{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/hanbk/torch_venv/lib/python3.8/site-packages/IPython/core/display.py:419: UserWarning: Consider using IPython.display.IFrame instead\n", " warnings.warn(\"Consider using IPython.display.IFrame instead\")\n" ] }, { "data": { "text/html": [ "" ], "text/plain": [ "" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from IPython.display import HTML\n", "\n", "HTML(\n", " ''\n", ")" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "import argparse\n", "import os\n", "import random\n", "import time\n", "from distutils.util import strtobool\n", "\n", "import gym\n", "import numpy as np\n", "import torch\n", "import torch.nn as nn\n", "import torch.optim as optim\n", "from torch.distributions.categorical import Categorical\n", "from torch.utils.tensorboard import SummaryWriter\n", "\n", "from huggingface_hub import HfApi, upload_folder\n", "from huggingface_hub.repocard import metadata_eval_result, metadata_save\n", "\n", "from pathlib import Path\n", "import datetime\n", "import tempfile\n", "import json\n", "import shutil\n", "import imageio\n", "\n", "from wasabi import Printer\n", "\n", "msg = Printer()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "def parse_args():\n", " # fmt: off\n", " parser = argparse.ArgumentParser()\n", " parser.add_argument(\"--exp-name\", type=str, default=os.path.basename(__file__).rstrip(\".py\"),\n", " help=\"the name of this experiment\")\n", " parser.add_argument(\"--seed\", type=int, default=1,\n", " help=\"seed of the experiment\")\n", " parser.add_argument(\"--torch-deterministic\", type=lambda x: bool(strtobool(x)), default=True, nargs=\"?\", const=True,\n", " help=\"if toggled, `torch.backends.cudnn.deterministic=False`\")\n", " parser.add_argument(\"--cuda\", type=lambda x: bool(strtobool(x)), default=True, nargs=\"?\", const=True,\n", " help=\"if toggled, cuda will be enabled by default\")\n", " parser.add_argument(\"--track\", type=lambda x: bool(strtobool(x)), default=False, nargs=\"?\", const=True,\n", " help=\"if toggled, this experiment will be tracked with Weights and Biases\")\n", " parser.add_argument(\"--wandb-project-name\", type=str, default=\"cleanRL\",\n", " help=\"the wandb's project name\")\n", " parser.add_argument(\"--wandb-entity\", type=str, default=None,\n", " help=\"the entity (team) of wandb's project\")\n", " parser.add_argument(\"--capture-video\", type=lambda x: bool(strtobool(x)), default=False, nargs=\"?\", const=True,\n", " help=\"weather to capture videos of the agent performances (check out `videos` folder)\")\n", "\n", " # Algorithm specific arguments\n", " parser.add_argument(\"--env-id\", type=str, default=\"CartPole-v1\",\n", " help=\"the id of the environment\")\n", " parser.add_argument(\"--total-timesteps\", type=int, default=50000,\n", " help=\"total timesteps of the experiments\")\n", " parser.add_argument(\"--learning-rate\", type=float, default=2.5e-4,\n", " help=\"the learning rate of the optimizer\")\n", " parser.add_argument(\"--num-envs\", type=int, default=4,\n", " help=\"the number of parallel game environments\")\n", " parser.add_argument(\"--num-steps\", type=int, default=128,\n", " help=\"the number of steps to run in each environment per policy rollout\")\n", " parser.add_argument(\"--anneal-lr\", type=lambda x: bool(strtobool(x)), default=True, nargs=\"?\", const=True,\n", " help=\"Toggle learning rate annealing for policy and value networks\")\n", " parser.add_argument(\"--gae\", type=lambda x: bool(strtobool(x)), default=True, nargs=\"?\", const=True,\n", " help=\"Use GAE for advantage computation\")\n", " parser.add_argument(\"--gamma\", type=float, default=0.99,\n", " help=\"the discount factor gamma\")\n", " parser.add_argument(\"--gae-lambda\", type=float, default=0.95,\n", " help=\"the lambda for the general advantage estimation\")\n", " parser.add_argument(\"--num-minibatches\", type=int, default=4,\n", " help=\"the number of mini-batches\")\n", " parser.add_argument(\"--update-epochs\", type=int, default=4,\n", " help=\"the K epochs to update the policy\")\n", " parser.add_argument(\"--norm-adv\", type=lambda x: bool(strtobool(x)), default=True, nargs=\"?\", const=True,\n", " help=\"Toggles advantages normalization\")\n", " parser.add_argument(\"--clip-coef\", type=float, default=0.2,\n", " help=\"the surrogate clipping coefficient\")\n", " parser.add_argument(\"--clip-vloss\", type=lambda x: bool(strtobool(x)), default=True, nargs=\"?