Bug fix for label_map for publaynet

Author: lolipopshock

docs/notes/modelzoo.md

@@ -30,5 +30,5 @@ model.detect(image)
 | Dataset                                                      | Label Map                                                    |
 | ------------------------------------------------------------ | ------------------------------------------------------------ |
 | [HJDataset](https://dell-research-harvard.github.io/HJDataset/) | `{1:"Page Frame", 2:"Row", 3:"Title Region", 4:"Text Region", 5:"Title", 6:"Subtitle", 7:"Other"}` |
-| [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet)        | `{0:"Text", 1:"Title", 2:"List", 3:"Table", 4:"Figure"}`     |
+| [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet)        | `{1: "Text", 2: "Title", 3: "List", 4:"Table", 5:"Figure"}`     |
 | [PrimaLayout](https://www.primaresearch.org/dataset/)        | `{1:"TextRegion", 2:"ImageRegion", 3:"TableRegion", 4:"MathsRegion", 5:"SeparatorRegion", 6:"OtherRegion"}` |

examples/Deep Layout Parsing.ipynb

@@ -58,7 +58,7 @@
    "source": [
     "model = lp.Detectron2LayoutModel('lp://PubLayNet/faster_rcnn_R_50_FPN_3x/config', \n",
     "                                 extra_config=[\"MODEL.ROI_HEADS.SCORE_THRESH_TEST\", 0.8],\n",
-    "                                 label_map={0: \"Text\", 1: \"Title\", 2: \"List\", 3:\"Table\", 4:\"Figure\"})\n",
+    "                                 label_map={1: \"Text\", 2: \"Title\", 3: \"List\", 4:\"Table\", 5:\"Figure\"})\n",
     "    # Load the deep layout model from the layoutparser API \n",
     "    # For all the supported model, please check the Model \n",
     "    # Zoo Page: https://layout-parser.readthedocs.io/en/latest/notes/modelzoo.html"