cfzd / monoground Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
thanks for you job,my question is :
raise KeyError("Non-existent config key: {}".format(full_key))
KeyError: 'Non-existent config key: MODEL.HEAD.DENSE_DEPTH
here is config:
MODEL:
INPLACE_ABN: True
HEAD:
REGRESSION_HEADS: [['2d_dim'], ['3d_offset'], ['corner_offset'], ['corner_uncertainty'], ['3d_dim'], ['ori_cls', 'ori_offset'], ['depth'], ['depth_uncertainty']]
REGRESSION_CHANNELS: [[4, ], [2, ], [20], [3], [3, ], [8, 8], [1, ], [1, ]]
ENABLE_EDGE_FUSION: True
TRUNCATION_OUTPUT_FUSION: 'add'
EDGE_FUSION_NORM: 'BN'
TRUNCATION_OFFSET_LOSS: 'log'
BN_MOMENTUM: 0.1
USE_NORMALIZATION: "BN"
LOSS_TYPE: ["Penalty_Reduced_FocalLoss", "L1", "giou", "L1"]
MODIFY_INVALID_KEYPOINT_DEPTH: True
CORNER_LOSS_DEPTH: 'soft_combine'
LOSS_NAMES: ['hm_loss', 'bbox_loss', 'depth_loss', 'offset_loss', 'orien_loss', 'dims_loss', 'corner_loss', 'keypoint_loss', 'keypoint_depth_loss', 'trunc_offset_loss', 'weighted_avg_depth_loss']
LOSS_UNCERTAINTY: [True, True, False, True, True, True, True, True, False, True, True]
INIT_LOSS_WEIGHT: [1, 1, 1, 0.5, 1, 1, 0.2, 1.0, 0.2, 0.1, 0.2]
CENTER_MODE: 'max'
HEATMAP_TYPE: 'centernet'
DIMENSION_REG: ['exp', True, False]
USE_UNCERTAINTY: False
DEPTH_MODE: 'inv_sigmoid'
OUTPUT_DEPTH: 'soft'
DIMENSION_WEIGHT: [1, 1, 1]
DENSE_DEPTH: False
DENSE_DEPTH_SAMPLE_NUM: 21
DENSE_DEPTH_SAMPLING_METHOD: 'random'
DENSE_DEPTH_SAMPLING_NUM_TYPE: 'area'
UNCERTAINTY_INIT: True
ADD_GROUND_DEPTH: True
FREEZE_BACKBONE: False
BOT_CENTER: False
LOAD_MODEL_META: False
DETACH_GROUND_DEPTH: False
USING_GROUND_DEPTH_INFER: True
GROUND_DEPTH_LOSS_WEIGHT: 0.1
GD_XY: False
GD_DEPTH_COORD_CONV: True
DILATED_GROUND_DEPTH: True
REDUCE_LOSS_NORM: True
USE_SYNC_BN: True
Since the size of the nuScenes dataset is too large to download, I wonder if you could provide the the pretrained weight of Monoground for me? My email address is [email protected]
Looking forward to your timely reply!
RT
In the Ground branch, after Dilated Conv, The size of the predicted depth map is equal to the size of the feature map after downsampling?
Hello, cfzd !
I trained monoground on the kitti validation dataset and found that I can't reproduce the result on paper.
Since my lab doesn't have 2080Ti and RTX 3090 doesn't support cuda10, I use PyTorch version: 1.11.0+cu113, and rebuild DCNV2 based on https://github.com/lbin/DCNv2.
Others are keep the same with your config.What can I do to get the similar result as yours ?
Waiting for your reply.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.