[ci] prepare integration into samgis

lisa_on_cuda/utils/app_helpers.py

@@ -206,11 +206,11 @@ def get_inference_model_by_args(args_to_parse):
     no_seg_out, error_happened = placeholders["no_seg_out"], placeholders["error_happened"]
 
     @session_logger.set_uuid_logging
-    def inference(input_str, input_image_pathname):
+    def inference(input_str: str, input_image: str | np.ndarray):
         ## filter out special chars
         input_str = get_cleaned_input(input_str)
-        logging.info(f"input_str type: {type(input_str)}, input_image type: {type(input_image_pathname)}.")
-        logging.info(f"input_str: {input_str}, input_image: {type(input_image_pathname)}.")
+        logging.info(f"input_str type: {type(input_str)}, input_image type: {type(input_image)}.")
+        logging.info(f"input_str: {input_str}, input_image: {type(input_image)}.")
 
         ## input valid check
         if not re.match(r"^[A-Za-z ,.!?\'\"]+$", input_str) or len(input_str) < 1:
@@ -232,8 +232,10 @@ def get_inference_model_by_args(args_to_parse):
         conv.append_message(conv.roles[1], "")
         prompt = conv.get_prompt()
 
-        image_np = cv2.imread(input_image_pathname)
-        image_np = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
+        image_np = input_image
+        if isinstance(input_image, str):
+            image_np = cv2.imread(input_image)
+            image_np = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
         original_size_list = [image_np.shape[:2]]
 
         image_clip = (

notebooks/tests_colab.ipynb

@@ -16,7 +16,7 @@
     "accelerator": "GPU",
     "widgets": {
       "application/vnd.jupyter.widget-state+json": {
-        "51413ef239f048eea0c9e2918cee48cc": {
+        "e968b46a1ecb485fa9f164f6ec0f5569": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "HBoxModel",
           "model_module_version": "1.5.0",
@@ -31,14 +31,14 @@
             "_view_name": "HBoxView",
             "box_style": "",
             "children": [
-              "IPY_MODEL_b0266b1bb0954ca3a086af17d4710c61",
-              "IPY_MODEL_9ef4c775d0ac42bb94e982ff22151968",
-              "IPY_MODEL_cdf02b65bc574213bece3dd7bb447701"
+              "IPY_MODEL_759af27e6e3e439f9a8739c470d9b4ed",
+              "IPY_MODEL_5d5bd7bb543c44c48acb5a38d0e2b392",
+              "IPY_MODEL_77f3526c940841ec8c3d3bb1da85dbc8"
             ],
-            "layout": "IPY_MODEL_b12b23aeae5f4ccf9947c53018a227f1"
+            "layout": "IPY_MODEL_5eca36e7aa8a4775911eeb4c8684af6d"
           }
         },
-        "b0266b1bb0954ca3a086af17d4710c61": {
+        "759af27e6e3e439f9a8739c470d9b4ed": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "HTMLModel",
           "model_module_version": "1.5.0",
@@ -53,13 +53,13 @@
             "_view_name": "HTMLView",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_f4db86625411496499a09155dcd107f2",
+            "layout": "IPY_MODEL_944fa9555ead4941aa855bbd35a4f5d7",
             "placeholder": "​",
-            "style": "IPY_MODEL_62c9dd19d1cb414893f5d1d538834602",
+            "style": "IPY_MODEL_2ad8fb9acc93495ca60d355ea4b0c161",
             "value": "Loading checkpoint shards: 100%"
           }
         },
-        "9ef4c775d0ac42bb94e982ff22151968": {
+        "5d5bd7bb543c44c48acb5a38d0e2b392": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "FloatProgressModel",
           "model_module_version": "1.5.0",
@@ -75,15 +75,15 @@
             "bar_style": "success",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_e665c80334da4da387339db1fa52d3c1",
+            "layout": "IPY_MODEL_a03fbfb4742342758d99d4354a9191e5",
             "max": 3,
             "min": 0,
             "orientation": "horizontal",
-            "style": "IPY_MODEL_71434c95d69d4783bf2b27c50c641ff8",
+            "style": "IPY_MODEL_e7f6ff163e4846388f621f41ad287bfb",
             "value": 3
           }
         },
-        "cdf02b65bc574213bece3dd7bb447701": {
+        "77f3526c940841ec8c3d3bb1da85dbc8": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "HTMLModel",
           "model_module_version": "1.5.0",
@@ -98,13 +98,13 @@
             "_view_name": "HTMLView",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_8d21439ee9ab437586b08cb7063c6a4b",
+            "layout": "IPY_MODEL_de68261aa80941afb2759b764aa10226",
             "placeholder": "​",
-            "style": "IPY_MODEL_cafa0b3fa2a74738a37559c521706e18",
-            "value": " 3/3 [07:11<00:00, 144.77s/it]"
+            "style": "IPY_MODEL_8d9f42c52f604fb590e77a3f5441ec09",
+            "value": " 3/3 [11:05<00:00, 210.21s/it]"
           }
         },
-        "b12b23aeae5f4ccf9947c53018a227f1": {
+        "5eca36e7aa8a4775911eeb4c8684af6d": {
           "model_module": "@jupyter-widgets/base",
           "model_name": "LayoutModel",
           "model_module_version": "1.2.0",
@@ -156,7 +156,7 @@
             "width": null
           }
         },
-        "f4db86625411496499a09155dcd107f2": {
