Upload folder using huggingface_hub

.gitignore

@@ -1,5 +1,4 @@
 data/
-models/*
-!models/model.safetensors
+models/
 
 __pycache__

README.md

@@ -6,9 +6,17 @@ sdk_version: 4.16.0
 ---
 # パルワールドで最もポケモンに似ているパルは何か？
 
-## Run gradio
+## Run gradio on local
 
 ```powershell
-conda activate til-machine-learning
+conda env create -f environment.yml
+conda activate pokemon-pal
 python app.py
 ```
+
+## Deploy gradio
+
+```powershell
+conda activate pokemon-pal
+gradio deploy
+```

environment.yml

@@ -0,0 +1,321 @@
+
+name: pokemon-pal
+channels:
+  - pytorch
+  - nvidia
+  - microsoft
+  - conda-forge
+  - defaults
+dependencies:
+  - aiofiles=23.2.1=pyhd8ed1ab_0
+  - aiohttp=3.9.1=py311ha68e1ae_0
+  - aiosignal=1.3.1=pyhd8ed1ab_0
+  - altair=5.2.0=pyhd8ed1ab_0
+  - annotated-types=0.6.0=pyhd8ed1ab_0
+  - anyio=3.7.1=pyhd8ed1ab_0
+  - aom=3.7.1=h63175ca_0
+  - asttokens=2.4.1=pyhd8ed1ab_0
+  - attrs=23.2.0=pyh71513ae_0
+  - aws-c-auth=0.7.11=hcf9e330_1
+  - aws-c-cal=0.6.9=hd33547d_3
+  - aws-c-common=0.9.12=hcfcfb64_0
+  - aws-c-compression=0.2.17=hd33547d_8
+  - aws-c-event-stream=0.4.1=h875930a_2
+  - aws-c-http=0.8.0=ha1a3518_2
+  - aws-c-io=0.14.0=hf372335_1
+  - aws-c-mqtt=0.10.1=hda1dad8_0
+  - aws-c-s3=0.4.9=hef93162_0
+  - aws-c-sdkutils=0.1.13=hd33547d_1
+  - aws-checksums=0.1.17=hd33547d_7
+  - aws-crt-cpp=0.26.0=hed7b20b_8
+  - aws-sdk-cpp=1.11.210=h20b5662_10
+  - beartype=0.17.0=pyhd8ed1ab_0
+  - beautifulsoup4=4.12.3=pyha770c72_0
+  - blas=2.121=mkl
+  - blas-devel=3.9.0=21_win64_mkl
+  - brotli=1.1.0=hcfcfb64_1
+  - brotli-bin=1.1.0=hcfcfb64_1
+  - brotli-python=1.1.0=py311h12c1d0e_1
+  - bs4=4.12.3=hd8ed1ab_0
+  - bzip2=1.0.8=hcfcfb64_5
+  - c-ares=1.26.0=hcfcfb64_0
+  - ca-certificates=2023.11.17=h56e8100_0
+  - cairo=1.18.0=h1fef639_0
+  - certifi=2023.11.17=pyhd8ed1ab_0
+  - charset-normalizer=3.3.2=pyhd8ed1ab_0
+  - click=8.1.7=win_pyh7428d3b_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - comm=0.2.1=pyhd8ed1ab_0
+  - contourpy=1.2.0=py311h005e61a_0
+  - cuda-cccl=12.3.101=0
+  - cuda-cudart=12.1.105=0
+  - cuda-cudart-dev=12.1.105=0
+  - cuda-cupti=12.1.105=0
+  - cuda-libraries=12.1.0=0
+  - cuda-libraries-dev=12.1.0=0
+  - cuda-nvrtc=12.1.105=0
+  - cuda-nvrtc-dev=12.1.105=0
+  - cuda-nvtx=12.1.105=0
+  - cuda-opencl=12.3.101=0
+  - cuda-opencl-dev=12.3.101=0
+  - cuda-profiler-api=12.3.101=0
+  - cuda-runtime=12.1.0=0
+  - cycler=0.12.1=pyhd8ed1ab_0
+  - datasets=2.14.4=pyhd8ed1ab_0
+  - dav1d=1.2.1=hcfcfb64_0
+  - debugpy=1.8.0=py311h12c1d0e_1
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - dill=0.3.7=pyhd8ed1ab_0
+  - exceptiongroup=1.2.0=pyhd8ed1ab_2
+  - executing=2.0.1=pyhd8ed1ab_0
+  - expat=2.5.0=h63175ca_1
+  - ffmpeg=6.1.1=gpl_hadb5375_101
+  - ffmpy=0.3.0=pyhb6f538c_0