\", const=True,\n", " help=\"Toggles whether or not to use a clipped loss for the value function, as per the paper.\")\n", " parser.add_argument(\"--ent-coef\", type=float, default=0.01,\n", " help=\"coefficient of the entropy\")\n", " parser.add_argument(\"--vf-coef\", type=float, default=0.5,\n", " help=\"coefficient of the value function\")\n", " parser.add_argument(\"--max-grad-norm\", type=float, default=0.5,\n", " help=\"the maximum norm for the gradient clipping\")\n", " parser.add_argument(\"--target-kl\", type=float, default=None,\n", " help=\"the target KL divergence threshold\")\n", "\n", " # Adding HuggingFace argument\n", " parser.add_argument(\"--repo-id\", type=str, default=\"ThomasSimonini/ppo-CartPole-v1\", help=\"id of the model repository from the Hugging Face Hub {username/repo_name}\")\n", "\n", " args = parser.parse_args()\n", " args.batch_size = int(args.num_envs * args.num_steps)\n", " args.minibatch_size = int(args.batch_size // args.num_minibatches)\n", " # fmt: on\n", " return args" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def package_to_hub(\n", " repo_id,\n", " model,\n", " hyperparameters,\n", " eval_env,\n", " video_fps=30,\n", " commit_message=\"Push agent to the Hub\",\n", " token=None,\n", " logs=None,\n", "):\n", " \"\"\"\n", " Evaluate, Generate a video and Upload a model to Hugging Face Hub.\n", " This method does the complete pipeline:\n", " - It evaluates the model\n", " - It generates the model card\n", " - It generates a replay video of the agent\n", " - It pushes everything to the hub\n", " :param repo_id: id of the model repository from the Hugging Face Hub\n", " :param model: trained model\n", " :param eval_env: environment used to evaluate the agent\n", " :param fps: number of fps for rendering the video\n", " :param commit_message: commit message\n", " :param logs: directory on local machine of tensorboard logs you'd like to upload\n", " \"\"\"\n", " msg.info(\n", " \"This function will save, evaluate, generate a video of your agent, \"\n", " \"create a model card and push everything to the hub. \"\n", " \"It might take up to 1min. \\n \"\n", " \"This is a work in progress: if you encounter a bug, please open an issue.\"\n", " )\n", " # Step 1: Clone or create the repo\n", " repo_url = HfApi().create_repo(\n", " repo_id=repo_id,\n", " token=token,\n", " private=False,\n", " exist_ok=True,\n", " )\n", "\n", " with tempfile.TemporaryDirectory() as tmpdirname:\n", " tmpdirname = Path(\"./\")\n", "\n", " # Step 2: Save the model\n", " torch.save(model.state_dict(), tmpdirname / \"model.pt\")\n", "\n", " # Step 3: Evaluate the model and build JSON\n", " mean_reward, std_reward = _evaluate_agent(eval_env, 10, model)\n", "\n", " # First get datetime\n", " eval_datetime = datetime.datetime.now()\n", " eval_form_datetime = eval_datetime.isoformat()\n", "\n", " evaluate_data = {\n", " \"env_id\": hyperparameters.env_id,\n", " \"mean_reward\": mean_reward,\n", " \"std_reward\": std_reward,\n", " \"n_evaluation_episodes\": 10,\n", " \"eval_datetime\": eval_form_datetime,\n", " }\n", "\n", " # Write a JSON file\n", " with open(tmpdirname / \"results.json\", \"w\") as outfile:\n", " json.dump(evaluate_data, outfile)\n", "\n", " # Step 4: Generate a video\n", " video_path = tmpdirname / \"replay.mp4\"\n", " record_video(eval_env, model, video_path, video_fps)\n", "\n", " # Step 5: Generate the model card\n", " generated_model_card, metadata = _generate_model_card(\n", " \"PPO\", hyperparameters.env_id, mean_reward, std_reward, hyperparameters\n", " )\n", " _save_model_card(tmpdirname, generated_model_card, metadata)\n", "\n", " # Step 6: Add logs if needed\n", " if logs:\n", " _add_logdir(tmpdirname, Path(logs))\n", "\n", " msg.info(f\"Pushing repo {repo_id} to the Hugging Face Hub\")\n", "\n", " repo_url = upload_folder(\n", " repo_id=repo_id,\n", " folder_path=tmpdirname,\n", " path_in_repo=\"\",\n", " commit_message=commit_message,\n", " token=token,\n", " )\n", "\n", " msg.info(f\"Your model is pushed to the Hub. You can view your model here: {repo_url}\")\n", " return repo_url" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3.8.10 ('torch_venv')", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.10" }, "orig_nbformat": 4, "vscode": { "interpreter": { "hash": "745a3b3e3fb7ac09f0ebb6d5eb47d006584e16db5d9df6f9a8b654baa561b29f" } } }, "nbformat": 4, "nbformat_minor": 2 }