+        "944fa9555ead4941aa855bbd35a4f5d7": {
           "model_module": "@jupyter-widgets/base",
           "model_name": "LayoutModel",
           "model_module_version": "1.2.0",
@@ -208,7 +208,7 @@
             "width": null
           }
         },
-        "62c9dd19d1cb414893f5d1d538834602": {
+        "2ad8fb9acc93495ca60d355ea4b0c161": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "DescriptionStyleModel",
           "model_module_version": "1.5.0",
@@ -223,7 +223,7 @@
             "description_width": ""
           }
         },
-        "e665c80334da4da387339db1fa52d3c1": {
+        "a03fbfb4742342758d99d4354a9191e5": {
           "model_module": "@jupyter-widgets/base",
           "model_name": "LayoutModel",
           "model_module_version": "1.2.0",
@@ -275,7 +275,7 @@
             "width": null
           }
         },
-        "71434c95d69d4783bf2b27c50c641ff8": {
+        "e7f6ff163e4846388f621f41ad287bfb": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "ProgressStyleModel",
           "model_module_version": "1.5.0",
@@ -291,7 +291,7 @@
             "description_width": ""
           }
         },
-        "8d21439ee9ab437586b08cb7063c6a4b": {
+        "de68261aa80941afb2759b764aa10226": {
           "model_module": "@jupyter-widgets/base",
           "model_name": "LayoutModel",
           "model_module_version": "1.2.0",
@@ -343,7 +343,7 @@
             "width": null
           }
         },
-        "cafa0b3fa2a74738a37559c521706e18": {
+        "8d9f42c52f604fb590e77a3f5441ec09": {
           "model_module": "@jupyter-widgets/controls",
           "model_name": "DescriptionStyleModel",
           "model_module_version": "1.5.0",
@@ -394,6 +394,7 @@
         "sudo apt install git-lfs -y\n",
         "echo \"installed git-lfs\"\n",
         "git clone https://huggingface.co/spaces/aletrn/lisa-on-cuda\n",
+        "git checkout packaging\n",
         "# cd lisa-on-cuda\n",
         "# git pull\n",
         "echo \"cloned.\""
@@ -403,7 +404,7 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "mbt3zCgrIXQd",
-        "outputId": "be6f2b84-8d96-406a-aa3f-182ce93181ce"
+        "outputId": "bd1fe583-a85b-43ea-8eb9-255774e0b409"
       },
       "execution_count": 1,
       "outputs": [
@@ -427,7 +428,53 @@
             "\n",
             "WARNING: apt does not have a stable CLI interface. Use with caution in scripts.\n",
             "\n",
-            "Cloning into 'lisa-on-cuda'...\n"
+            "Cloning into 'lisa-on-cuda'...\n",
+            "Filtering content:  48% (15/31)\rFiltering content:  51% (16/31)\rFiltering content:  54% (17/31)\rFiltering content:  58% (18/31)\rFiltering content:  61% (19/31)\rFiltering content:  64% (20/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  67% (21/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  70% (22/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  74% (23/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  77% (24/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  80% (25/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  83% (26/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  87% (27/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  90% (28/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  93% (29/31), 17.74 MiB | 33.28 MiB/s\rFiltering content:  96% (30/31), 17.74 MiB | 33.28 MiB/s\rFiltering content: 100% (31/31), 17.74 MiB | 33.28 MiB/s\rFiltering content: 100% (31/31), 19.13 MiB | 12.35 MiB/s, done.\n",
+            "fatal: not a git repository (or any of the parent directories): .git\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "%%bash\n",
+        "\n",
+        "cd /content/lisa-on-cuda/\n",
+        "git checkout packaging\n",
+        "git log|head"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "d1VEHQ5Zkq-8",
+        "outputId": "72e819bb-433e-408a-b382-5b3c5febc19a"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Branch 'packaging' set up to track remote branch 'packaging' from 'origin'.\n",
+            "commit 60fa201359a4a3ae870f114f647a9fd05b7a0d13\n",
+            "Author: alessandro trinca tornidor <[email protected]>\n",
+            "Date:   Sun Mar 10 19:12:36 2024 +0100\n",
+            "\n",
+            "    [refactor] prepare packaging moving all the modules under 'lisa_on_cuda' (renamed from 'model')\n",
+            "\n",
+            "commit 52318ecdc84c7f3e099ad62e05b0bb4956888985\n",
+            "Author: alessandro trinca tornidor <[email protected]>\n",
+            "Date:   Sun Mar 10 01:30:58 2024 +0100\n",
+            "\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Switched to a new branch 'packaging'\n"
           ]
         }
       ]
@@ -440,10 +487,499 @@
         "print(\"ok\")"
       ],
       "metadata": {
-        "id": "NzJXs40cfFFH"
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "NzJXs40cfFFH",
+        "outputId": "436dbb22-2420-43c5-898c-c9184155c1c3"
       },
