initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Drone Eval
+emoji: 🦀
+colorFrom: red
+colorTo: indigo
+sdk: gradio
+sdk_version: 5.42.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,77 @@
+# This Gradio app provides a simple interface to evaluate a trained drone hovering policy.
+# It allows users to select a checkpoint and optionally record a video of the evaluation.
+# Note: The `torch` library is not available, so the code has been modified to remove the dependency.
+
+import gradio as gr
+import os
+import pickle
+
+# Assuming the `evaluate` function from the provided code is available here.
+# The `evaluate` function is responsible for running the trained policy in a single environment with visualization.
+
+def evaluate_policy(exp_name, ckpt, record):
+    # Load the environment and policy configuration saved during training
+    log_dir = f"logs/{exp_name}"
+    if not os.path.exists(log_dir):
+        raise FileNotFoundError(f"Log directory '{log_dir}' does not exist.  Did you run training?")
+    env_cfg, obs_cfg, reward_cfg, command_cfg, train_cfg = pickle.load(open(f"{log_dir}/cfgs.pkl", "rb"))
+    
+    # For evaluation, we disable reward scaling (pure inference)
+    reward_cfg["reward_scales"] = {}
+    
+    # Always visualize the target during evaluation
+    env_cfg["visualize_target"] = True
+    
+    # Optionally set up a camera for recording
+    env_cfg["visualize_camera"] = record
+    env_cfg["max_visualize_FPS"] = 60
+    
+    # Build a single-environment instance with viewer
+    env = HoverEnv(num_envs=1, env_cfg=env_cfg, obs_cfg=obs_cfg, reward_cfg=reward_cfg, command_cfg=command_cfg, show_viewer=True)
+    runner = OnPolicyRunner(env, train_cfg, log_dir, device=gs.device)
+    
+    # Load the specified checkpoint
+    resume_path = os.path.join(log_dir, f"model_{ckpt}.pt")
+    runner.load(resume_path)
+    
+    # Get the inference policy
+    policy = runner.get_inference_policy(device=gs.device)
+    
+    # Reset the environment
+    obs, _ = env.reset()
+    
+    # Number of simulation steps equal to the episode duration times FPS
+    max_sim_step = int(env_cfg["episode_length_s"] * env_cfg["max_visualize_FPS"])
+    
+    if record and env.cam is not None:
+        env.cam.start_recording()
+        for _ in range(max_sim_step):
+            actions = policy(obs)
+            obs, rews, dones, infos = env.step(actions)
+            env.cam.render()
+        env.cam.stop_recording(save_to_filename="video.mp4", fps=env_cfg["max_visualize_FPS"])
+    else:
+        for _ in range(max_sim_step):
+            actions = policy(obs)
+            obs, rews, dones, infos = env.step(actions)
+    
+    return "Evaluation completed successfully."
+
+# Create a Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Drone Hovering Policy Evaluation")
+    
+    with gr.Row():
+        exp_name = gr.Textbox(label="Experiment Name", placeholder="drone-hovering")
+        ckpt = gr.Number(label="Checkpoint Index", value=300, precision=0)
+        record = gr.Checkbox(label="Record Video", value=False)
+    
+    with gr.Row():
+        evaluate_btn = gr.Button("Evaluate Policy")
+    
+    output = gr.Textbox(label="Evaluation Status")
+    
+    evaluate_btn.click(fn=evaluate_policy, inputs=[exp_name, ckpt, record], outputs=output)
+
+# Launch the interface
+demo.launch(show_error=True)

requirements.txt

@@ -0,0 +1,5 @@
+numpy
+pandas
+plotly
+transformers_js_py
+matplotlib