EveryDream/AutoCaption.ipynb

{"cells":[{"cell_type":"markdown","metadata":{},"source":["# Please read the documentation here before you start.\n","[Auto Captioning](doc/AUTO_CAPTION.md)\n","\n","This notebook requires a GPU instance, any will do, you don't need anything power.  4GB is fine.\n","\n","Only colab has automatic file transfers at this time.  If you are using another platform, you will need to manually download your output files."]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":929,"status":"ok","timestamp":1667184580032,"user":{"displayName":"Victor Hall","userId":"00029068894644207946"},"user_tz":240},"id":"lWGx2LuU8Q_I","outputId":"d0eb4d03-f16d-460b-981d-d5f88447e85e"},"outputs":[],"source":["#download repo\n","!git clone https://github.com/victorchall/EveryDream.git\n","%cd EveryDream"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4944,"status":"ok","timestamp":1667184754992,"user":{"displayName":"Victor Hall","userId":"00029068894644207946"},"user_tz":240},"id":"RJxfSai-8pkD","outputId":"0ac1b805-62a0-48aa-e0da-ee19503bb3f1"},"outputs":[],"source":["# install requirements\n","!pip install torch=='1.12.1+cu113' 'torchvision==0.13.1+cu113' --extra-index-url https://download.pytorch.org/whl/cu113\n","!pip install pandas>='1.3.5'\n","!git clone https://github.com/salesforce/BLIP scripts/BLIP\n","!pip install timm\n","!pip install fairscale=='0.4.4'\n","!pip install transformers=='4.19.2'\n","!pip install timm"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":383,"status":"ok","timestamp":1667185773878,"user":{"displayName":"Victor Hall","userId":"00029068894644207946"},"user_tz":240},"id":"ruRaJ7Cx9vhw","outputId":"f0701d3e-bfa9-45a9-a742-c3615466aad7"},"outputs":[],"source":["# make folders for input and output\n","!mkdir input\n","!mkdir output\n","!mkdir .cache"]},{"cell_type":"markdown","metadata":{"id":"sbeUIVXJ-EVf"},"source":["# Upload your input images into the EveryDream/input folder\n","\n","![upload to input](demo/upload_images_caption.png)"]},{"cell_type":"markdown","metadata":{},"source":["## Please read the documentation here for information on the parameters\n","\n","[Auto Captioning](doc/AUTO_CAPTION.md)\n","\n","*You cannot have commented lines between uncommented lines.  If you uncomment a line below, move it above any other commented lines.*\n","\n","*!python must remain the first line.*"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":18221,"status":"ok","timestamp":1667185808005,"user":{"displayName":"Victor Hall","userId":"00029068894644207946"},"user_tz":240},"id":"4TAICahl-RPn","outputId":"da7fa1a8-0855-403a-c295-4da31658d1f6"},"outputs":[],"source":["!python scripts/auto_caption.py \\\n","--img_dir EveryDream/input \\\n","--out_dir EveryDream/output \\\n","#--fomat mrwho \\\n","#--min_length 34 \\\n","#--q_factor 1.3 \\\n","#--nucleus \\"]},{"cell_type":"markdown","metadata":{"id":"HBrWnu1C_lN9"},"source":["## Download your captioned images from EveryDream/output\n","\n","If you're on a colab you can use the cell below to push your output to your Gdrive."]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":["from google.colab import drive\n","drive.mount('/content/drive')\n","\n","!mkdir /content/drive/MyDrive/AutoCaption\n","!cp output/*.* /content/drive/MyDrive/AutoCaption"]},{"cell_type":"markdown","metadata":{},"source":["## If not on colab/gdrive, the following will zip up your files for extraction\n","\n","You'll still need to use your runtime's own download feature to download the zip.\n","\n","![output zip](demo/output_zip.png)"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":["!pip install patool\n","\n","import patoolib\n","\n","!mkdir output/zip\n","\n","!zip -r output/zip/output.zip output"]}],"metadata":{"colab":{"authorship_tag":"ABX9TyN9ZSr0RyOQKdfeVsl2uOiE","collapsed_sections":[],"provenance":[{"file_id":"16QrivRfoDFvE7fAa7eLeVlxj78Q573E0","timestamp":1667185879409}]},"kernelspec":{"display_name":"Python 3.10.5 ('.venv': venv)","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.10.5"},"vscode":{"interpreter":{"hash":"faf4a6abb601e3a9195ce3e9620411ceec233a951446de834cdf28542d2d93b4"}}},"nbformat":4,"nbformat_minor":0}