rayguan97 / m3detr Goto Github PK
View Code? Open in Web Editor NEWCode base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
License: Apache License 2.0
Code base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
License: Apache License 2.0
Hey Guys,
voxel_set_abstraction.py
file. File "..../tools/../pcdet/models/__init__.py", line 30, in model_func ret_dict, tb_dict, disp_dict = model(batch_dict) File "....../.pyenv/versions/3.7.7/envs/rp/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "............../tools/../pcdet/models/detectors/ours_3d.py", line 11, in forward batch_dict = cur_module(batch_dict) File "............../.pyenv/versions/3.7.7/envs/rp/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "............../tools/../pcdet/models/backbones_3d/pfe/voxel_set_abstraction.py", line 593, in forward batch_dict = self.reduce_points(batch_dict) File "............/tools/../pcdet/models/backbones_3d/pfe/voxel_set_abstraction.py", line 542, in reduce_points for bs_idx, roi in enumerate(batch_dict['batch_cls_preds']): KeyError: 'batch_cls_preds'
batch_dict
before the function call for reduce_points
, and there is no key named as batch_cls_preds
BATCH_DICT: dict_keys(['points', 'frame_id', 'sample_idx', 'gt_boxes', 'use_lead_xyz', 'voxels', 'voxel_coords', 'voxel_num_points', 'metadata', 'batch_size', 'voxel_features', 'encoded_spconv_tensor', 'encoded_spconv_tensor_stride', 'multi_scale_3d_features', 'multi_scale_3d_strides', 'spatial_features', 'spatial_features_stride'])
Thanks in Advance!!
Will there be code availbe with soon?
Would be glad to see that :-)
Take care Jürgen
When training the M3DETR, there is an error which is : No key word batch_cls_preds happened in VoxelSetAbstractionTransFusionv5.
The specific code is as follows:
def reduce_points(self, batch_dict):
batch_indices = batch_dict['points'][:, 0].long()
masks = []
for bs_idx, roi in enumerate(batch_dict['batch_cls_preds']):
bs_mask = (batch_indices == bs_idx)
pts = batch_dict['points'][bs_mask].unsqueeze(dim=1)[:, :, 1: 4] # (N, 1, 3)
s, _ = torch.max(batch_dict['batch_cls_preds'][bs_idx], dim=1)
top, idx = torch.topk(s, self.topks)
c = batch_dict['batch_box_preds'][bs_idx][idx][:, :3].unsqueeze(dim=0)
dist = (pts - c)**2
dist, _ = dist.sum(dim=-1).min(dim=1)
mask = (dist <= self.reduce_radius)
masks.extend(mask)
batch_dict['points'] = batch_dict['points'][masks]
return batch_dict
It seems to me that the training phase should not be present: "batch_cls_preds," which should only be present in the inference phase. I would like to ask your opinion.
Do you have a training model for Kitti dataset
hello, I am very interested in your work. So I do exp. on KITTI dataset, but I found the result is lower than PV-RCNN and don't reproduce the same / close results as your paper both on R11 and R40 metrics. Could you please share the checkpoint? Thank you for your reply.
So, how can I solve it?
Hi! Can you help with a few questions on positional embeddings:
Thank you! I look forward to your reply and the code release.
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.