-      "execution_count": null,
-      "outputs": []
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "absl-py==1.4.0\n",
+            "aiohttp==3.9.3\n",
+            "aiosignal==1.3.1\n",
+            "alabaster==0.7.16\n",
+            "albumentations==1.3.1\n",
+            "altair==4.2.2\n",
+            "annotated-types==0.6.0\n",
+            "anyio==3.7.1\n",
+            "appdirs==1.4.4\n",
+            "argon2-cffi==23.1.0\n",
+            "argon2-cffi-bindings==21.2.0\n",
+            "array-record==0.5.0\n",
+            "arviz==0.15.1\n",
+            "astropy==5.3.4\n",
+            "astunparse==1.6.3\n",
+            "async-timeout==4.0.3\n",
+            "atpublic==4.0\n",
+            "attrs==23.2.0\n",
+            "audioread==3.0.1\n",
+            "autograd==1.6.2\n",
+            "Babel==2.14.0\n",
+            "backcall==0.2.0\n",
+            "beautifulsoup4==4.12.3\n",
+            "bidict==0.23.1\n",
+            "bigframes==0.22.0\n",
+            "bleach==6.1.0\n",
+            "blinker==1.4\n",
+            "blis==0.7.11\n",
+            "blosc2==2.0.0\n",
+            "bokeh==3.3.4\n",
+            "bqplot==0.12.43\n",
+            "branca==0.7.1\n",
+            "build==1.1.1\n",
+            "CacheControl==0.14.0\n",
+            "cachetools==5.3.3\n",
+            "catalogue==2.0.10\n",
+            "certifi==2024.2.2\n",
+            "cffi==1.16.0\n",
+            "chardet==5.2.0\n",
+            "charset-normalizer==3.3.2\n",
+            "chex==0.1.85\n",
+            "click==8.1.7\n",
+            "click-plugins==1.1.1\n",
+            "cligj==0.7.2\n",
+            "cloudpathlib==0.16.0\n",
+            "cloudpickle==2.2.1\n",
+            "cmake==3.27.9\n",
+            "cmdstanpy==1.2.1\n",
+            "colorcet==3.1.0\n",
+            "colorlover==0.3.0\n",
+            "colour==0.1.5\n",
+            "community==1.0.0b1\n",
+            "confection==0.1.4\n",
+            "cons==0.4.6\n",
+            "contextlib2==21.6.0\n",
+            "contourpy==1.2.0\n",
+            "cryptography==42.0.5\n",
+            "cufflinks==0.17.3\n",
+            "cupy-cuda12x==12.2.0\n",
+            "cvxopt==1.3.2\n",
+            "cvxpy==1.3.3\n",
+            "cycler==0.12.1\n",
+            "cymem==2.0.8\n",
+            "Cython==3.0.9\n",
+            "dask==2023.8.1\n",
+            "datascience==0.17.6\n",
+            "db-dtypes==1.2.0\n",
+            "dbus-python==1.2.18\n",
+            "debugpy==1.6.6\n",
+            "decorator==4.4.2\n",
+            "defusedxml==0.7.1\n",
+            "distributed==2023.8.1\n",
+            "distro==1.7.0\n",
+            "dlib==19.24.2\n",
+            "dm-tree==0.1.8\n",
+            "docutils==0.18.1\n",
+            "dopamine-rl==4.0.6\n",
+            "duckdb==0.9.2\n",
+            "earthengine-api==0.1.392\n",
+            "easydict==1.13\n",
+            "ecos==2.0.13\n",
+            "editdistance==0.6.2\n",
+            "eerepr==0.0.4\n",
+            "en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl#sha256=86cc141f63942d4b2c5fcee06630fd6f904788d2f0ab005cce45aadb8fb73889\n",
+            "entrypoints==0.4\n",
+            "et-xmlfile==1.1.0\n",
+            "etils==1.7.0\n",
+            "etuples==0.3.9\n",
+            "exceptiongroup==1.2.0\n",
+            "fastai==2.7.14\n",
+            "fastcore==1.5.29\n",
+            "fastdownload==0.0.7\n",
+            "fastjsonschema==2.19.1\n",
+            "fastprogress==1.0.3\n",
+            "fastrlock==0.8.2\n",
+            "filelock==3.13.1\n",
+            "fiona==1.9.5\n",
+            "firebase-admin==5.3.0\n",
+            "Flask==2.2.5\n",
+            "flatbuffers==23.5.26\n",
+            "flax==0.8.1\n",
+            "folium==0.14.0\n",
+            "fonttools==4.49.0\n",
+            "frozendict==2.4.0\n",
+            "frozenlist==1.4.1\n",
+            "fsspec==2023.6.0\n",
+            "future==0.18.3\n",
+            "gast==0.5.4\n",
+            "gcsfs==2023.6.0\n",
+            "GDAL==3.6.4\n",
+            "gdown==4.7.3\n",
+            "geemap==0.32.0\n",
+            "gensim==4.3.2\n",
+            "geocoder==1.38.1\n",
+            "geographiclib==2.0\n",
+            "geopandas==0.13.2\n",
+            "geopy==2.3.0\n",
+            "gin-config==0.5.0\n",
+            "glob2==0.7\n",
+            "google==2.0.3\n",
+            "google-ai-generativelanguage==0.4.0\n",
+            "google-api-core==2.11.1\n",
+            "google-api-python-client==2.84.0\n",
+            "google-auth==2.27.0\n",
+            "google-auth-httplib2==0.1.1\n",
+            "google-auth-oauthlib==1.2.0\n",
+            "google-cloud-aiplatform==1.43.0\n",
+            "google-cloud-bigquery==3.12.0\n",
+            "google-cloud-bigquery-connection==1.12.1\n",
+            "google-cloud-bigquery-storage==2.24.0\n",
+            "google-cloud-core==2.3.3\n",
+            "google-cloud-datastore==2.15.2\n",
+            "google-cloud-firestore==2.11.1\n",
