Comments (2)
ehedlin
commented on July 23, 2024
1
I am loading the model into another project where I am using my own dataloader etc. I am assuming I am just having a problem with the disconnect. Thank you :)
from meshtransformer.
kevinlin311tw
commented on July 23, 2024
Thanks for raising the issue.
I re-run the evaluation with the model checkpoint. But I couldn't obtain the numbers you mentioned above. Could you please share your commands here? It would be helpful to identify the issue.
I use the following command:
python -m torch.distributed.launch --nproc_per_node=8 metro/tools/run_metro_bodymesh.py --val_yaml human3.6m/valid.protocol2.yaml --arch hrnet-w64 --per_gpu_eval_batch_size 30 --run_eval_only --num_worker 24 --resume_checkpoint models/metro_release/metro_h36m_state_dict.bin --num_hidden_layers 4 --num_attention_heads 4 --input_feat_dim 2051,512,128 --hidden_feat_dim 1024,256,128
The corresponding output log:
2021-06-08 20:53:43,911 METRO INFO: Using 8 GPUs
2021-06-08 20:53:48,330 METRO INFO: Update config parameter num_hidden_layers: 12 -> 4
2021-06-08 20:53:48,383 METRO INFO: Update config parameter hidden_size: 768 -> 1024
2021-06-08 20:53:48,440 METRO INFO: Update config parameter num_attention_heads: 12 -> 4
2021-06-08 20:53:49,899 METRO INFO: Init model from scratch.
2021-06-08 20:53:49,956 METRO INFO: Update config parameter num_hidden_layers: 12 -> 4
2021-06-08 20:53:50,008 METRO INFO: Update config parameter hidden_size: 768 -> 256
2021-06-08 20:53:50,060 METRO INFO: Update config parameter num_attention_heads: 12 -> 4
2021-06-08 20:53:50,402 METRO INFO: Init model from scratch.
2021-06-08 20:53:50,452 METRO INFO: Update config parameter num_hidden_layers: 12 -> 4
2021-06-08 20:53:50,501 METRO INFO: Update config parameter hidden_size: 768 -> 128
2021-06-08 20:53:50,570 METRO INFO: Update config parameter num_attention_heads: 12 -> 4
2021-06-08 20:53:50,764 METRO INFO: Init model from scratch.
2021-06-08 20:53:57,637 METRO INFO: => loading hrnet-v2-w64 model
2021-06-08 20:53:57,694 METRO INFO: Transformers total parameters: 102256646
2021-06-08 20:53:57,756 METRO INFO: Backbone total parameters: 128059944
2021-06-08 20:53:57,867 METRO INFO: Loading state dict from checkpoint models/metro_release/metro_h36m_state_dict.bin
2021-06-08 20:54:07,573 METRO INFO: Training parameters Namespace(arch='hrnet-w64', config_name='', data_dir='datasets', device=device(type='cuda', index=0), distributed=True, drop_out=0.1, hidden_feat_dim='1024,256,128', hidden_size=128, img_scale_factor=1, input_feat_dim='2051,512,128', intermediate_size=-1, joints_loss_weight=1000.0, legacy_setting=True, local_rank=0, logging_steps=1000, lr=0.0001, model_name_or_path='metro/modeling/bert/bert-base-uncased/', num_attention_heads=4, num_gpus=8, num_hidden_layers=4, num_train_epochs=200, num_workers=24, output_dir='output/', per_gpu_eval_batch_size=30, per_gpu_train_batch_size=30, resume_checkpoint='models/metro_release/metro_h36m_state_dict.bin', run_eval_only=True, seed=88, train_yaml='imagenet2012/train.yaml', val_yaml='human3.6m/valid.protocol2.yaml', vertices_loss_weight=100.0, vloss_w_full=0.33, vloss_w_sub=0.33, vloss_w_sub2=0.33)
2021-06-08 20:56:01,317 METRO INFO: Validation epoch: 0 mPVE: 0.00, mPJPE: 54.04, PAmPJPE: 36.75
from meshtransformer.
Related Issues (20)
- Dataset download error HOT 1
- This repo is missing important files
- How to visualize attention correlation as the paper
- Training on single dataset HOT 1
- Output Score / Confidence
- Project dependencies may have API risk issues
- Cannot render my hand by my photo HOT 1
- About the template vertices and joints
- Question about training with hand dataset? HOT 1
- Can't download 'https://datarelease.blob.core.windows.net/metro/datasets/filename.tar'
- pre-trained models！ERROR 400: Bad Request.
- Demo Lack of three-digit reconstruction effect，缺少三位重建 HOT 1
- COCO SMPL Data Missing
- About DDP train on the specified gpu
- It is stopped in 2023-10-31 16:00:44,169 METRO Inference INFO: Using 1 GPUs
- Exception: Unable to get url: http://files.is.tue.mpg.de/mloper/opendr/osmesa/OSMesa.Linux.aarch64.zip HOT 1
- Question about the learning rate adjustment strategy
- Question about weight decay setting
- Pre-trained model licensing
- How to do single-player multi-card training？ 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 meshtransformer.