daveredrum / d3net Goto Github PK
View Code? Open in Web Editor NEW[ECCV2022] D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
Home Page: https://daveredrum.github.io/D3Net/
[ECCV2022] D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
Home Page: https://daveredrum.github.io/D3Net/
Thanks for sharing this great work!
I am currently hitting an issue while running the evaluation for the pointgroup detector using the checkpoint file you shared.
python scripts/eval.py --folder <output_folder> --task detection
Output:
Traceback (most recent call last):
File "scripts/eval.py", line 522, in
model = init_model(cfg, dataset)
File "scripts/eval.py", line 121, in init_model
model.load_state_dict(checkpoint["state_dict"], strict=False)
File "/home/rajrup/miniconda3/envs/d3net-original/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1406, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for PipelineNet:
size mismatch for embeddings: copying a param with shape torch.Size([3441, 300]) from checkpoint, the shape in current model is torch.Size([3535, 300]).
size mismatch for speaker.caption.embeddings: copying a param with shape torch.Size([3441, 300]) from checkpoint, the shape in current model is torch.Size([3535, 300]).
size mismatch for speaker.caption.classifier.2.weight: copying a param with shape torch.Size([3441, 512]) from checkpoint, the shape in current model is torch.Size([3535, 512]).
size mismatch for speaker.caption.classifier.2.bias: copying a param with shape torch.Size([3441]) from checkpoint, the shape in current model is torch.Size([3535]).
The dimension of the tensors in checkpoint doesn't match the one required in the code. Before the model load step, the val splits, and the vocabulary loads fine. I might be missing something here. Can you please help me solve this issue?
Thanks!
It refers to scan2cap.
Besides, missing file conf/pointgroup-speaker-listener.yaml
hi @daveredrum
I'm getting the following error on executing the command below on colab terminal:
Command:
/content/D3Net/data/scannet# python prepare_scannet.py
Error:
data split: train
scene0000_00
Traceback (most recent call last):
File "prepare_scannet.py", line 222, in
process_all_scans(cfg)
File "prepare_scannet.py", line 205, in process_all_scans
process_one_scan(scan, cfg)
File "prepare_scannet.py", line 181, in process_one_scan
mesh, aligned_mesh, sem_labels, instance_ids, instance_bboxes, aligned_instance_bboxes = export(scan, cfg)
File "prepare_scannet.py", line 146, in export
mesh = read_mesh_file(mesh_file) #(num_verts, 9) xyz+rgb+normal
File "prepare_scannet.py", line 30, in read_mesh_file
mesh = scannet_utils.read_mesh_vertices_rgb_normal(mesh_file) #(num_verts, 9) xyz+rgb+normal
File "/content/D3Net/data/scannet/scannet_utils.py", line 119, in read_mesh_vertices_rgb_normal
assert(os.path.isfile(filename))
AssertionError
Is it possible that I'm doing something incorrectly in
I'm not entirely sure what is to be done here
Hi @daveredrum ,
I follow the instruction in README to train the PointGroup Detector, but the mAP@50 is around 32, which is quite low.
python scripts/train.py --config conf/pointgroup.yaml
I test the given checkpoint, and I can get the result of 50 mAP@50. So I guess there is something wrong with the given training hyper-parameters. Can you check it?
Thanks for your help.
Best
Hello,
I encountered an issue while trying to execute python scripts/train.py --config conf/pointgroup.yaml
I got the error message TypeError: file must have 'read' and 'readline' attributes
.
I could fix it by changing line 451 in lib/dataset/pipeline.py to:
with open(self.cfg["{}_PATH".format(self.name.upper())].glove_pickle, 'rb') as pickle_file:
glove = pickle.load(pickle_file)
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.