Tribev2 Brain Encoding

from tribev2 import TribeModel
# Load from HuggingFace (downloads weights to cache)model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")
# Build events dataframe from a video filedf = model.get_events_dataframe(video_path="path/to/video.mp4")
# Predict brain responsespreds, segments = model.predict(events=df)print(preds.shape)  # (n_timesteps, n_vertices) on fsaverage5

from tribev2 import TribeModel
model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")
# All modalities together (text is auto-converted to speech and transcribed)df = model.get_events_dataframe(    video_path="path/to/video.mp4",    audio_path="path/to/audio.wav",   # optional, overrides video audio    text_path="path/to/script.txt",   # optional, auto-timed)
preds, segments = model.predict(events=df)print(preds.shape)  # (n_timesteps, n_vertices)

from tribev2 import TribeModel
model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")
df = model.get_events_dataframe(text_path="path/to/narration.txt")preds, segments = model.predict(events=df)

from tribev2 import TribeModelfrom tribev2.plotting import plot_brain_surface
model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")df = model.get_events_dataframe(video_path="path/to/video.mp4")preds, segments = model.predict(events=df)
# Plot a single timepoint on the cortical surfaceplot_brain_surface(preds[0], backend="nilearn")   # or backend="pyvista"

from tribev2 import TribeModel
# Load pretrained weightsmodel = TribeModel.from_pretrained(    "facebook/tribev2",    cache_folder="./cache"  # local cache for HuggingFace weights)
# Build events dataframe (word-level timings, chunking, etc.)df = model.get_events_dataframe(    video_path=None,   # str path to .mp4    audio_path=None,   # str path to .wav    text_path=None,    # str path to .txt)
# Run predictionpreds, segments = model.predict(events=df)# preds: np.ndarray of shape (n_timesteps, n_vertices)# segments: list of segment metadata dicts

# tribev2/grids/defaults.py (key fields){    "datapath": "/path/to/studies",       # override with DATAPATH env var    "savepath": "/path/to/output",        # override with SAVEPATH env var    "slurm_partition": "learnfair",       # override with SLURM_PARTITION env var    "model": "FmriEncoder",    "modalities": ["video", "audio", "text"],    "surface": "fsaverage5",              # ~20k vertices}

from tribev2.main import Data, TribeExperimentfrom tribev2.pl_module import TribePLModuleimport pytorch_lightning as pl
# Configure experimentexperiment = TribeExperiment(    datapath="/path/to/studies",    savepath="/path/to/output",    modalities=["video", "audio", "text"],)
data = Data(experiment)module = TribePLModule(experiment)
trainer = pl.Trainer(    max_epochs=50,    accelerator="gpu",    devices=4,)trainer.fit(module, data)

from tribev2.utils_fmri import project_to_fsaverage, get_roi_mask
# Project MNI coordinates to fsaverage5 surfacesurface_data = project_to_fsaverage(mni_data, target="fsaverage5")
# Get a specific ROI mask (e.g., early visual cortex)roi_mask = get_roi_mask(roi_name="V1", surface="fsaverage5")v1_responses = preds[:, roi_mask]print(v1_responses.shape)  # (n_timesteps, n_v1_vertices)

from tribev2 import TribeModelimport numpy as np
model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")
video_paths = ["video1.mp4", "video2.mp4", "video3.mp4"]all_predictions = []
for vp in video_paths:    df = model.get_events_dataframe(video_path=vp)    preds, segments = model.predict(events=df)    all_predictions.append(preds)
# all_predictions: list of (n_timesteps_i, n_vertices) arrays

from tribev2 import TribeModelfrom tribev2.utils_fmri import get_roi_mask
model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")df = model.get_events_dataframe(video_path="video.mp4")preds, segments = model.predict(events=df)
# Focus on auditory cortexac_mask = get_roi_mask("auditory_cortex", surface="fsaverage5")auditory_responses = preds[:, ac_mask]  # (n_timesteps, n_ac_vertices)

preds, segments = model.predict(events=df)
for i, seg in enumerate(segments):    print(f"Segment {i}: onset={seg['onset']:.2f}s, duration={seg['duration']:.2f}s")    print(f"  Brain response shape: {preds[i].shape}")

# Use CPU for inference on smaller machinesimport torchmodel = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")model.to("cpu")

# Provide audio separately or use text-only modedf = model.get_events_dataframe(    video_path="silent_video.mp4",    audio_path="separate_audio.wav",)