InternVideo2.5 - Action Recognition

from gradio_client import Client
import json
import base64

client = Client("magboola/internvideo2-zerogpu")

# Prepare frames as base64-encoded JPEGs
frames_b64 = [base64.b64encode(frame_bytes).decode() for frame_bytes in frames]

# Optional: custom action candidates
custom_actions = ["scoring a goal", "making a tackle", "celebrating"]

result = client.predict(
    frames_base64=json.dumps(frames_b64),
    timestamp_s=5.0,
    action_candidates=json.dumps(custom_actions),
    api_name="/api_classify_action"
)
print(result)
# {"success": True, "action": "scoring a goal", "confidence": 0.9, ...}

result = client.predict(
    frames_base64=json.dumps(frames_b64),
    timestamp_s=5.0,
    action_candidates="",  # Empty for default actions
    api_name="/api_classify_action"
)