+  - filelock=3.13.1=pyhd8ed1ab_0
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=h77eed37_1
+  - fontconfig=2.14.2=hbde0cde_0
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - fonttools=4.47.2=py311ha68e1ae_0
+  - freetype=2.12.1=hdaf720e_2
+  - frozenlist=1.4.1=py311ha68e1ae_0
+  - fsspec=2023.12.2=pyhca7485f_0
+  - gettext=0.21.1=h5728263_0
+  - glib=2.78.3=h12be248_0
+  - glib-tools=2.78.3=h12be248_0
+  - gradio=4.16.0=pyhd8ed1ab_0
+  - gradio-client=0.8.1=pyhd8ed1ab_0
+  - graphite2=1.3.13=1000
+  - gst-plugins-base=1.22.9=h001b923_0
+  - gstreamer=1.22.9=hb4038d2_0
+  - h11=0.14.0=pyhd8ed1ab_0
+  - h2=4.1.0=pyhd8ed1ab_0
+  - harfbuzz=8.3.0=h7ab893a_0
+  - hpack=4.0.0=pyh9f0ad1d_0
+  - httpcore=1.0.2=pyhd8ed1ab_0
+  - httpx=0.26.0=pyhd8ed1ab_0
+  - huggingface_hub=0.20.2=pyhd8ed1ab_0
+  - hyperframe=6.0.1=pyhd8ed1ab_0
+  - icu=73.2=h63175ca_0
+  - idna=3.6=pyhd8ed1ab_0
+  - importlib-metadata=7.0.1=pyha770c72_0
+  - importlib-resources=6.1.1=pyhd8ed1ab_0
+  - importlib_metadata=7.0.1=hd8ed1ab_0
+  - importlib_resources=6.1.1=pyhd8ed1ab_0
+  - intel-openmp=2024.0.0=h57928b3_49841
+  - ipykernel=6.29.0=pyha63f2e9_0
+  - ipython=8.20.0=pyh7428d3b_0
+  - jedi=0.19.1=pyhd8ed1ab_0
+  - jinja2=3.1.3=pyhd8ed1ab_0
+  - joblib=1.3.2=pyhd8ed1ab_0
+  - jsonschema=4.21.1=pyhd8ed1ab_0
+  - jsonschema-specifications=2023.12.1=pyhd8ed1ab_0
+  - jupyter_client=8.6.0=pyhd8ed1ab_0
+  - jupyter_core=5.7.1=py311h1ea47a8_0
+  - kiwisolver=1.4.5=py311h005e61a_1
+  - krb5=1.21.2=heb0366b_0
+  - lcms2=2.16=h67d730c_0
+  - lerc=4.0.0=h63175ca_0
+  - libabseil=20230802.1=cxx17_h63175ca_0
+  - libarrow=14.0.2=he5f67d5_2_cpu
+  - libarrow-acero=14.0.2=h63175ca_2_cpu
+  - libarrow-dataset=14.0.2=h63175ca_2_cpu
+  - libarrow-flight=14.0.2=h53b1db0_2_cpu
+  - libarrow-flight-sql=14.0.2=h78eab7c_2_cpu
+  - libarrow-gandiva=14.0.2=hb2eaab1_2_cpu
+  - libarrow-substrait=14.0.2=hd4c9904_2_cpu
+  - libblas=3.9.0=21_win64_mkl
+  - libbrotlicommon=1.1.0=hcfcfb64_1
+  - libbrotlidec=1.1.0=hcfcfb64_1
+  - libbrotlienc=1.1.0=hcfcfb64_1
+  - libcblas=3.9.0=21_win64_mkl
+  - libclang=15.0.7=default_hde6756a_4
+  - libclang13=15.0.7=default_h85b4d89_4
+  - libcrc32c=1.1.2=h0e60522_0
+  - libcublas=12.1.0.26=0
+  - libcublas-dev=12.1.0.26=0
+  - libcufft=11.0.2.4=0
+  - libcufft-dev=11.0.2.4=0
+  - libcurand=10.3.4.107=0
+  - libcurand-dev=10.3.4.107=0
+  - libcurl=8.5.0=hd5e4a3a_0
+  - libcusolver=11.4.4.55=0
+  - libcusolver-dev=11.4.4.55=0
+  - libcusparse=12.0.2.55=0
+  - libcusparse-dev=12.0.2.55=0
+  - libdeflate=1.19=hcfcfb64_0
+  - libevent=2.1.12=h3671451_1
+  - libexpat=2.5.0=h63175ca_1
+  - libffi=3.4.2=h8ffe710_5
+  - libglib=2.78.3=h16e383f_0
+  - libgoogle-cloud=2.12.0=h39f2fc6_4
+  - libgrpc=1.59.3=h5bbd4a7_0