+            "google-cloud-functions==1.13.3\n",
+            "google-cloud-iam==2.14.3\n",
+            "google-cloud-language==2.13.3\n",
+            "google-cloud-resource-manager==1.12.3\n",
+            "google-cloud-storage==2.8.0\n",
+            "google-cloud-translate==3.11.3\n",
+            "google-colab @ file:///colabtools/dist/google-colab-1.0.0.tar.gz#sha256=e916d4e7c3ba6158df864a2e03852211d8fab20abb3db5205b865eedf4be9799\n",
+            "google-crc32c==1.5.0\n",
+            "google-generativeai==0.3.2\n",
+            "google-pasta==0.2.0\n",
+            "google-resumable-media==2.7.0\n",
+            "googleapis-common-protos==1.62.0\n",
+            "googledrivedownloader==0.4\n",
+            "graphviz==0.20.1\n",
+            "greenlet==3.0.3\n",
+            "grpc-google-iam-v1==0.13.0\n",
+            "grpcio==1.62.0\n",
+            "grpcio-status==1.48.2\n",
+            "gspread==3.4.2\n",
+            "gspread-dataframe==3.3.1\n",
+            "gym==0.25.2\n",
+            "gym-notices==0.0.8\n",
+            "h5netcdf==1.3.0\n",
+            "h5py==3.9.0\n",
+            "holidays==0.44\n",
+            "holoviews==1.17.1\n",
+            "html5lib==1.1\n",
+            "httpimport==1.3.1\n",
+            "httplib2==0.22.0\n",
+            "huggingface-hub==0.20.3\n",
+            "humanize==4.7.0\n",
+            "hyperopt==0.2.7\n",
+            "ibis-framework==7.1.0\n",
+            "idna==3.6\n",
+            "imageio==2.31.6\n",
+            "imageio-ffmpeg==0.4.9\n",
+            "imagesize==1.4.1\n",
+            "imbalanced-learn==0.10.1\n",
+            "imgaug==0.4.0\n",
+            "importlib-metadata==7.0.1\n",
+            "importlib_resources==6.1.2\n",
+            "imutils==0.5.4\n",
+            "inflect==7.0.0\n",
+            "iniconfig==2.0.0\n",
+            "intel-openmp==2023.2.3\n",
+            "ipyevents==2.0.2\n",
+            "ipyfilechooser==0.6.0\n",
+            "ipykernel==5.5.6\n",
+            "ipyleaflet==0.18.2\n",
+            "ipython==7.34.0\n",
+            "ipython-genutils==0.2.0\n",
+            "ipython-sql==0.5.0\n",
+            "ipytree==0.2.2\n",
+            "ipywidgets==7.7.1\n",
+            "itsdangerous==2.1.2\n",
+            "jax==0.4.23\n",
+            "jaxlib @ https://storage.googleapis.com/jax-releases/cuda12/jaxlib-0.4.23+cuda12.cudnn89-cp310-cp310-manylinux2014_x86_64.whl#sha256=8e42000672599e7ec0ea7f551acfcc95dcdd0e22b05a1d1f12f97b56a9fce4a8\n",
+            "jeepney==0.7.1\n",
+            "jieba==0.42.1\n",
+            "Jinja2==3.1.3\n",
+            "joblib==1.3.2\n",
+            "jsonpickle==3.0.3\n",
+            "jsonschema==4.19.2\n",
+            "jsonschema-specifications==2023.12.1\n",
+            "jupyter-client==6.1.12\n",
+            "jupyter-console==6.1.0\n",
+            "jupyter-server==1.24.0\n",
+            "jupyter_core==5.7.1\n",
+            "jupyterlab_pygments==0.3.0\n",
+            "jupyterlab_widgets==3.0.10\n",
+            "kaggle==1.5.16\n",
+            "kagglehub==0.2.0\n",
+            "keras==2.15.0\n",
+            "keyring==23.5.0\n",
+            "kiwisolver==1.4.5\n",
+            "langcodes==3.3.0\n",
+            "launchpadlib==1.10.16\n",
+            "lazr.restfulclient==0.14.4\n",
+            "lazr.uri==1.0.6\n",
+            "lazy_loader==0.3\n",
+            "libclang==16.0.6\n",
+            "librosa==0.10.1\n",
+            "lightgbm==4.1.0\n",
+            "linkify-it-py==2.0.3\n",
+            "llvmlite==0.41.1\n",
+            "locket==1.0.0\n",
+            "logical-unification==0.4.6\n",
+            "lxml==4.9.4\n",
+            "malloy==2023.1067\n",
+            "Markdown==3.5.2\n",
+            "markdown-it-py==3.0.0\n",
+            "MarkupSafe==2.1.5\n",
+            "matplotlib==3.7.1\n",
+            "matplotlib-inline==0.1.6\n",
+            "matplotlib-venn==0.11.10\n",
+            "mdit-py-plugins==0.4.0\n",
+            "mdurl==0.1.2\n",
+            "miniKanren==1.0.3\n",
+            "missingno==0.5.2\n",
+            "mistune==0.8.4\n",
+            "mizani==0.9.3\n",
+            "mkl==2023.2.0\n",
+            "ml-dtypes==0.2.0\n",
+            "mlxtend==0.22.0\n",
+            "more-itertools==10.1.0\n",
+            "moviepy==1.0.3\n",
+            "mpmath==1.3.0\n",
+            "msgpack==1.0.8\n",
+            "multidict==6.0.5\n",
+            "multipledispatch==1.0.0\n",
+            "multitasking==0.0.11\n",
+            "murmurhash==1.0.10\n",
+            "music21==9.1.0\n",
+            "natsort==8.4.0\n",
+            "nbclassic==1.0.0\n",
+            "nbclient==0.9.0\n",
+            "nbconvert==6.5.4\n",
+            "nbformat==5.9.2\n",
+            "nest-asyncio==1.6.0\n",
+            "networkx==3.2.1\n",
+            "nibabel==4.0.2\n",
+            "nltk==3.8.1\n",
+            "notebook==6.5.5\n",
+            "notebook_shim==0.2.4\n",
+            "numba==0.58.1\n",
