Skip to main content

Browse the archive

https://github.com/nutonomy/nuscenes-devkit
27 November 2022, 12:13:26 UTC
sort by:
Revision Author Date Message Commit Date
12fb091 whyekit-aptiv 02 September 2020, 15:09:55 UTC Fix links in readme and nuImages tutorial (#459) 02 September 2020, 15:09:55 UTC
9b492f7 Holger Caesar 01 September 2020, 08:45:09 UTC nuScenes v2.0 - Official code release (#458) * Merge lidarseg_v1.0 into nuscenes_v2.0 (#434) * nuScenes-lidarseg (#343) * initial commit for NuScenes-lidarseg * add function to list lidarseg categories and create colormap * integrated lidarseg function into nuscenes * print number of lidarseg annotations * Render lidarseg labels in image * Improve error message when pointsensor is not lidar * Calculate stats for lidarseg * Assertion for nsweeps to display lidarseg labels * Render only points in image which are labeled with classes the user chooses * Modularize function to filter colormap * Modularize function for generating colors for lidarseg classes * Clean up example usages * Allow user to filter and show desired lidarseg labels for render_sample_data * Save figure from render_pointcloud_in_image without excessive border * Render scene with pointclouds and lidarseg labels * Shift conditional statements in render_sample_data() * Check that lidar pointcloud is a keyframe * Render all camera channels with pointclouds and lidarseg labels for all scenes * Allow user to show lidarseg labels for render_sample() * Hacks to render for VOs * Added scene to filename for easy retrieval for VOs * Render scenes for VOs per class * Updated rendering of scenes for cameras to output videos * Function to convert plt scatter plot to cv2 * Tidy up examples * Print stats for lidarseg keyframe * Enable sorting of counts * Tweak verbosity for render_sample * Include class index when printing sample stats * Assert that path for video given by user ends with .avi * Enable showing of legend when mapping pc to image * Style edits * nuScenes-lidarseg initial tutorial * Cleanup, move methods out of tutorial, copyright * Cleanup * Remove empty cell * Throw errors rather than warnings * Address some comments on style. * Add full stops to comments * Tidy up utils * Removed TODOs * Initial draft of lidarseg tutorial * Added gifs for tutorial * Tidy up tutorial * Add setup instructions to tutorial * Edit style for one assertion * Changed show_lidarseg_labels default value in render_sample * Change type to np.ndarray * Fix some typos * Remove version from lidarseg.json * Bugfix * Unbugfix * Don't add category_lidarseg to table_names * Comment out dangerous commands Co-authored-by: Holger Caesar <holger@nutonomy.com> * View predictions using lidarseg devkit (#396) * Allow user to view preds using render_pointcloud_in_image * Allow users to get stats of predictions for a sample * Add visualization for user's preds to relevant functions * Updated tutorial * Fixed some typos in tutorial * Comment out code which may crash notebook * Fix double # * Get lidarseg file name from json instead, default coloring to depth if empty json * Change show_lidarseg_preds to lidarseg_preds_bin_path * Amend doc string for lidarseg_preds_bin_path * Amend render video functions to take folder name for preds * Amend tutorial * Remove gifs from folder * Clear outputs from tutorial * Update documentations for lidarseg (#404) * Update docs for lidarseg * Fix some typos * Address comments for docs * Update folder structure description in notebook * Automatically determine which lidarseg classes are present in a pointcloud projected onto an image (#410) * Auto find liarseg labels present in projected pcl * Add assertion to check num of bin files equals num of lidarseg records * Address comments * Adjust legend for aesthetics * Improve aesthetics for render_scene_with_pointclouds_for_all_cameras (#412) * Flip back cams horizontally for aesthetics * Explicitly set margins to zero and turn axes off * Prevent final frames from showing up in notebook if user stops render * Allow render_scene_with_pointclouds_for_all_cameras to output frames as images * Update indices in tutorial examples * Style changes * Clear memory in render_camera_channel_with_pointclouds if user stops rendering * Graceful exit if users stops rendering * Change random seed for color scheme * Style edits * Enable bboxes to be plotted with lidarseg (#418) * Include rendering of lidarseg with bboxes for render_scene_with_pointclouds_for_all_cameras * Add option to render bboxes in lidarseg videos * Style edits * Rename methods * Renamed argument to be more similar to nuScenes * Rename