Spaces:
Sleeping
Sleeping
File size: 2,061 Bytes
0558e79 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
from octo.model.octo_model import OctoModel
from PIL import Image
import numpy as np
import jax
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
import os
import io
import base64
# Set JAX to use CPU platform (adjust if GPU is needed)
os.environ['JAX_PLATFORMS'] = 'cpu'
# Load the model once globally (assumes it's cached locally)
model = OctoModel.load_pretrained("hf://rail-berkeley/octo-small-1.5")
# Initialize FastAPI app
app = FastAPI(title="Octo Model Inference API")
# Define request body model
class InferenceRequest(BaseModel):
image_base64: str # Base64-encoded image string
task: str = "pick up the fork" # Default task
# Health check endpoint
@app.get("/health")
async def health_check():
return {"status": "healthy"}
# Inference endpoint
@app.post("/predict")
async def predict(request: InferenceRequest):
try:
# Decode base64 image
img_base64 = request.image_base64
if img_base64.startswith("data:image"):
img_base64 = img_base64.split(",")[1]
img_data = base64.b64decode(img_base64)
img = Image.open(io.BytesIO(img_data)).resize((256, 256))
img = np.array(img)
# Add batch and time horizon dimensions
img = img[np.newaxis, np.newaxis, ...] # Shape: (1, 1, 256, 256, 3)
observation = {
"image_primary": img,
"timestep_pad_mask": np.array([[True]])
}
# Create task and predict actions
task_obj = model.create_tasks(texts=[request.task])
actions = model.sample_actions(
observation,
task_obj,
unnormalization_statistics=model.dataset_statistics["bridge_dataset"]["action"],
rng=jax.random.PRNGKey(0)
)
actions = actions[0]
# Convert NumPy array to list for JSON response
actions_list = actions.tolist()
return {"actions": actions_list}
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error processing request: {str(e)}") |