+  - libhwloc=2.9.3=default_haede6df_1009
+  - libiconv=1.17=hcfcfb64_2
+  - libjpeg-turbo=3.0.0=hcfcfb64_1
+  - liblapack=3.9.0=21_win64_mkl
+  - liblapacke=3.9.0=21_win64_mkl
+  - libnpp=12.0.2.50=0
+  - libnpp-dev=12.0.2.50=0
+  - libnvjitlink=12.1.105=0
+  - libnvjitlink-dev=12.1.105=0
+  - libnvjpeg=12.1.1.14=0
+  - libnvjpeg-dev=12.1.1.14=0
+  - libogg=1.3.4=h8ffe710_1
+  - libopus=1.3.1=h8ffe710_1
+  - libparquet=14.0.2=h7ec3a38_2_cpu
+  - libpng=1.6.39=h19919ed_0
+  - libprotobuf=4.24.4=hb8276f3_0
+  - libre2-11=2023.06.02=h8c5ae5e_0
+  - libsodium=1.0.18=h8d14728_1
+  - libsqlite=3.44.2=hcfcfb64_0
+  - libssh2=1.11.0=h7dfc565_0
+  - libthrift=0.19.0=ha2b3283_1
+  - libtiff=4.6.0=h6e2ebb7_2
+  - libutf8proc=2.8.0=h82a8f57_0
+  - libuv=1.44.2=hcfcfb64_1
+  - libvorbis=1.3.7=h0e60522_0
+  - libwebp-base=1.3.2=hcfcfb64_0
+  - libxcb=1.15=hcd874cb_0
+  - libxml2=2.12.4=hc3477c8_1
+  - libzlib=1.2.13=hcfcfb64_5
+  - lz4-c=1.9.4=hcfcfb64_0
+  - m2w64-gcc-libgfortran=5.3.0=6
+  - m2w64-gcc-libs=5.3.0=7
+  - m2w64-gcc-libs-core=5.3.0=7
+  - m2w64-gmp=6.1.0=2
+  - m2w64-libwinpthread-git=5.0.0.4634.697f757=2
+  - markdown-it-py=3.0.0=pyhd8ed1ab_0
+  - markupsafe=2.1.4=py311ha68e1ae_0
+  - matplotlib=3.8.2=py311h1ea47a8_0
+  - matplotlib-base=3.8.2=py311h6e989c2_0
+  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
+  - mdurl=0.1.2=pyhd8ed1ab_0
+  - mkl=2024.0.0=h66d3029_49657
+  - mkl-devel=2024.0.0=h57928b3_49657
+  - mkl-include=2024.0.0=h66d3029_49657
+  - mpmath=1.3.0=pyhd8ed1ab_0
+  - msys2-conda-epoch=20160418=1
+  - multidict=6.0.4=py311ha68e1ae_1
+  - multiprocess=0.70.15=py311ha68e1ae_1
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - nest-asyncio=1.6.0=pyhd8ed1ab_0
+  - networkx=3.2.1=pyhd8ed1ab_0
+  - numpy=1.26.3=py311h0b4df5a_0
+  - openh264=2.4.0=h63175ca_0
+  - openjpeg=2.5.0=h3d672ee_3
+  - openssl=3.2.0=hcfcfb64_1
+  - orc=1.9.2=hf0b6bd4_0
+  - orjson=3.9.10=py311h5443569_0
+  - packaging=23.2=pyhd8ed1ab_0
+  - pandas=2.2.0=py311hf63dbb6_0
+  - parso=0.8.3=pyhd8ed1ab_0
+  - pcre2=10.42=h17e33f8_0
+  - pickleshare=0.7.5=py_1003
+  - pip=23.3.2=pyhd8ed1ab_0
+  - pixman=0.43.0=h63175ca_0
+  - pkgutil-resolve-name=1.3.10=pyhd8ed1ab_1
+  - platformdirs=4.1.0=pyhd8ed1ab_0
+  - ply=3.11=py_1
+  - prompt-toolkit=3.0.42=pyha770c72_0
+  - psutil=5.9.8=py311ha68e1ae_0
+  - pthread-stubs=0.4=hcd874cb_1001
+  - pthreads-win32=2.9.1=hfa6e2cd_3
+  - pure_eval=0.2.2=pyhd8ed1ab_0
+  - pyarrow=14.0.2=py311h6a6099b_2_cpu
+  - pydantic=2.5.3=pyhd8ed1ab_0
+  - pydantic-core=2.14.6=py311hc37eb10_1
+  - pydub=0.25.1=pyhd8ed1ab_0
+  - pygments=2.17.2=pyhd8ed1ab_0
+  - pyparsing=3.1.1=pyhd8ed1ab_0
+  - pyqt=5.15.9=py311h125bc19_5
+  - pyqt5-sip=12.12.2=py311h12c1d0e_5
+  - pysocks=1.7.1=pyh0701188_6
