File size: 9,005 Bytes
51defdc 8eeb550 51defdc 8eeb550 51defdc | 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 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 | # SPDX-License-Identifier: Apache-2.0
"""Eager bring-up runners of the device stages, teacher-forced from the CPU-reference goldens
(``code/scripts/device_stage_check.py``; PLAN 4.4: every new stage eager x2 before any trace). Production and the
gated tests run the same stage modules through ``tt.model.TtMETEOR``'s traces."""
from __future__ import annotations
from typing import Any, Dict, Mapping
import numpy as np
from ..reference import config as C
from ..ttaw.metrics import pcc
from ..ttaw.ops.conv import FeatureMap
from .layers import Consts
from .unpack import split_det2d, to_reference
__all__ = ["STAGES", "compare_taps_to_golden", "read", "upload_rows", "golden_rows"]
def read(t: Any) -> np.ndarray:
import ttnn
a = ttnn.to_torch(t.tensor if isinstance(t, FeatureMap) else t)
return a.float().numpy() if a.is_floating_point() else a.numpy()
def golden_rows(nchw: np.ndarray) -> np.ndarray:
"""NCHW -> NHWC rows [1, 1, N*H*W, C] float32."""
a = np.asarray(nchw, np.float32)
n, c, h, w = a.shape
return np.ascontiguousarray(a.transpose(0, 2, 3, 1).reshape(1, 1, n * h * w, c))
def upload_rows(dev: Any, rows: np.ndarray, *, dtype: str = "bfloat16", layout: str = "tile", shape=None) -> Any:
import torch
import ttnn
from ..ttaw.tensors import ttnn_dtype
a = np.ascontiguousarray(rows if shape is None else rows.reshape(shape))
return ttnn.from_torch(torch.from_numpy(a), dtype=ttnn_dtype(dtype),
layout=ttnn.TILE_LAYOUT if layout == "tile" else ttnn.ROW_MAJOR_LAYOUT, device=dev,
memory_config=ttnn.DRAM_MEMORY_CONFIG)
def compare_taps_to_golden(taps: Mapping[str, np.ndarray], gold: Mapping[str, np.ndarray]) -> Dict[str, Any]:
"""PCC (float) / agreement (class maps) of every tap that has a golden; det2d merged maps are split."""
rows: Dict[str, Any] = {}
for k, v in taps.items():
if k.startswith("det2d_s"):
s = int(k[-1])
hm, reg = split_det2d(v, s)
for name, a in ((f"hm2d_s{s}", hm), (f"reg2d_s{s}", reg)):
rows[name] = {"pcc": round(float(pcc(a, gold[name])), 7),
"max_abs": float(np.abs(a - gold[name]).max())}
continue
if k not in gold:
continue
g = np.asarray(gold[k])
a = np.asarray(v)
if a.shape != g.shape and a.size == g.size:
a = a.reshape(g.shape)
if a.shape != g.shape:
rows[k] = {"error": f"shape {a.shape} vs golden {g.shape}"}
continue
if g.dtype == np.uint8 or g.dtype == np.bool_:
rows[k] = {"agreement": round(float((a == g).mean()), 7)}
else:
a64, g64 = a.astype(np.float64), g.astype(np.float64)
rows[k] = {"pcc": round(float(pcc(a64, g64)), 7), "max_abs": float(np.abs(a64 - g64).max()),
"ref_max": float(np.abs(g64).max())}
return rows
class _Stage:
def __init__(self, dev: Any, params: Any):
self.dev = dev
self.params = params
self.consts = Consts()
def release(self) -> None:
self.consts.release()
class ImageStage(_Stage):
"""uint8 cameras -> encoder + image heads (every tap)."""
def __init__(self, dev: Any, params: Any):
super().__init__(dev, params)
from .image import TtImageBranch
self.branch = TtImageBranch(params, self.consts)
self.shape = self.branch.img_shape # IMG_SHAPE, or whole rows with IMG_IN=rows
def run(self, gold: Mapping[str, np.ndarray]) -> Dict[str, np.ndarray]:
imgs = np.asarray(gold["input.imgs"], np.uint8)[0] # [8, 3, 432, 768]
rows = np.ascontiguousarray(imgs.transpose(0, 2, 3, 1).reshape(self.shape))
x = upload_rows(self.dev, rows, dtype="uint8", layout="row_major")
taps: Dict[str, Any] = {}
out = self.branch(x, taps=taps)
res = {k: to_reference(k, read(v)) for k, v in taps.items()}
for k in ("seg2d", "depth", "depth_mean", "det2d_s0", "det2d_s1", "det2d_s2", "tl"):
res[k] = to_reference(k, read(out[k]))
return res
def release(self) -> None:
self.branch.release()
super().release()
def nhwc_rows(nchw: np.ndarray, pad_to: int = 0) -> np.ndarray:
rows = golden_rows(nchw)
if pad_to and rows.shape[-1] < pad_to:
rows = np.concatenate([rows, np.zeros(rows.shape[:-1] + (pad_to - rows.shape[-1],), np.float32)], axis=-1)
return rows
class LiftStage(_Stage):
"""golden ctx.painted / depth.prob + the host lift tables -> lift.weight, lift.bev, bev.raw."""
def __init__(self, dev: Any, params: Any):
super().__init__(dev, params)
from .lift import TtLift
self.lift = TtLift(self.consts)
def run(self, gold: Mapping[str, np.ndarray]) -> Dict[str, np.ndarray]:
from ..host.calib import lift_geometry
from .lift import TABLE_NAMES, lift_tables
geom = lift_geometry(gold["input.K"], gold["input.T_cam_ego"], points=self.params.ground_points())
tb = lift_tables(geom)
ctx = np.asarray(gold["ctx.painted"], np.float32).transpose(0, 2, 3, 1)
prob = np.asarray(gold["depth.prob"], np.float32).transpose(0, 2, 3, 1)
d = self.dev
args = [upload_rows(d, ctx, layout="row_major"), upload_rows(d, prob, layout="row_major"),
upload_rows(d, tb["lift_grid"], dtype="float32", layout="row_major"),
[upload_rows(d, tb[name], dtype="float32") for name in TABLE_NAMES]]
taps: Dict[str, Any] = {}
raw = self.lift(*args, taps=taps)
taps["bev.raw"] = raw
return {k: to_reference(k, read(v)) for k, v in taps.items()}
def release(self) -> None:
self.lift.release()
super().release()
class BevStage(_Stage):
"""golden bev.raw -> BEV trunk and heads (every tap)."""
def __init__(self, dev: Any, params: Any):
super().__init__(dev, params)
from .bev import TtBev
self.bev = TtBev(params, self.consts)
def run(self, gold: Mapping[str, np.ndarray]) -> Dict[str, np.ndarray]:
raw = FeatureMap(upload_rows(self.dev, nhwc_rows(gold["bev.raw"])), 1, C.BEV_H, C.BEV_W, C.BEV_C)
taps: Dict[str, Any] = {}
out = self.bev(raw, taps=taps)
res = {k: to_reference(k, read(v)) for k, v in taps.items()}
res["bev.fused"] = to_reference("bev.fused", read(out["fused"]))
res["lane.pre"] = to_reference("lane.pre", read(out["lane_pre"]))
hr = to_reference("hm", read(out["hm_reg"]).reshape(-1, 8)[:, :2])
res["det.hm_pre"] = hr
res["det.reg_pre"] = to_reference("reg", read(out["hm_reg"]).reshape(-1, 8)[:, 2:8])
res["occ"] = to_reference("occ", read(out["occ"]))
res["traj"] = to_reference("traj", read(out["traj"]))
res["stationary"] = to_reference("stationary", read(out["stationary"]))
res["risk"] = to_reference("risk", read(out["risk32"]).reshape(-1, 32)[:, :1])
return res
def release(self) -> None:
self.bev.release()
super().release()
class HeadStage(_Stage):
"""golden bev.fused, lane.pre, det.hm_pre / reg_pre, risk, v0 -> planner, refiners, tail (every tap)."""
def __init__(self, dev: Any, params: Any):
super().__init__(dev, params)
from .head import TtHead
self.head = TtHead(params, self.consts)
def run(self, gold: Mapping[str, np.ndarray]) -> Dict[str, np.ndarray]:
d = self.dev
fused = FeatureMap(upload_rows(d, nhwc_rows(gold["bev.fused"])), 1, C.BEV_H, C.BEV_W, C.BEV_C)
lane_pre = FeatureMap(upload_rows(d, nhwc_rows(gold["lane.pre"]), dtype="float32"), 1, C.BEV_H, C.BEV_W, 9)
hr = np.concatenate([gold["det.hm_pre"], gold["det.reg_pre"]], axis=1)
hm_reg = FeatureMap(upload_rows(d, nhwc_rows(hr), dtype="float32"), 1, C.DET_H, C.DET_W, 8)
risk = FeatureMap(upload_rows(d, nhwc_rows(gold["risk"], 32), dtype="float32"), 1, C.DET_H, C.DET_W, 32)
v0 = upload_rows(d, np.asarray(gold["input.v0"], np.float32).reshape(1, 1, 1, 1), dtype="float32")
taps: Dict[str, Any] = {}
out = self.head(fused, lane_pre, hm_reg, risk, v0, taps=taps)
res = {k: (to_reference(k, read(v)) if not k.startswith("ego.") or k == "ego.sem_in" else read(v))
for k, v in taps.items()}
res["ego"] = to_reference("ego", read(out["ego"]))
res["lane_logit"] = to_reference("lane_logit", read(out["lane_logit"]))
res["lane"] = to_reference("lane", read(out["lane"]))
hrr = read(out["hm_reg"]).reshape(-1, 8)
res["hm"] = to_reference("hm", hrr[:, :2])
res["reg"] = to_reference("reg", hrr[:, 2:8])
return res
def release(self) -> None:
self.head.release()
super().release()
STAGES = {"image": ImageStage, "lift": LiftStage, "bev": BevStage, "head": HeadStage}
|