Comments (3)
What in the code is using pydantic? I don't remember using it 🤔
from dynamic-cloth-folding.
What in the code is using pydantic? I don't remember using it 🤔
The 'cloth_env.py' needs it, I checked that import albumentations as A
that albumentations
relays on pdantic
. The version of my pydantic
is 2.7.0. And the error occurred in train.py
line28:
def experiment(variant): eval_env = cloth_env.ClothEnv( **variant['env_kwargs'], randomization_kwargs=variant['randomization_kwargs'])
I print the 'varient' here:
{'algorithm': 'SAC', 'title': 'default-run-0', 'save_folder': '/root/dynamic-cloth-folding/trainings/default-run-0', 'random_seed': 0, 'randomization_kwargs': {'lights_randomization': True, 'materials_randomization': True, 'camera_position_randomization': True, 'lookat_position_randomization': True, 'lookat_position_randomization_radius': 0.03, 'dynamics_randomization': True, 'albumentations_randomization': True, 'cloth_size': 0.2, 'camera_type': 'side', 'camera_config': {'type': 'small', 'fovy_range': (13, 15), 'height': 100, 'width': 848}, 'position_perturbation_size': 0.2, 'rotation_perturbation_size': 0.75, 'fovy_perturbation_size': 0.05}, 'value_function_kwargs': {'fc_layer_size': 512, 'fc_layer_depth': 5}, 'policy_kwargs': {'input_width': 100, 'input_height': 100, 'input_channels': 1, 'kernel_sizes': [3, 3, 3, 3], 'n_channels': [32, 32, 32, 32], 'strides': [2, 2, 2, 2], 'paddings': [0, 0, 0, 0], 'hidden_sizes_aux': [256, 8], 'hidden_sizes_main': [256, 256, 256, 256], 'init_w': 0.0001, 'aux_output_size': 9}, 'env_kwargs': {'save_folder': '/root/dynamic-cloth-folding/trainings/default-run-0', 'timestep': 0.01, 'success_distance': 0.05, 'robot_observation': 'ctrl', 'control_frequency': 10, 'ctrl_filter': 0.03, 'kp': 1000.0, 'frame_stack_size': 1, 'damping_ratio': 1, 'success_reward': 0, 'fail_reward': -1, 'extra_reward': 1, 'output_max': 0.03, 'max_close_steps': 10, 'sparse_dense': True, 'goal_noise_range': (0.0, 0.03), 'image_obs_noise_mean': 0.5, 'image_obs_noise_std': 0.5, 'model_kwargs_path': './data/model_params.csv'}, 'eval_kwargs': {'save_images_every_epoch': 10, 'num_runs': 20, 'max_path_length': 50, 'additional_keys': ['robot_observation'], 'frame_stack_size': 1, 'save_blurred_images': True, 'save_folder': '/root/dynamic-cloth-folding/trainings/default-run-0'}, 'algorithm_kwargs': {'num_epochs': 100, 'num_trains_per_train_loop': 1000, 'num_expl_steps_per_train_loop': 1000, 'num_train_loops_per_epoch': 20, 'max_path_length': 50, 'save_policy_every_epoch': 1, 'batch_size': 256, 'num_demoers': 0, 'save_folder': '/root/dynamic-cloth-folding/trainings/default-run-0'}, 'path_collector_kwargs': {'additional_keys': ['robot_observation'], 'demo_paths': ['./data/demos.csv'], 'demo_divider': 0.03, 'num_processes': 1}, 'replay_buffer_kwargs': {'max_size': 100000, 'fraction_goals_rollout_goals': 0.19999999999999996, 'internal_keys': ['image', 'robot_observation']}, 'trainer_kwargs': {'discount': 0.99, 'soft_target_tau': 0.005, 'target_update_period': 1, 'policy_lr': 0.0003, 'qf_lr': 0.0003, 'reward_scale': 1, 'use_automatic_entropy_tuning': True, 'corner_prediction_loss_coef': 0.001}}
Could you provide some suggestions? Thanks!
from dynamic-cloth-folding.
Looks like those pydantic logs are just warnings, most likely unrelated to the segfault. I would recommend running with e.g. gdb
to see what's happening: #3 (comment)
The issue is definitely in some binding/cpp code, not in python.
from dynamic-cloth-folding.
Related Issues (5)
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 dynamic-cloth-folding.