+  - python=3.11.7=h2628c8c_1_cpython
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python-multipart=0.0.6=pyhd8ed1ab_0
+  - python-tzdata=2023.4=pyhd8ed1ab_0
+  - python-xxhash=3.4.1=py311ha68e1ae_0
+  - python_abi=3.11=4_cp311
+  - pytorch=2.1.2=py3.11_cuda12.1_cudnn8_0
+  - pytorch-cuda=12.1=hde6ce7c_5
+  - pytorch-mutex=1.0=cuda
+  - pytz=2023.3.post1=pyhd8ed1ab_0
+  - pywin32=306=py311h12c1d0e_2
+  - pyyaml=6.0.1=py311ha68e1ae_1
+  - pyzmq=25.1.2=py311h9250fbb_0
+  - qt-main=5.15.8=h9e85ed6_18
+  - re2=2023.06.02=hcbb65ff_0
+  - referencing=0.32.1=pyhd8ed1ab_0
+  - regex=2023.12.25=py311ha68e1ae_0
+  - requests=2.31.0=pyhd8ed1ab_0
+  - rich=13.7.0=pyhd8ed1ab_0
+  - rpds-py=0.17.1=py311hc37eb10_0
+  - ruff=0.1.14=py311hc14472d_1
+  - safetensors=0.3.3=py311hc37eb10_1
+  - scikit-learn=1.4.0=py311h142b183_0
+  - scipy=1.12.0=py311h0b4df5a_2
+  - semantic_version=2.10.0=pyhd8ed1ab_0
+  - setuptools=69.0.3=pyhd8ed1ab_0
+  - shellingham=1.5.4=pyhd8ed1ab_0
+  - sip=6.7.12=py311h12c1d0e_0
+  - six=1.16.0=pyh6c4a22f_0
+  - snappy=1.1.10=hfb803bf_0
+  - sniffio=1.3.0=pyhd8ed1ab_0
+  - soupsieve=2.5=pyhd8ed1ab_1
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - svt-av1=1.8.0=h63175ca_0
+  - sympy=1.12=pyh04b8f61_3
+  - tbb=2021.11.0=h91493d7_1
+  - threadpoolctl=3.2.0=pyha21a80b_0
+  - tk=8.6.13=h5226925_1
+  - tokenizers=0.15.1=py311h91c4a10_0
+  - toml=0.10.2=pyhd8ed1ab_0
+  - tomli=2.0.1=pyhd8ed1ab_0
+  - tomlkit=0.12.0=pyha770c72_0
+  - toolz=0.12.1=pyhd8ed1ab_0
+  - tornado=6.3.3=py311ha68e1ae_1
+  - tqdm=4.66.1=pyhd8ed1ab_0
+  - traitlets=5.14.1=pyhd8ed1ab_0
+  - transformers=4.37.1=pyhd8ed1ab_0
+  - typer=0.9.0=pyhd8ed1ab_0
+  - typing-extensions=4.9.0=hd8ed1ab_0
+  - typing_extensions=4.9.0=pyha770c72_0
+  - tzdata=2023d=h0c530f3_0
+  - ucrt=10.0.22621.0=h57928b3_0
+  - urllib3=2.1.0=pyhd8ed1ab_0
+  - vc=14.3=hcf57466_18
+  - vc14_runtime=14.38.33130=h82b7239_18
+  - vs2015_runtime=14.38.33130=hcb4865c_18
+  - wcwidth=0.2.13=pyhd8ed1ab_0
+  - websockets=11.0.3=py311ha68e1ae_1
+  - wheel=0.42.0=pyhd8ed1ab_0
+  - win_inet_pton=1.1.0=pyhd8ed1ab_6
+  - x264=1!164.3095=h8ffe710_2
+  - x265=3.5=h2d74725_3
+  - xorg-libxau=1.0.11=hcd874cb_0
+  - xorg-libxdmcp=1.1.3=hcd874cb_0
+  - xxhash=0.8.2=hcfcfb64_0
+  - xz=5.2.6=h8d14728_0
+  - yaml=0.2.5=h8ffe710_2
+  - yarl=1.9.4=py311ha68e1ae_0
+  - zeromq=4.3.5=h63175ca_0
+  - zipp=3.17.0=pyhd8ed1ab_0
+  - zlib=1.2.13=hcfcfb64_5
+  - zstd=1.5.5=h12be248_0
+  - pip:
+      - carvekit==4.1.1
+      - fastapi==0.108.0
+      - loguru==0.7.2
+      - opencv-python==4.8.1.78
+      - pillow==10.1.0
+      - starlette==0.32.0.post1
+      - torchaudio==2.1.2
+      - torchvision==0.16.2
+      - typing==3.7.4.3
+      - uvicorn==0.25.0
+      - win32-setctime==1.1.0
+

