diff --git a/demo.ipynb b/demo.ipynb
index 143503a31b0bd1843a95e7c4f3d2bf95696ab09b..b72047d4cbbb30c9b400d8fba9917e6aa51639e0 100644
--- a/demo.ipynb
+++ b/demo.ipynb
@@ -45,10 +45,11 @@
     "# Directory to save logs and trained model\n",
     "MODEL_DIR = os.path.join(ROOT_DIR, \"logs\")\n",
     "\n",
-    "# Path to trained weights file\n",
-    "# Download this file and place in the root of your \n",
-    "# project (See README file for details)\n",
+    "# Local path to trained weights file\n",
     "COCO_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_coco.h5\")\n",
+    "# Download COCO trained weights from Releases if needed\n",
+    "if not os.path.exists(COCO_MODEL_PATH):\n",
+    "    utils.download_trained_weights(COCO_MODEL_PATH)\n",
     "\n",
     "# Directory of images to run detection on\n",
     "IMAGE_DIR = os.path.join(ROOT_DIR, \"images\")"
@@ -144,6 +145,7 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {
+    "collapsed": true,
     "scrolled": false
    },
    "outputs": [],
@@ -282,7 +284,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.2"
   }
  },
  "nbformat": 4,
diff --git a/inspect_model.ipynb b/inspect_model.ipynb
index 67ecb6f981e0aab84d19a5de8bc9c01672e2e436..cccefe8c45bbecc2c3034dac29092b25572eb5e8 100644
--- a/inspect_model.ipynb
+++ b/inspect_model.ipynb
@@ -49,10 +49,11 @@
     "# Directory to save logs and trained model\n",
     "MODEL_DIR = os.path.join(ROOT_DIR, \"logs\")\n",
     "\n",
-    "# Path to trained weights file\n",
-    "# Download this file and place in the root of your \n",
-    "# project (See README file for details)\n",
+    "# Local path to trained weights file\n",
     "COCO_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_coco.h5\")\n",
+    "# Download COCO trained weights from Releases if needed\n",
+    "if not os.path.exists(COCO_MODEL_PATH):\n",
+    "    utils.download_trained_weights(COCO_MODEL_PATH)\n",
     "\n",
     "# Path to Shapes trained weights\n",
     "SHAPES_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_shapes.h5\")"
@@ -1377,7 +1378,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.2"
   }
  },
  "nbformat": 4,
diff --git a/inspect_weights.ipynb b/inspect_weights.ipynb
index 3519397797766ae0477ebc7f96c3d78c9ad06a78..912fae84c81e8e7f2afa10f46d0ba1b90f0e261e 100644
--- a/inspect_weights.ipynb
+++ b/inspect_weights.ipynb
@@ -44,8 +44,11 @@
     "# Directory to save logs and trained model\n",
     "MODEL_DIR = os.path.join(ROOT_DIR, \"logs\")\n",
     "\n",
-    "# Path to COCO trained weights\n",
+    "# Local path to trained weights file\n",
     "COCO_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_coco.h5\")\n",
+    "# Download COCO trained weights from Releases if needed\n",
+    "if not os.path.exists(COCO_MODEL_PATH):\n",
+    "    utils.download_trained_weights(COCO_MODEL_PATH)\n",
     "\n",
     "# Path to Shapes trained weights\n",
     "SHAPES_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_shapes.h5\")"
@@ -266,7 +269,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.2"
   }
  },
  "nbformat": 4,
diff --git a/train_shapes.ipynb b/train_shapes.ipynb
index 25ff3c7ea46a4902939b82400e80448c5ab563e5..666b4db3edfccad641f4708d0ec23e95930f5ea5 100644
--- a/train_shapes.ipynb
+++ b/train_shapes.ipynb
@@ -51,8 +51,11 @@
     "# Directory to save logs and trained model\n",
     "MODEL_DIR = os.path.join(ROOT_DIR, \"logs\")\n",
     "\n",
-    "# Path to COCO trained weights\n",
-    "COCO_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_coco.h5\")"
+    "# Local path to trained weights file\n",
+    "COCO_MODEL_PATH = os.path.join(ROOT_DIR, \"mask_rcnn_coco.h5\")\n",
+    "# Download COCO trained weights from Releases if needed\n",
+    "if not os.path.exists(COCO_MODEL_PATH):\n",
+    "    utils.download_trained_weights(COCO_MODEL_PATH)"
    ]
   },
   {
@@ -1024,7 +1027,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.2"
   }
  },
  "nbformat": 4,
diff --git a/utils.py b/utils.py
index c93b2861cbff84f89575546bcfea07607d6e20aa..13d13b743d515275e8b66672f084e2b7d6a1af81 100644
--- a/utils.py
+++ b/utils.py
@@ -16,6 +16,11 @@ import tensorflow as tf
 import scipy.misc
 import skimage.color
 import skimage.io
+import urllib.request
+import shutil
+
+# URL from which to download the latest COCO trained weights
+COCO_MODEL_URL = "https://github.com/matterport/Mask_RCNN/releases/download/v2.0/mask_rcnn_coco.h5"
 
 
 ############################################################
@@ -688,3 +693,16 @@ def batch_slice(inputs, graph_fn, batch_size, names=None):
         result = result[0]
 
     return result
+
+
+def download_trained_weights(coco_model_path, verbose=1):
+    """Download COCO trained weights from Releases.
+
+    coco_model_path: local path of COCO trained weights
+    """
+    if verbose > 0:
+        print("Downloading pretrained model to " + coco_model_path + " ...")
+    with urllib.request.urlopen(COCO_MODEL_URL) as resp, open(coco_model_path, 'wb') as out:
+        shutil.copyfileobj(resp, out)
+    if verbose > 0:
+        print("... done downloading pretrained model!")