Skip to content

Detailed Performance of FSD #62

Open
Open
Detailed Performance of FSD#62

Description

@Abyssaledge
Abyssaledge
opened on Sep 19, 2022

Performance of fsd_waymoD1_1x_submission.py (test set): submission
Performance of fsd_waymoD1_1x.py (validation set):

OBJECT_TYPE_TYPE_VEHICLE_LEVEL_1: [mAP 0.792293] [mAPH 0.787888]                                                                                              
OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2: [mAP 0.704975] [mAPH 0.700932]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_1: [mAP 0.825951] [mAPH 0.773279]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2: [mAP 0.739378] [mAPH 0.690696]
OBJECT_TYPE_TYPE_SIGN_LEVEL_1: [mAP 0] [mAPH 0]     
OBJECT_TYPE_TYPE_SIGN_LEVEL_2: [mAP 0] [mAPH 0]                   
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_1: [mAP 0.77096] [mAPH 0.759925]   
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2: [mAP 0.743786] [mAPH 0.73312]    
RANGE_TYPE_VEHICLE_[0, 30)_LEVEL_1: [mAP 0.928933] [mAPH 0.925183] 
RANGE_TYPE_VEHICLE_[0, 30)_LEVEL_2: [mAP 0.916398] [mAPH 0.91269]    
RANGE_TYPE_VEHICLE_[30, 50)_LEVEL_1: [mAP 0.782089] [mAPH 0.777451]  
RANGE_TYPE_VEHICLE_[30, 50)_LEVEL_2: [mAP 0.714469] [mAPH 0.710126]
RANGE_TYPE_VEHICLE_[50, +inf)_LEVEL_1: [mAP 0.593706] [mAPH 0.586526]
RANGE_TYPE_VEHICLE_[50, +inf)_LEVEL_2: [mAP 0.461929] [mAPH 0.456148]
RANGE_TYPE_PEDESTRIAN_[0, 30)_LEVEL_1: [mAP 0.865141] [mAPH 0.823203]
RANGE_TYPE_PEDESTRIAN_[0, 30)_LEVEL_2: [mAP 0.82562] [mAPH 0.784474]
RANGE_TYPE_PEDESTRIAN_[30, 50)_LEVEL_1: [mAP 0.814913] [mAPH 0.756908]
RANGE_TYPE_PEDESTRIAN_[30, 50)_LEVEL_2: [mAP 0.738424] [mAPH 0.684682]
RANGE_TYPE_PEDESTRIAN_[50, +inf)_LEVEL_1: [mAP 0.74548] [mAPH 0.662026]
RANGE_TYPE_PEDESTRIAN_[50, +inf)_LEVEL_2: [mAP 0.588333] [mAPH 0.5195]
RANGE_TYPE_SIGN_[0, 30)_LEVEL_1: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[0, 30)_LEVEL_2: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[30, 50)_LEVEL_1: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[30, 50)_LEVEL_2: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[50, +inf)_LEVEL_1: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[50, +inf)_LEVEL_2: [mAP 0] [mAPH 0]
RANGE_TYPE_CYCLIST_[0, 30)_LEVEL_1: [mAP 0.854262] [mAPH 0.843677]
RANGE_TYPE_CYCLIST_[0, 30)_LEVEL_2: [mAP 0.848135] [mAPH 0.837626]
RANGE_TYPE_CYCLIST_[30, 50)_LEVEL_1: [mAP 0.733669] [mAPH 0.722557]
RANGE_TYPE_CYCLIST_[30, 50)_LEVEL_2: [mAP 0.695306] [mAPH 0.684749]
RANGE_TYPE_CYCLIST_[50, +inf)_LEVEL_1: [mAP 0.616862] [mAPH 0.602011]
RANGE_TYPE_CYCLIST_[50, +inf)_LEVEL_2: [mAP 0.576674] [mAPH 0.562745]

Activity

  1. Abyssaledge
    pinned this issue on Sep 19, 2022

  2. shawnding commented on Dec 15, 2022

    @shawnding
    shawnding
    on Dec 15, 2022

    Hi, @Abyssaledge

    I noticed there is a 6-frame FSD++ on the WOD leaderboard here.

    Do you mind publishing the detailed performance of this 6f model on the evaluation set?

    Thanks!