notebooks/crop.ipynb

@@ -61,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -113,30 +113,6 @@
     "show_bounding_boxes('../data/nobg/ポケットモンスターシールド/2020022922273500_s.png')\n"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n"
-     ]
-    }
-   ],
-   "source": [
-    "file_path = '../data/nobg/every-pal-in-palworld-a-complete-paldeck-list/016 Palworld Teafant.png.png'\n",
-    "\n",
-    "image_pil = Image.open(file_path)\n",
-    "image = np.array(image_pil)\n",
-    "\n",
-    "# Get the bounding boxes of the objects in the image\n",
-    "contours = get_object_bounding_boxes(image)\n",
-    "print(contours)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -145,8 +121,8 @@
    "source": [
     "import os\n",
     "\n",
-    "input_dir = \"../data/nobg\"\n",
-    "output_dir = \"../data/cropped\"\n",
+    "input_dir = \"../data/nobg/ポケモン公式\"\n",
+    "output_dir = \"../data/cropped/ポケモン公式\"\n",
     "\n",
     "def get_max_bounding_rect(contours):\n",
     "    if len(contours) == 0:\n",

notebooks/nobg.ipynb

@@ -2,20 +2,9 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\hiroga\\miniconda3\\envs\\pokemon-pal\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
-      "c:\\Users\\hiroga\\miniconda3\\envs\\pokemon-pal\\Lib\\site-packages\\torchvision\\transforms\\functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import torch\n",
     "from carvekit.api.high import HiInterface\n",

notebooks/train.ipynb

@@ -196,12 +196,12 @@
     "        test_losses.append(running_test_loss/len(test_loader))\n",
     "        print(f\"Epoch {epoch+1}: Train Loss = {train_losses[-1]}, Test Loss = {test_losses[-1]}\")\n",
     "        \n",
-    "        # Save the model\n",
-    "        model_dir = '../models/'\n",
-    "        if not os.path.exists(model_dir):\n",
-    "            os.makedirs(model_dir)\n",
-    "        tensors = {name: param for name, param in model.named_parameters()}\n",
-    "        save_file(tensors, f\"{model_dir}SimpleCNN_{epoch+1}_{data_dir.replace('.', '').replace('/', '_')}_{image_size}x{image_size}.safetensors\")\n",
+    "    # Save the model\n",
+    "    model_dir = '../models/'\n",
+    "    if not os.path.exists(model_dir):\n",
+    "        os.makedirs(model_dir)\n",
+    "    tensors = {name: param for name, param in model.named_parameters()}\n",
+    "    save_file(tensors, f\"{model_dir}SimpleCNN_{epoch+1}_{data_dir.replace('.', '').replace('/', '_')}_{image_size}x{image_size}.safetensors\")\n",
     "    save_file(tensors, f\"{model_dir}model.safetensors\")\n",
     "\n",
     "    # Plotting the losses\n",