "Once you have finished training your YOLOv8 model, you’ll have a set of trained weights ready for use. These weights will be in the `/runs/classify/train/weights/best.pt` folder of your project. You can upload and your model weights to Roboflow Deploy for autolabeling, autoscaling inference, and using later.\n",
+        "\n",
+        "The `.deploy()` function in the [Roboflow pip package](https://docs.roboflow.com/python) supports uploading YOLOv8 weights.\n",
+        "\n",
+        "Run this cell to save your model weights:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "project.version(dataset.version).deploy(model_type=\"yolov8-cls\", model_path=f\"{HOME}/runs/classify/train/\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},