+            "numexpr==2.9.0\n",
+            "numpy==1.25.2\n",
+            "oauth2client==4.1.3\n",
+            "oauthlib==3.2.2\n",
+            "opencv-contrib-python==4.8.0.76\n",
+            "opencv-python==4.8.0.76\n",
+            "opencv-python-headless==4.9.0.80\n",
+            "openpyxl==3.1.2\n",
+            "opt-einsum==3.3.0\n",
+            "optax==0.1.9\n",
+            "orbax-checkpoint==0.4.4\n",
+            "osqp==0.6.2.post8\n",
+            "packaging==23.2\n",
+            "pandas==1.5.3\n",
+            "pandas-datareader==0.10.0\n",
+            "pandas-gbq==0.19.2\n",
+            "pandas-stubs==1.5.3.230304\n",
+            "pandocfilters==1.5.1\n",
+            "panel==1.3.8\n",
+            "param==2.0.2\n",
+            "parso==0.8.3\n",
+            "parsy==2.1\n",
+            "partd==1.4.1\n",
+            "pathlib==1.0.1\n",
+            "patsy==0.5.6\n",
+            "peewee==3.17.1\n",
+            "pexpect==4.9.0\n",
+            "pickleshare==0.7.5\n",
+            "Pillow==9.4.0\n",
+            "pins==0.8.4\n",
+            "pip-tools==6.13.0\n",
+            "platformdirs==4.2.0\n",
+            "plotly==5.15.0\n",
+            "plotnine==0.12.4\n",
+            "pluggy==1.4.0\n",
+            "polars==0.20.2\n",
+            "pooch==1.8.1\n",
+            "portpicker==1.5.2\n",
+            "prefetch-generator==1.0.3\n",
+            "preshed==3.0.9\n",
+            "prettytable==3.10.0\n",
+            "proglog==0.1.10\n",
+            "progressbar2==4.2.0\n",
+            "prometheus_client==0.20.0\n",
+            "promise==2.3\n",
+            "prompt-toolkit==3.0.43\n",
+            "prophet==1.1.5\n",
+            "proto-plus==1.23.0\n",
+            "protobuf==3.20.3\n",
+            "psutil==5.9.5\n",
+            "psycopg2==2.9.9\n",
+            "ptyprocess==0.7.0\n",
+            "py-cpuinfo==9.0.0\n",
+            "py4j==0.10.9.7\n",
+            "pyarrow==14.0.2\n",
+            "pyarrow-hotfix==0.6\n",
+            "pyasn1==0.5.1\n",
+            "pyasn1-modules==0.3.0\n",
+            "pycocotools==2.0.7\n",
+            "pycparser==2.21\n",
+            "pydantic==2.6.3\n",
+            "pydantic_core==2.16.3\n",
+            "pydata-google-auth==1.8.2\n",
+            "pydot==1.4.2\n",
+            "pydot-ng==2.0.0\n",
+            "pydotplus==2.0.2\n",
+            "PyDrive==1.3.1\n",
+            "PyDrive2==1.6.3\n",
+            "pyerfa==2.0.1.1\n",
+            "pygame==2.5.2\n",
+            "Pygments==2.16.1\n",
+            "PyGObject==3.42.1\n",
+            "PyJWT==2.3.0\n",
+            "pymc==5.10.4\n",
+            "pymystem3==0.2.0\n",
+            "PyOpenGL==3.1.7\n",
+            "pyOpenSSL==24.0.0\n",
+            "pyparsing==3.1.1\n",
+            "pyperclip==1.8.2\n",
+            "pyproj==3.6.1\n",
+            "pyproject_hooks==1.0.0\n",
+            "pyshp==2.3.1\n",
+            "PySocks==1.7.1\n",
+            "pytensor==2.18.6\n",
+            "pytest==7.4.4\n",
+            "python-apt @ file:///backend-container/containers/python_apt-0.0.0-cp310-cp310-linux_x86_64.whl#sha256=b209c7165d6061963abe611492f8c91c3bcef4b7a6600f966bab58900c63fefa\n",
+            "python-box==7.1.1\n",
+            "python-dateutil==2.8.2\n",
+            "python-louvain==0.16\n",
+            "python-slugify==8.0.4\n",
+            "python-utils==3.8.2\n",
+            "pytz==2023.4\n",
+            "pyviz_comms==3.0.1\n",
+            "PyWavelets==1.5.0\n",
+            "PyYAML==6.0.1\n",
+            "pyzmq==23.2.1\n",
+            "qdldl==0.1.7.post0\n",
+            "qudida==0.0.4\n",
+            "ratelim==0.1.6\n",
+            "referencing==0.33.0\n",
+            "regex==2023.12.25\n",
+            "requests==2.31.0\n",
+            "requests-oauthlib==1.3.1\n",
+            "requirements-parser==0.5.0\n",
+            "rich==13.7.1\n",
+            "rpds-py==0.18.0\n",
+            "rpy2==3.4.2\n",
+            "rsa==4.9\n",
+            "safetensors==0.4.2\n",
+            "scikit-image==0.19.3\n",
+            "scikit-learn==1.2.2\n",
+            "scipy==1.11.4\n",
+            "scooby==0.9.2\n",
+            "scs==3.2.4.post1\n",
+            "seaborn==0.13.1\n",
+            "SecretStorage==3.3.1\n",
+            "Send2Trash==1.8.2\n",
+            "sentencepiece==0.1.99\n",
+            "shapely==2.0.3\n",
+            "six==1.16.0\n",
+            "sklearn-pandas==2.2.0\n",
+            "smart-open==6.4.0\n",
+            "sniffio==1.3.1\n",
+            "snowballstemmer==2.2.0\n",
+            "sortedcontainers==2.4.0\n",
+            "soundfile==0.12.1\n",
+            "soupsieve==2.5\n",
+            "soxr==0.3.7\n",
+            "spacy==3.7.4\n",
+            "spacy-legacy==3.0.12\n",
+            "spacy-loggers==1.0.5\n",
+            "Sphinx==5.0.2\n",
+            "sphinxcontrib-applehelp==1.0.8\n",
+            "sphinxcontrib-devhelp==1.0.6\n",
+            "sphinxcontrib-htmlhelp==2.0.5\n",