  3. Abyssaledge commented on Dec 15, 2022

    @Abyssaledge
    Abyssaledge
    on Dec 15, 2022
    CollaboratorAuthor

    FSD++ is our new work, which does not simply concatenate 6-frame point clouds. We are going to release it one month later.

  4. shawnding commented on Dec 15, 2022

    @shawnding
    shawnding
    on Dec 15, 2022

    I see. Do you have the performance of the plain FSD on WOD validation set using 6 past frames? Thanks

  5. Abyssaledge commented on Dec 16, 2022

    @Abyssaledge
    Abyssaledge
    on Dec 16, 2022
    CollaboratorAuthor

    Below is the validation results of plain FSD uses 6 past frames, trained with 6 epochs. I have not tried the better 12-epoch schedule yet. Hope it helps.

    OBJECT_TYPE_TYPE_VEHICLE_LEVEL_1: [mAP 0.799491] [mAPH 0.794361]
OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2: [mAP 0.715469] [mAPH 0.710729]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_1: [mAP 0.852234] [mAPH 0.823217]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2: [mAP 0.780457] [mAPH 0.752212]
OBJECT_TYPE_TYPE_SIGN_LEVEL_1: [mAP 0] [mAPH 0]
OBJECT_TYPE_TYPE_SIGN_LEVEL_2: [mAP 0] [mAPH 0]
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_1: [mAP 0.799318] [mAPH 0.790754]
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2: [mAP 0.773707] [mAPH 0.765401]
RANGE_TYPE_VEHICLE_[0, 30)_LEVEL_1: [mAP 0.928514] [mAPH 0.924518]
RANGE_TYPE_VEHICLE_[0, 30)_LEVEL_2: [mAP 0.917057] [mAPH 0.913095]
RANGE_TYPE_VEHICLE_[30, 50)_LEVEL_1: [mAP 0.790543] [mAPH 0.78467]
RANGE_TYPE_VEHICLE_[30, 50)_LEVEL_2: [mAP 0.725964] [mAPH 0.720454]
RANGE_TYPE_VEHICLE_[50, +inf)_LEVEL_1: [mAP 0.614176] [mAPH 0.605479]
RANGE_TYPE_VEHICLE_[50, +inf)_LEVEL_2: [mAP 0.483056] [mAPH 0.475891]
RANGE_TYPE_PEDESTRIAN_[0, 30)_LEVEL_1: [mAP 0.877269] [mAPH 0.851449]
RANGE_TYPE_PEDESTRIAN_[0, 30)_LEVEL_2: [mAP 0.841557] [mAPH 0.81575]
RANGE_TYPE_PEDESTRIAN_[30, 50)_LEVEL_1: [mAP 0.84102] [mAPH 0.812239]
RANGE_TYPE_PEDESTRIAN_[30, 50)_LEVEL_2: [mAP 0.777104] [mAPH 0.749143]
RANGE_TYPE_PEDESTRIAN_[50, +inf)_LEVEL_1: [mAP 0.804108] [mAPH 0.772521]
RANGE_TYPE_PEDESTRIAN_[50, +inf)_LEVEL_2: [mAP 0.673028] [mAPH 0.643962]
RANGE_TYPE_SIGN_[0, 30)_LEVEL_1: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[0, 30)_LEVEL_2: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[30, 50)_LEVEL_1: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[30, 50)_LEVEL_2: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[50, +inf)_LEVEL_1: [mAP 0] [mAPH 0]
RANGE_TYPE_SIGN_[50, +inf)_LEVEL_2: [mAP 0] [mAPH 0]
RANGE_TYPE_CYCLIST_[0, 30)_LEVEL_1: [mAP 0.853747] [mAPH 0.845311]
RANGE_TYPE_CYCLIST_[0, 30)_LEVEL_2: [mAP 0.848122] [mAPH 0.83974]
RANGE_TYPE_CYCLIST_[30, 50)_LEVEL_1: [mAP 0.782653] [mAPH 0.773833]
RANGE_TYPE_CYCLIST_[30, 50)_LEVEL_2: [mAP 0.745297] [mAPH 0.736878]
RANGE_TYPE_CYCLIST_[50, +inf)_LEVEL_1: [mAP 0.683078] [mAPH 0.6742]
RANGE_TYPE_CYCLIST_[50, +inf)_LEVEL_2: [mAP 0.642995] [mAPH 0.634601]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions