models: CenterPoint + calibration_status onboarding (stage graph, deploy, INT8) - #20
Draft
vividf wants to merge 1 commit into
Draft
models: CenterPoint + calibration_status onboarding (stage graph, deploy, INT8)#20vividf wants to merge 1 commit into
vividf wants to merge 1 commit into
Conversation
This was referenced Sep 5, 2026
…loy, INT8) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
vividf
force-pushed
the
pr9-cli-family-dispatch
branch
from
September 7, 2026 05:23
8270b7a to
9e0ff0f
Compare
vividf
force-pushed
the
pr10-centerpoint-onboarding
branch
from
September 7, 2026 05:23
6e26d88 to
697ca48
Compare
This was referenced Sep 7, 2026
Draft
Draft
quant: declarative quantization (plan/placement, modelopt engine, PTQ/QAT, self-describing ckpt)
#17
Draft
Draft
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stack(base
pr-stack-base=7e35d97):#11 → #12 → #13 → #14 → #15 → #16 → #17 → #18 → #19 → #20(CenterPoint 全功能點)→ #21 → #25 → #22 → #23 → #24(= 開發 branch HEAD,逐位元一致)。合併由下而上,每合一層把下一層 base retarget。這個 PR 是什麼
CenterPoint(+ calibration_status)全功能上線點——合入當下 train / quantize / deploy / test 全部可用(CLI、quantization、編排都在其之前;此順序經 import audit 驗證)。這是 stage-graph + 宣告式量化的第一個完整應用,pattern 在 #22(BEVFusion)、#23(PTv3)重複;review 這個 PR = 建立三分之一的 onboarding 心智。
實測數字
verification 兩 gate(pytorch↔onnx、onnx↔tensorrt)PASS;QAT 與 PTQ 持平(0.8128 vs 0.8132 @1000 frames,50 校準樣本另一 config 系)→ 正式路徑 = PTQ,QAT recipe(freeze + cosine 1e-5)保留可用。
逐檔導覽
main_modules/centerpoint/stages.py:TorchStage(voxelize/scatter)+ GraphStage(pts_backbone_neck_head 一張圖)的切界;output_fields映射 head 輸出。main_modules/centerpoint/quantization.py:QuantRules(quantize_submodules={"backbone": ("conv",), ...})。main_modules/centerpoint/model.py(R050 自舊路徑):模型類。heads/centerhead.py:head_conv_kernel參數——唯一理由是 AWML/mmdet3d ckpt 相容(kernel 1;native=3),docstring 載明;velocity loss 的 non-finite masking。models/common/layers/conv.py:ConvModule 增 kernel_size(上項的支撐)。preprocessing/detection3d/point_pillar*.py+ 測試:pillar 前處理。_int8/_int8_qatexperiment(skip_quantize的 stage-0 是 release recipe:輸入端量化掉 ~1.2 mAP,實測記錄在 config 註解;verification tolerance 帶 observed 值)。test_centerpoint_stages、test_calibration_status_stages、test_tree_parity(量化重建與原模型樹一致)。models/detection3d/centerpoint.py整檔 TODO 待刪(experiments 已全指向 main_modules 版)。檔案清單(點開)
Review checklist
_int8.yaml的 skip_quantize 與 tolerance 註解(observed 值在不在)。🤖 Generated with Claude Code