+            "sphinxcontrib-jsmath==1.0.1\n",
+            "sphinxcontrib-qthelp==1.0.7\n",
+            "sphinxcontrib-serializinghtml==1.1.10\n",
+            "SQLAlchemy==2.0.28\n",
+            "sqlglot==19.9.0\n",
+            "sqlparse==0.4.4\n",
+            "srsly==2.4.8\n",
+            "stanio==0.3.0\n",
+            "statsmodels==0.14.1\n",
+            "sympy==1.12\n",
+            "tables==3.8.0\n",
+            "tabulate==0.9.0\n",
+            "tbb==2021.11.0\n",
+            "tblib==3.0.0\n",
+            "tenacity==8.2.3\n",
+            "tensorboard==2.15.2\n",
+            "tensorboard-data-server==0.7.2\n",
+            "tensorflow==2.15.0\n",
+            "tensorflow-datasets==4.9.4\n",
+            "tensorflow-estimator==2.15.0\n",
+            "tensorflow-gcs-config==2.15.0\n",
+            "tensorflow-hub==0.16.1\n",
+            "tensorflow-io-gcs-filesystem==0.36.0\n",
+            "tensorflow-metadata==1.14.0\n",
+            "tensorflow-probability==0.23.0\n",
+            "tensorstore==0.1.45\n",
+            "termcolor==2.4.0\n",
+            "terminado==0.18.0\n",
+            "text-unidecode==1.3\n",
+            "textblob==0.17.1\n",
+            "tf-keras==2.15.0\n",
+            "tf-slim==1.1.0\n",
+            "thinc==8.2.3\n",
+            "threadpoolctl==3.3.0\n",
+            "tifffile==2024.2.12\n",
+            "tinycss2==1.2.1\n",
+            "tokenizers==0.15.2\n",
+            "toml==0.10.2\n",
+            "tomli==2.0.1\n",
+            "toolz==0.12.1\n",
+            "torch @ https://download.pytorch.org/whl/cu121/torch-2.1.0%2Bcu121-cp310-cp310-linux_x86_64.whl#sha256=0d4e8c52a1fcf5ed6cfc256d9a370fcf4360958fc79d0b08a51d55e70914df46\n",
+            "torchaudio @ https://download.pytorch.org/whl/cu121/torchaudio-2.1.0%2Bcu121-cp310-cp310-linux_x86_64.whl#sha256=676bda4042734eda99bc59b2d7f761f345d3cde0cad492ad34e3aefde688c6d8\n",
+            "torchdata==0.7.0\n",
+            "torchsummary==1.5.1\n",
+            "torchtext==0.16.0\n",
+            "torchvision @ https://download.pytorch.org/whl/cu121/torchvision-0.16.0%2Bcu121-cp310-cp310-linux_x86_64.whl#sha256=e76e78d0ad43636c9884b3084ffaea8a8b61f21129fbfa456a5fe734f0affea9\n",
+            "tornado==6.3.3\n",
+            "tqdm==4.66.2\n",
+            "traitlets==5.7.1\n",
+            "traittypes==0.2.1\n",
+            "transformers==4.38.2\n",
+            "triton==2.1.0\n",
+            "tweepy==4.14.0\n",
+            "typer==0.9.0\n",
+            "types-pytz==2024.1.0.20240203\n",
+            "types-setuptools==69.1.0.20240302\n",
+            "typing_extensions==4.10.0\n",
+            "tzlocal==5.2\n",
+            "uc-micro-py==1.0.3\n",
+            "uritemplate==4.1.1\n",
+            "urllib3==2.0.7\n",
+            "vega-datasets==0.9.0\n",
+            "wadllib==1.3.6\n",
+            "wasabi==1.1.2\n",
+            "wcwidth==0.2.13\n",
+            "weasel==0.3.4\n",
+            "webcolors==1.13\n",
+            "webencodings==0.5.1\n",
+            "websocket-client==1.7.0\n",
+            "Werkzeug==3.0.1\n",
+            "widgetsnbextension==3.6.6\n",
+            "wordcloud==1.9.3\n",
+            "wrapt==1.14.1\n",
+            "xarray==2023.7.0\n",
+            "xarray-einstats==0.7.0\n",
+            "xgboost==2.0.3\n",
+            "xlrd==2.0.1\n",
+            "xxhash==3.4.1\n",
+            "xyzservices==2023.10.1\n",
+            "yarl==1.9.4\n",
+            "yellowbrick==1.5\n",
+            "yfinance==0.2.37\n",
+            "zict==3.0.0\n",
+            "zipp==3.17.0\n",
+            "ok\n"
+          ]
+        }
+      ]
     },
     {
       "cell_type": "code",
@@ -460,15 +996,15 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "jwcwJ__nPhx-",
-        "outputId": "1b3a2aec-5e3b-49be-d194-15ec8b690549"
+        "outputId": "9365e9d2-9243-4c75-a449-62ea1daed5b7"
       },
-      "execution_count": 3,
+      "execution_count": 8,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "start notebook: now is 2024-03-09 23:54:08.763804.\n",
+            "start notebook: now is 2024-03-10 18:17:30.651301.\n",
             "Mounted at /content/gdrive/\n"
           ]
         }
@@ -490,9 +1026,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "RHo4vB4tRQL8",
-        "outputId": "1c370348-41ae-4256-a372-24f2921e6de5"
+        "outputId": "54cfc19b-2568-4acd-daa8-52e1f31387f8"
       },
-      "execution_count": 4,
+      "execution_count": 9,
       "outputs": [
         {
           "output_type": "stream",
@@ -528,9 +1064,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "E_d_5lEKRzyo",
-        "outputId": "574f7f9a-37ca-47ba-acfa-4b7fe3f293a7"
+        "outputId": "81528d6f-9b0b-4854-f84b-ccc1e41755f0"
       },
-      "execution_count": 5,
+      "execution_count": 10,
       "outputs": [
         {
           "output_type": "stream",
@@ -544,7 +1080,7 @@
             "drwx------ 5 root root 4096 Mar  6 22:54 pip\n",
