workaround for Project-MONAI#1542

Signed-off-by: YunLiu <[email protected]>
KumoLiu · Apr 16, 2024 · 2177016 · 2177016
1 parent f534a1a
commit 2177016
Show file tree

Hide file tree

Showing 7 changed files with 17 additions and 136 deletions.
diff --git a/pathology/hovernet/README.MD b/pathology/hovernet/README.MD
@@ -8,7 +8,7 @@ It also has torch version notebooks to run training and evaluation.
 
 ### 1. Data
 
-CoNSeP datasets which are used in the examples can be downloaded from <https://warwick.ac.uk/fac/cross_fac/tia/data/HoVerNet/>.
+CoNSeP datasets which are used in the examples can be downloaded from <https://opendatalab.com/OpenDataLab/CoNSeP>.
 
 - First download CoNSeP dataset to `DATA_ROOT` (default is `"/workspace/Data/Pathology/CoNSeP"`).
 - Run `python prepare_patches.py` to prepare patches from images.

diff --git a/pathology/hovernet/hovernet_torch.ipynb b/pathology/hovernet/hovernet_torch.ipynb
@@ -207,7 +207,7 @@
    "source": [
     "## Download dataset, prepare patch\n",
     "Each user is responsible for checking the content of datasets and the applicable licenses and determining if suitable for the intended use.\n",
-    "1. download CoNSeP dataset\n",
+    "1. download CoNSeP dataset which can be downloaded form [ConSeP](https://opendatalab.com/OpenDataLab/CoNSeP)\n",
     "2. run ./prepare_patches.py to prepare patches from images. \n",
     "  Similar to https://github.com/vqdang/hover_net/blob/master/extract_patches.py"
    ]
@@ -218,13 +218,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "resource = \"https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip\"\n",
-    "md5 = \"a4fa18067849c536cba5fceee0427e81\"\n",
-    "\n",
-    "compressed_file = os.path.join(root_dir, \"consep_dataset.zip\")\n",
-    "data_dir = os.path.join(root_dir, \"CoNSeP\")\n",
-    "if not os.path.exists(data_dir):\n",
-    "    download_and_extract(resource, compressed_file, root_dir, md5)"
+    "data_dir = os.path.join(root_dir, \"CoNSeP\")"
    ]
   },
   {

diff --git a/pathology/nuclick/README.md b/pathology/nuclick/README.md
@@ -4,7 +4,7 @@ It also has notebooks to run inference over trained (monai-zoo) model.
 
 ### 1. Data
 
-Training these model requires data. Some public available datasets which are used in the examples can be downloaded from [ConSeP](https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet).
+Training these model requires data. Some public available datasets which are used in the examples can be downloaded from [ConSeP](https://opendatalab.com/OpenDataLab/CoNSeP). Each user is responsible for checking the content of datasets and the applicable licenses and determining if suitable for the intended use.
 
 ### 2. Questions and bugs
 

diff --git a/pathology/nuclick/nuclei_classification_infer.ipynb b/pathology/nuclick/nuclei_classification_infer.ipynb
@@ -249,43 +249,6 @@
     "    plt.show()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "consep_dataset.zip: 146MB [00:40, 3.76MB/s]                                                                                                                                                                                                                    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2022-12-06 10:50:51,968 - INFO - Downloaded: /tmp/tmpct_gfbvg/consep_dataset.zip\n",
-      "2022-12-06 10:50:51,970 - INFO - Expected md5 is None, skip md5 check for file /tmp/tmpct_gfbvg/consep_dataset.zip.\n",
-      "2022-12-06 10:50:51,972 - INFO - Writing into directory: workspace.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "consep_zip = \"https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip\"\n",
-    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
-    "\n",
-    "if not os.path.exists(consep_dir):\n",
-    "    download_and_extract(consep_zip, output_dir=workspace_path)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 8,
@@ -310,6 +273,8 @@
     }
    ],
    "source": [
+    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
+    "\n",
     "image_file = os.path.join(consep_dir, \"Test\", \"Images\", \"test_12.png\")\n",
     "label_mat = os.path.join(consep_dir, \"Test\", \"Labels\", \"test_12.mat\")\n",
     "\n",

