Comments (7)
Hi, is it possible that you share the scene folder with me? That would make finding the problem a lot easier :)
from adop.
@darglein Thank you for your help. I will send it to you by email.
from adop.
Your dataset works fine on my system. This is the training output after 5 minutes:
If used the following parameter file:
[TrainParams]
random_seed = 3746934646
do_train = true
do_eval = true
batch_size = 1
inner_batch_size = 4
inner_sample_size = 3
num_epochs = 10
save_checkpoints_its = 10
eval_only_on_checkpoint = true
name = kitti_0_500_2
debug = false
output_file_type = .png
split_method =
max_images = 4
duplicate_train_factor = 32
shuffle_initial_indices = false
shuffle_train_indices = true
split_remove_neighbors = 0
split_index_file_train =
split_index_file_test =
train_on_eval = true
train_factor = 0.0000000000
num_workers_train = 4
num_workers_eval = 2
train_crop_size = 256
train_mask_border = 16
reduced_check_point = true
write_images_at_checkpoint = true
keep_all_scenes_in_memory = false
use_image_masks = false
write_test_images = true
texture_random_init = true
texture_color_init = false
train_use_crop = true
experiment_dir = experiments/
scene_base_dir = scenes/
scene_names = kitt_data
checkpoint_directory =
loss_vgg = 1.0000000000
loss_l1 = 1.0000000000
loss_mse = 0.0000000000
min_zoom = 0.7500000000
max_zoom = 1.5000000000
crop_prefere_border = true
optimize_eval_camera = false
interpolate_eval_settings = false
noise_pose_r = 0.0000000000
noise_pose_t = 0.0000000000
noise_intr_k = 0.0000000000
noise_intr_d = 0.0000000000
noise_point = 0.0000000000
lr_decay_factor = 0.7500000000
lr_decay_patience = 10
lock_camera_params_epochs = 50
lock_structure_params_epochs = 50
[RenderParams]
render_outliers = false
check_normal = true
ghost_gradients = true
drop_out_points_by_radius = true
outlier_count = 1000000
drop_out_radius_threshold = 0.6000000238
dropout = 0.2500000000
depth_accept = 0.0099999998
test_backward_mode = 0
distortion_gradient_factor = 0.0099999998
K_gradient_factor = 0.5000000000
[PipelineParams]
train = true
verbose_eval = false
log_render = false
log_texture = true
skip_neural_render_network = false
enable_environment_map = true
env_map_w = 1024
env_map_h = 512
env_map_channels = 4
num_texture_channels = 4
cat_env_to_color = false
cat_masks_to_color = false
[OptimizerParams]
texture_optimizer = adam
fix_render_network = false
fix_texture = false
fix_environment_map = false
fix_points = true
fix_poses = false
fix_intrinsics = true
fix_vignette = false
fix_response = false
fix_wb = true
fix_exposure = false
fix_motion_blur = true
fix_rolling_shutter = true
lr_render_network = 0.0004000000
lr_texture = 0.0100000000
lr_background_color = 0.0002000000
lr_environment_map = 0.0020000000
lr_points = 0.0001000000
lr_poses = 0.0050000000
lr_intrinsics = 0.0100000000
response_smoothness = 1.0000000000
lr_vignette = 0.0000050000
lr_response = 0.0010000000
lr_wb = 0.0010000000
lr_exposure = 0.0005000000
lr_motion_blur = 0.0050000000
lr_rolling_shutter = 0.0000020000
[NeuralCameraParams]
enable_vignette = true
enable_exposure = true
enable_response = true
enable_white_balance = false
enable_motion_blur = false
enable_rolling_shutter = false
response_params = 25
response_gamma = 0.4545454681
response_leak_factor = 0.0099999998
[MultiScaleUnet2dParams]
num_input_layers = 4
num_input_channels = 4
num_output_channels = 3
feature_factor = 4
num_layers = 4
add_input_to_filters = false
channels_last = false
half_float = false
upsample_mode = bilinear
norm_layer_down = id
norm_layer_up = id
last_act =
conv_block = gated
conv_block_up = gated
pooling = average
from adop.
@darglein Thank you for your help. I also got the same result on my classmate's computer. I would like to ask what else might cause this problem in the case of the same code and data. For example, compilation problems or package saiga_OpenGL No? I haven't started training yet. The output of GroudTruth image when eval epoch=0 is already an exception.
from adop.
Can you try a full rebuild with a new conda environment? Maybe you have missed one of the changes in the last weeks.
from adop.
@darglein thanks, i will try.
from adop.
Sorry for troubling you. When you tranning this data, what have you done to the point cloud ? Are you rebuild the point cloud from all the lidar point from the different sequences and use the camera to color the point ?
from adop.
Related Issues (20)
- doubt about the point cloud in demo video HOT 3
- failed to build with ffmpeg in Ubuntu 18.04
- updated src/readme HOT 1
- Can not train
- Train issue: point_cloud_cuda->t_normal.defined()
- Silent Crash without EXIF Data HOT 2
- Update src/Readme with system requirements
- Training and inference script in python
- install pytorch source
- make -j10 Failed
- ./install_pytorch.sh这条命令,在源码中没有install_pytorch.sh,怎么进行?
- python setup.py install gives us an error
- modelsimpl.h compability issue HOT 1
- fail to run ./build/bin/adop_viewer --scene_dir scenes/boat HOT 1
- can't move in vr_viewer using oculus quest 2 HOT 1
- How to use the mask function?
- exception_handler.cc
- `GLIBCXX_3.4.30' not found HOT 2
- Loading images failed
- If you REALLY want to run this code HOT 3
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 adop.