             "drwx------ 2 root root 4096 Mar  8 21:12 torch\n",
             "drwx------ 2 root root 4096 Mar  8 13:35 transformers\n",
-            "lrwxrwxrwx 1 root root 51 Mar  9 23:57 /root/.cache -> /content/gdrive/My Drive/lisa_on_gpu_folder/.cache/\n",
+            "lrwxrwxrwx 1 root root 51 Mar 10 18:17 /root/.cache -> /content/gdrive/My Drive/lisa_on_gpu_folder/.cache/\n",
             "ok\n"
           ]
         }
@@ -564,9 +1100,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "7C5Qjf6JMmGf",
-        "outputId": "1bdf565b-636e-4acb-a0a9-cb0abdb6fb10"
+        "outputId": "63dadc8f-7801-426d-dca2-6feb4d474073"
       },
-      "execution_count": 6,
+      "execution_count": 11,
       "outputs": [
         {
           "output_type": "stream",
@@ -612,9 +1148,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "rg7Hx-D06PI7",
-        "outputId": "5c86320a-1791-432c-f099-bbcb0e2ba2fa"
+        "outputId": "44338e58-9691-4dde-a9f4-eaaf70f8e4a0"
       },
-      "execution_count": 10,
+      "execution_count": 15,
       "outputs": [
         {
           "output_type": "stream",
@@ -828,9 +1364,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "LLQWY0bGO60Z",
-        "outputId": "9f0cb99b-3442-4b67-91a7-8ce84ba8000b"
+        "outputId": "d73ba5ab-10f3-4356-c077-2b4ecf966f63"
       },
-      "execution_count": 11,
+      "execution_count": 16,
       "outputs": [
         {
           "output_type": "stream",
@@ -1355,7 +1891,11 @@
       "source": [
         "%cd /content/lisa-on-cuda/\n",
         "\n",
-        "from utils import app_helpers, constants, utils\n",
+        "try:\n",
+        "  from lisa_on_cuda.utils import app_helpers, constants, utils\n",
+        "except KeyError as ke:\n",
+        "  print(ke)\n",
+        "  raise ke\n",
         "\n",
         "print(\"ok\")"
       ],
@@ -1364,9 +1904,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "5ZTfd2uu-ii0",
-        "outputId": "2fa1e9a8-9b61-4258-bda2-810a71de224a"
+        "outputId": "7fe562f2-2b9c-40e1-f7b7-8b3c53666d1e"
       },
-      "execution_count": 12,
+      "execution_count": 17,
       "outputs": [
         {
           "output_type": "stream",
@@ -1382,7 +1922,7 @@
       "cell_type": "code",
       "source": [
         "import logging\n",
-        "from utils import utils\n",
+        "from lisa_on_cuda.utils import utils\n",
         "import matplotlib.pyplot as plt\n",
         "\n",
         "logging.basicConfig(level=logging.INFO, force = True)\n",
@@ -1397,9 +1937,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "a8YNIvLRQePo",
-        "outputId": "21320288-5e2e-40ac-9dcd-f82bf593cb73"
+        "outputId": "7252dd85-f07d-48f8-e627-b635c2120fc1"
       },
-      "execution_count": 13,
+      "execution_count": 18,
       "outputs": [
         {
           "output_type": "stream",
@@ -1433,9 +1973,9 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "8957d1ed-9240-430e-f3dc-12724c40afd5"
+        "outputId": "8bb6ccbc-fddf-49d3-d6d9-f15c001bf55c"
       },
-      "execution_count": 14,
+      "execution_count": 19,
       "outputs": [
         {
           "output_type": "stream",
@@ -1462,23 +2002,23 @@
           "base_uri": "https://localhost:8080/",
           "height": 319,
           "referenced_widgets": [
-            "51413ef239f048eea0c9e2918cee48cc",
-            "b0266b1bb0954ca3a086af17d4710c61",
-            "9ef4c775d0ac42bb94e982ff22151968",
-            "cdf02b65bc574213bece3dd7bb447701",
-            "b12b23aeae5f4ccf9947c53018a227f1",
-            "f4db86625411496499a09155dcd107f2",
-            "62c9dd19d1cb414893f5d1d538834602",
-            "e665c80334da4da387339db1fa52d3c1",
-            "71434c95d69d4783bf2b27c50c641ff8",
-            "8d21439ee9ab437586b08cb7063c6a4b",
-            "cafa0b3fa2a74738a37559c521706e18"
+            "e968b46a1ecb485fa9f164f6ec0f5569",
+            "759af27e6e3e439f9a8739c470d9b4ed",
+            "5d5bd7bb543c44c48acb5a38d0e2b392",
+            "77f3526c940841ec8c3d3bb1da85dbc8",
+            "5eca36e7aa8a4775911eeb4c8684af6d",
+            "944fa9555ead4941aa855bbd35a4f5d7",
+            "2ad8fb9acc93495ca60d355ea4b0c161",
+            "a03fbfb4742342758d99d4354a9191e5",
+            "e7f6ff163e4846388f621f41ad287bfb",
+            "de68261aa80941afb2759b764aa10226",
+            "8d9f42c52f604fb590e77a3f5441ec09"
           ]
         },
         "id": "aJHut43ETK3P",
-        "outputId": "a1a8c0f1-041a-415b-feda-7cf0f7fb1f5d"
+        "outputId": "63e17ff8-44e0-4158-8e4b-6bcab33ccc78"
       },
-      "execution_count": 15,
+      "execution_count": 20,
       "outputs": [
         {
           "output_type": "stream",
@@ -1492,7 +2032,7 @@
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "start the creation of the inference function, now is 2024-03-10 00:01:36.865746.\n"
+            "start the creation of the inference function, now is 2024-03-10 18:22:28.101518.\n"
           ]
         },
         {
@@ -1517,7 +2057,7 @@
