9c7833faf9
* Vegetarian Filet o Fish model * fix.. atc.. * test cluster_speed_limit * fix.. cluster_speed_limit.. 2 * fix.. clusterspeedlimit3 * cruise speed to roadlimit speed * fix.. * fix.. eng * deltaUp/Down for lanechange * fix.. atc desire... * fix.. * ff * ff * fix.. * fix.. eng * fix engsound * Update desire_helper.py * fix.. connect... * fix curve_min speed * Revert "fix curve_min speed" This reverts commit fcc9c2eb14eb3504abef3e420db93e8882e56f37. * Reapply "fix curve_min speed" This reverts commit 2d2bba476c58a7b4e13bac3c3ad0e4694c95515d. * fix.. auto speed up.. roadlimit * fix.. atc auto lanechange... * Update desire_helper.py * Update cruise.py * debug atc... * fix.. waze alert offset.. * fix.. * test atc.. * fix.. * fix.. atc * atc test.. * fix.. atc * fix.. atc2 * fix.. atc3 * KerryGold Model. latsmooth_sec = 0.0 * lat smooth seconds 0.13 * fix comment * fix.. auto cruise, and speed unit * change lanemode switching. * erase mazda lkas button.
65 lines
3.2 KiB
Python
65 lines
3.2 KiB
Python
import time, sys, hashlib
|
|
from pathlib import Path
|
|
from onnx.helper import tensor_dtype_to_np_dtype
|
|
from tinygrad.frontend.onnx import OnnxRunner, onnx_load
|
|
from tinygrad import Tensor, dtypes, TinyJit
|
|
from tinygrad.helpers import IMAGE, GlobalCounters, fetch, colored, getenv, trange
|
|
from tinygrad.tensor import _from_np_dtype
|
|
import numpy as np
|
|
from extra.bench_log import BenchEvent, WallTimeEvent
|
|
|
|
OPENPILOT_MODEL = sys.argv[1] if len(sys.argv) > 1 else "https://github.com/commaai/openpilot/raw/v0.9.4/selfdrive/modeld/models/supercombo.onnx"
|
|
|
|
if __name__ == "__main__":
|
|
onnx_model = onnx_load(onnx_path := fetch(OPENPILOT_MODEL))
|
|
run_onnx = OnnxRunner(onnx_model)
|
|
|
|
Tensor.manual_seed(100)
|
|
input_shapes = {inp.name:tuple(x.dim_value for x in inp.type.tensor_type.shape.dim) for inp in onnx_model.graph.input}
|
|
input_types = {inp.name: tensor_dtype_to_np_dtype(inp.type.tensor_type.elem_type) for inp in onnx_model.graph.input}
|
|
new_inputs = {k:Tensor.randn(*shp, dtype=_from_np_dtype(input_types[k])).mul(8).realize() for k,shp in input_shapes.items()}
|
|
new_inputs_junk = {k:Tensor.randn(*shp, dtype=_from_np_dtype(input_types[k])).mul(8).realize() for k,shp in input_shapes.items()}
|
|
new_inputs_junk_numpy = {k:v.numpy() for k,v in new_inputs_junk.items()}
|
|
|
|
# benchmark
|
|
for _ in range(5):
|
|
GlobalCounters.reset()
|
|
st = time.perf_counter_ns()
|
|
ret = next(iter(run_onnx(new_inputs_junk).values())).cast(dtypes.float32).numpy()
|
|
print(f"unjitted: {(time.perf_counter_ns() - st)*1e-6:7.4f} ms")
|
|
|
|
# NOTE: the inputs to a JIT must be first level arguments
|
|
run_onnx_jit = TinyJit(lambda **kwargs: run_onnx(kwargs), prune=True)
|
|
for _ in range(20):
|
|
GlobalCounters.reset()
|
|
st = time.perf_counter_ns()
|
|
with WallTimeEvent(BenchEvent.STEP):
|
|
# Need to cast non-image inputs from numpy, this is only realistic way to run model
|
|
inputs = {**{k:v for k,v in new_inputs_junk.items() if 'img' in k},
|
|
**{k:Tensor(v) for k,v in new_inputs_junk_numpy.items() if 'img' not in k}}
|
|
ret = next(iter(run_onnx_jit(**inputs).values())).cast(dtypes.float32).numpy()
|
|
print(f"jitted: {(time.perf_counter_ns() - st)*1e-6:7.4f} ms")
|
|
|
|
suffix = ""
|
|
if IMAGE.value < 2: suffix += f"_image{IMAGE.value}" # image=2 has no suffix for compatibility
|
|
if getenv("FLOAT16") == 1: suffix += "_float16"
|
|
path = Path(__file__).parent / "openpilot" / f"{hashlib.md5(OPENPILOT_MODEL.encode()).hexdigest()}{suffix}.npy"
|
|
|
|
# validate if we have records
|
|
tinygrad_out = next(iter(run_onnx_jit(**new_inputs).values())).cast(dtypes.float32).numpy()
|
|
if getenv("SAVE_OUTPUT"):
|
|
np.save(path, tinygrad_out)
|
|
print(f"saved output to {path}!")
|
|
elif getenv("FUZZ") and path.exists():
|
|
known_good_out = np.load(path)
|
|
for _ in trange(1000):
|
|
ret = next(iter(run_onnx_jit(**new_inputs).values())).cast(dtypes.float32).numpy()
|
|
np.testing.assert_allclose(known_good_out, ret, atol=1e-2, rtol=1e-2)
|
|
print(colored("fuzz validated!", "green"))
|
|
elif path.exists():
|
|
known_good_out = np.load(path)
|
|
np.testing.assert_allclose(known_good_out, tinygrad_out, atol=1e-2, rtol=1e-2)
|
|
print(colored("outputs validated!", "green"))
|
|
else:
|
|
print(colored("skipping validation", "yellow"))
|