diff --git a/pathology/nuclick/nuclei_classification_training_notebook.ipynb b/pathology/nuclick/nuclei_classification_training_notebook.ipynb
@@ -146,44 +146,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Configure Workspace Path"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "consep_dataset.zip: 146MB [00:23, 6.41MB/s]                                                                                                                                                                                                                    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2022-12-06 10:46:41,905 - INFO - Downloaded: /tmp/tmp834vb_2l/consep_dataset.zip\n",
-      "2022-12-06 10:46:41,907 - INFO - Expected md5 is None, skip md5 check for file /tmp/tmp834vb_2l/consep_dataset.zip.\n",
-      "2022-12-06 10:46:41,910 - INFO - Writing into directory: workspace.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "consep_zip = \"https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip\"\n",
-    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
-    "\n",
-    "if not os.path.exists(consep_dir):\n",
-    "    download_and_extract(consep_zip, output_dir=workspace_path)"
+    "## Configure Workspace Path\n",
+    "The public available datasets which are used in the examples can be downloaded from [ConSeP](https://opendatalab.com/OpenDataLab/CoNSeP). Each user is responsible for checking the content of datasets and the applicable licenses and determining if suitable for the intended use."
    ]
   },
   {
@@ -204,6 +168,9 @@
     }
    ],
    "source": [
+    "# consep_dir points to the root directory of the consep dataset\n",
+    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
+    "\n",
     "IImage(filename=os.path.join(consep_dir, \"Train\", \"Overlay\", \"train_8.png\"))"
    ]
   },

diff --git a/pathology/nuclick/nuclick_infer.ipynb b/pathology/nuclick/nuclick_infer.ipynb
@@ -247,43 +247,6 @@
     "    plt.show()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "consep_dataset.zip: 146MB [00:26, 5.86MB/s]                                                                                                                                                                                                                    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2022-12-06 10:38:08,238 - INFO - Downloaded: /tmp/tmp7_dupxgu/consep_dataset.zip\n",
-      "2022-12-06 10:38:08,239 - INFO - Expected md5 is None, skip md5 check for file /tmp/tmp7_dupxgu/consep_dataset.zip.\n",
-      "2022-12-06 10:38:08,241 - INFO - Writing into directory: workspace.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "consep_zip = \"https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip\"\n",
-    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
-    "\n",
-    "if not os.path.exists(consep_dir):\n",
-    "    download_and_extract(consep_zip, output_dir=workspace_path)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 8,
@@ -309,6 +272,8 @@
     }
    ],
    "source": [
+    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
+    "\n",
     "image_file = os.path.join(consep_dir, \"Test\", \"Images\", \"test_12.png\")\n",
     "foreground = [[190, 15], [218, 32], [296, 96]]\n",
     "\n",

diff --git a/pathology/nuclick/nuclick_training_notebook.ipynb b/pathology/nuclick/nuclick_training_notebook.ipynb
@@ -148,20 +148,7 @@
    "metadata": {},
    "source": [
     "## Configure Workspace Path\n",
-    "Please note this dataset is under noncommercial license. You may not use it for commercial purpose."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "consep_zip = \"https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip\"\n",
-    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
-    "\n",
-    "if not os.path.exists(consep_dir):\n",
-    "    download_and_extract(consep_zip, output_dir=workspace_path)"
+    "The public available datasets which are used in the examples can be downloaded from [ConSeP](https://opendatalab.com/OpenDataLab/CoNSeP). Each user is responsible for checking the content of datasets and the applicable licenses and determining if suitable for the intended use."
    ]
   },
   {
@@ -182,6 +169,9 @@
     }
    ],
    "source": [
+    "# consep_dir points to the root directory of the consep dataset\n",
+    "consep_dir = os.path.join(workspace_path, \"CoNSeP\")\n",
+    "\n",
     "IImage(filename=os.path.join(consep_dir, \"Train\", \"Overlay\", \"train_1.png\"))"
    ]
   },