             "application/vnd.jupyter.widget-view+json": {
               "version_major": 2,
               "version_minor": 0,
-              "model_id": "51413ef239f048eea0c9e2918cee48cc"
+              "model_id": "e968b46a1ecb485fa9f164f6ec0f5569"
             }
           },
           "metadata": {}
@@ -1564,9 +2104,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "rtPoSzRMTOOH",
-        "outputId": "645155cf-ae53-4799-861f-df986799d477"
+        "outputId": "d7e36ba1-df0e-4dfc-9083-383f0d8ed4cf"
       },
-      "execution_count": 16,
+      "execution_count": 21,
       "outputs": [
         {
           "output_type": "stream",
@@ -1582,7 +2122,7 @@
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "start inference using inference_fn, now is 2024-03-10 00:09:37.344407.\n",
+            "start inference using inference_fn, now is 2024-03-10 18:34:33.689389.\n",
             "input_prompt:Where can the driver see the car speed in this image? Please output segmentation mask..\n"
           ]
         },
@@ -1628,12 +2168,12 @@
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
-          "height": 357
+          "height": 365
         },
         "id": "euOi0BKETQXG",
-        "outputId": "608a1fc6-b46b-47b9-f85b-5f8a724e0091"
+        "outputId": "40c339d4-28b2-4e39-ab15-f2f8198d76fe"
       },
-      "execution_count": 17,
+      "execution_count": 22,
       "outputs": [
         {
           "output_type": "stream",
@@ -1659,7 +2199,7 @@
       "source": [
         "import cv2\n",
         "from PIL import Image\n",
-        "from utils import utils\n",
+        "from lisa_on_cuda.utils import utils\n",
         "\n",
         "\"\"\"\n",
         "# current_example_path = str(utils.ROOT / \"tests\" / \"imgs\" / f\"example{idx_example+1}_mask_0.png\")\n",
@@ -1684,9 +2224,9 @@
           "height": 506
         },
         "id": "0PEXxxgwVRRn",
-        "outputId": "1c37aeef-7136-4e5a-d2cf-2556e047218b"
+        "outputId": "f3d69a09-159d-434f-f6d1-326cc862ea75"
       },
-      "execution_count": 18,
+      "execution_count": 23,
       "outputs": [
         {
           "output_type": "stream",
@@ -1707,11 +2247,11 @@
           "output_type": "execute_result",
           "data": {
             "text/plain": [
-              "<matplotlib.image.AxesImage at 0x7f50f06e7b50>"
+              "<matplotlib.image.AxesImage at 0x7b5921257c40>"
             ]
           },
           "metadata": {},
-          "execution_count": 18
+          "execution_count": 23
         },
         {
           "output_type": "display_data",
@@ -1769,9 +2309,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "sZy30KDUVVJ_",
-        "outputId": "d0537ff2-3cd5-4b7b-b30b-462ce56c2edd"
+        "outputId": "4efff579-535a-40af-dcec-bb475f1600d2"
       },
-      "execution_count": 19,
+      "execution_count": 24,
       "outputs": [
         {
           "output_type": "stream",
@@ -1797,16 +2337,16 @@
         "\n",
         "ls -l /root/.cache/huggingface/hub/models--xinlai--LISA*/*/*\n",
         "\n",
-        "echo \"end\""
+        "echo \"end!\""
       ],
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "d7HoGCK_6ePE",
-        "outputId": "afa551e3-9633-4143-b8e4-80ed2688aa89"
+        "outputId": "4a188f51-b1c1-4995-fc68-76cf06c65643"
       },
-      "execution_count": 20,
+      "execution_count": 25,
       "outputs": [
         {
           "output_type": "stream",
@@ -1854,15 +2394,15 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "W7fsszLV7YCK",
-        "outputId": "8c8c571c-7a82-49a8-9bed-c10f9bdec0fc"
+        "outputId": "0e78182a-fea7-48fa-eba1-544ac3150342"
       },
-      "execution_count": 21,
+      "execution_count": 26,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "start notebook: now is 2024-03-10 00:09:48.537763.\n"
+            "start notebook: now is 2024-03-10 18:34:45.188229.\n"
           ]
         }
       ]
@@ -1877,7 +2417,7 @@
       "metadata": {
         "id": "1h1eIdUibJXo"
       },
-      "execution_count": 22,
+      "execution_count": 27,
       "outputs": []
     }
   ]

pyproject.toml

@@ -0,0 +1,41 @@
+[tool.poetry]
+name = "lisa-on-cuda"
+version = "0.1.0"
+description = ""
+authors = ["alessandro trinca tornidor <[email protected]>"]
+license = "Apache 2.0"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+einops = "^0.7.0"
+fastapi = "^0.110.0"
+gradio = "^4.21.0"
+gradio-client = "^0.12.0"
+markdown2 = "^2.4.13"
+nh3 = "^0.2.15"
+numpy = "1.25.2"
+openai = "^1.13.3"
+packaging = "^24.0"
+peft = "^0.9.0"
+pycocotools = "^2.0.7"
+ray = "^2.9.3"
+scipy = "^1.11.4"
+sentencepiece = "^0.2.0"
+shortuuid = "^1.0.12"
+torch = "^2.2.1"
+torchvision = "^0.17.1"
+tqdm = "^4.66.2"
+transformers = "4.31.0"
+uvicorn = "^0.28.0"
+opencv-python-headless = "4.8.1.78"
+bitsandbytes = "^0.42.0"
+
+
+[tool.poetry.group.test.dependencies]
+pytest = "^8.1.1"
+pytest-cov = "^4.1.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"