Comments (18)
What you should is just add another data loading code.
Add data/YOUR_DB/YOUR_DB.py and make similar code with data/any_db/any_db.py
Then, open main/config.py and set trainset_3d=['YOUR_DB'] or trainset_2d=['YOUR_DB']
I can't give you more detailed guidance because I know nothing about your DB :(
from i2l-meshnet_release.
- Can you tell me what you did when dealing with inconsistent dataset formats? Perhaps it can be said, what preprocessing did you do to the dataset?
- For example: in the directory data/xx/xx, there are some bbox_root_xx_output.json, xx_train.json, etc. How should I get these files based on my own dataset? Based on the general steps you took when processing the dataset in this project, can you tell me a general process?
- Maybe you can use one of the datasets used in your project as an example?
from i2l-meshnet_release.
I preprocessed all datasets to MSCOCO format. You can refer to that site and annotation of MSCOCO dataset.
from i2l-meshnet_release.
Hello, I have one more question.
How did you get these files, such as J_regressor_h36m_correct.npy and J_regressor_coco_hip_smpl.npy?
from i2l-meshnet_release.
h36m is from here and coco is from smpl joint regressor
from i2l-meshnet_release.
- Do we need to have our dataset-specific regressor like H36M? 'J_regressor_h36m_correct.npy'
- I saw COCO has 'J_regressor_coco_hip_smpl.npy' and 'coco_smplifyx_train.json', does the pseudo GT on COCO helps performance converge? or what will happen if we disable the loss for 2d dataset like COCO?
- How did you get the J-regressor for COCO dataset, will that be the same if we want to fit MPII 2d dataset?
from i2l-meshnet_release.
-
The dataset-specific regressor is used in the evaluation stage. The most commonly used evaluation metric is 3D distance between GT 3D joint coordinates and 3D joint coordinates from the predicted mesh. The 3D joint coordinates from the predicted mesh can be obtained by multiplying the dataset-specific joint regressor.
-
The 2D dataset like COCO is necessary because images in multi-view datasets (e.g., H36M) have very different image appearance compared with that of in-the-wild images. Your model may fail to generalize if you train it on only multi-view datasets.
-
The definition of some joints, especially hips, can be different for each dataset. You can somehow interpolate the given joint regressor in SMPL.
from i2l-meshnet_release.
Hello!
In config.py, what does this parameter (bbox_3d_size ) mean?
bbox_3d_size = 2
smpl_coord_img[:, 2] = (smpl_coord_img[:, 2] / (cfg.bbox_3d_size / 2) + 1) / 2. * cfg.output_hm_shape[0]
Thanks!
from i2l-meshnet_release.
smpl_coord_img[:,2]
is a root joint-relative depth value in meter.
To convert it to 0~64 (heatmap coordinate), I need to divide the depth value by its pre-defined max value (bbox_3d_size
).
from i2l-meshnet_release.
Hello, I still have some questions.
Training can get 7 losses, which are: loss['joint_fit'], loss['joint_orig'], loss['mesh_fit'], loss['mesh_joint_orig'], loss['mesh_joint_fit'], loss['mesh_normal '], loss['mesh_edge'].
I want to calculate the total loss.
-
L = L_poseNet + L_meshNet + L_vertex +λL_normal + L_edge
I think,
-
L_normal==loss['mesh_normal']
-
L_edge==loss['mesh_edge']
there are 5 losses left, then how should L_poseNet, L_meshNet, L_vertex be calculated?
Thank you very much for your reply!
from i2l-meshnet_release.
fit
means the prediction targets are from fitted mesh (GPs obtained by running SMPLify-X on GT 2D/3D pose of the dataset).
orig
means the prediction targets are from GT 2D/3D pose of the dataset.
L_pose^posenet == loss['joint_fit'] + loss['joint_orig']
L_pose^meshnet == loss['mesh_joint_fit'] + loss['mesh_joint_orig']
L_vertex == loss['mesh_fit']
from i2l-meshnet_release.
The rotation loss is defined on 6D, https://github.com/mks0601/I2L-MeshNet_RELEASE/blob/master/common/nets/module.py#L125
If we try to work on our own dataset, how do we get the 6D representation? Can you provide the code for converting?
Is the 6D representation https://arxiv.org/abs/1812.07035?
from i2l-meshnet_release.
Q. If we try to work on our own dataset, how do we get the 6D representation? Can you provide the code for converting?
A. The predicted 6D rotations are converted to 3D axis-angle, and the loss is calculated on the 3D axis-angle.
Q. Is the 6D representation https://arxiv.org/abs/1812.07035?
A. Yes
from i2l-meshnet_release.
I took nine photos in the MSCOCO data set for training, but the final result out['mesh_coord_img''], after visualization is a bunch of messy 3D points, after vis_mesh(), there is only one red point on the photo , Not a human body mesh. The training results of the 9 photos are incorrect. Why?
Using input.jpg in the demo, the test results are as follows:
from i2l-meshnet_release.
I cannot understand your question.. Did you use only 9 images for the training? why? How did you use only those images?
from i2l-meshnet_release.
Yeah, I selected nine pictures in MSCOCO train2017 for training,
000000391895.jpg,
000000522418.jpg,
000000184613.jpg,
000000318219.jpg,
000000554625.jpg,
000000574769.jpg,
000000060623.jpg,
000000005802.jpg,
000000222564.jpg,
Because I used 10 photos when training my own dataset task, but out['mesh_coord_img'] is some messy mesh points. Therefore, I used your original MSCOCO dataset 9 photos for training, and the results are also messy points.
I used 9 photos of the training model, tested input.jpg, and the results of visualization out['mesh_coord_img'] are as follows:
from i2l-meshnet_release.
First of all, using only 9 images with the provided learning schedule (13 epoch) will absolutely make the model not converged.
In general, at least thousands of images are required to train deep neural networks.
from i2l-meshnet_release.
@zqq-judy do you remember how can you get these files: bbox_root_xx_output.json, xx_train.json because I need them for my dataset
from i2l-meshnet_release.
Related Issues (20)
- Model Activation on a new dataset HOT 1
- Dataset converting to MSCOCO Format
- Pretrained model of param regressor for hand HOT 2
- "The file exceeds the download quota. " HOT 4
- issue about bbox_root_pw3d_output.json HOT 1
- No 'R' and 't' keys in camera parameters you provided
- I have googled it, but it has not been solved yet. I have the following problem, please help me
- The provided freihand pose param is different from freihand origin dataset HOT 3
- help for size mismatch problem HOT 1
- Training Settings for FreiHAND HOT 6
- Question about downsampled mesh performance HOT 1
- MSCOCO Background HOT 3
- issues about mano param in freihand dataset HOT 1
- pytorch matrix size incorrect HOT 1
- bbox_root_freihand_output.json HOT 2
- training the rootnet with Freihand Dataset. HOT 3
- the focal of rootnet training HOT 1
- Change to MANO in demo.py HOT 1
- The thickness of the generated mesh HOT 2
- when running the command: python demo.py --gpu 3 --stage param --test_epoch 8 I get the following error, can someone help me please to solve it HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from i2l-meshnet_release.