show_lidarseg_labels to show_lidarseg * Added comment on videos and images * Rewording * Making plotting of bboxes with lidarseg more modular * Remove option to save renders as images for render_scene_lidarseg * Use render_mode instead of render_if_no_points * Style edits * Update notebook * Style edits for notebook * Remove render_if_no_points for render_pointcloud_in_image * Style edits * Update file names for renders * Save image even for verbose=False * Made plot_points_and_bboxes * Update coloring * Update colormap * Choose nicer colors for some classes * Deep copy for colormap * Reduce bbox line width and update colormap * One line per arg * Update colormap * Remove unused method for arbitrary colormap * Remove leading 0 for filename * One colormap to rule them all * Update error msg for checking colormap to colors conversion * Add dpi as an arg for rendering lidarseg scenes * Amend docstring in get_colormap() * Make colormap DRY Co-authored-by: Holger Caesar <holger@nutonomy.com> * Remove render_if_no_points argument from lidarseg tutorial (#423) * Remove render_if_no_points arg and section * Rephrasing * Single category.json for both nuScenes and nuScenes-lidarseg (#424) * Change 'label' to 'name' when loading category json; check if preds folder exists * Check in various functions that lidarseg is installed * Shorten assertion statement * Check that new version of category.json is used, if loading lidarseg * Check only for 'index' in category records * nutonomy green for driveable surface (#425) * Improve lidarseg rendering methods, update tutorial, add unit tests (#429) * Initial commit to address comments * Fix bug where passing np.array instead of array into filter_lidarseg_labels throws an error * Rephrase some parts of tutorial * Include legend for render_sample_data * Add arg for show_lidarseg_legend in render_sample_data * Adjust aesthetics of legend in render_sample_data * Update colormap * Make creating legend modular * Ensure only labels in pc is included in legend * Explain verbose * Check that filter_lidarseg_labels is either a list or np.array * Allow user to list stats by class index * Update docstrings * Update tutorial to demo sort_by * Add unit tests * Make painting of labels modular * Add docstrings * Add lidarseg annotation instructions, update lidarseg tutorial intro (#431) * Initial commit * Add links from classes to examples * Link from examples to class definitions using Top * Remove extra white line * Include script to render lidarseg histogram for split (#433) * Initial commit * Arrange order of seaborn in requirements.txt * Add docstrings * Add more docstrings * Remove seaborn from requirements * Address comments * Add horizontal gridlines * Replicate look and feel of seaborn without needing package * Style edits * Add type in truncate_class_name Co-authored-by: Holger Caesar <holger@nutonomy.com> * Align indices in nuImages and nuScenes-lidarseg (#440) * Order colormap * Do not assume any ordering in colormap * nuImages v1.0 (#435) * nuImages v0.1 (#372) * Implemented lazy loading * Implement rendering of images with annotations * Disentangle requirements, better rendering * Explicitly init tables * Fix bug with explicitly assigned tables * Fix instance mask parsing * Fixed rendering * Remove unnecessary matplotlib commands * Remove explorer * Implemented list_attributes * list_cameras() and better lazy loading * Implement list_category * Improve tutorial, implement missing functions * Fix case when mask is empty, fix attribute names, change color map * Overhauled tutorial * Cleanup * Split readme into nuImages and nuScenes parts * Typo * Address review comments, add split to version * Render another image * nuImages new schema (#427) * Increment version number to v1.0 * Update table names * Installation instructions * Improve tutorial * Replace with global colormap, update tutorial * Patch all methods for new schema * Add detailed attribute tests * Added test for complete attributes * Add tests for foreign keys * Added schema figures * Add missing requirement * Skip long unit tests * Manual test alternative * Fix test issues and setup for all versions * Completed tests * Better error message * Show sample_token instead * Readd init shortcut for tutorial * Sort schema alphabetically * Add new table from nuScenes-lidarseg * Rename image to sample * Auto-format * Add new method list_sample_content * Add missing ego vehicle color * Remove nbr_points field from lidarseg table * Bugfix, select only the jpg * Typo * Modify render_image to take sample_data tokens * Start integrating depth methods * Rework depth rendering * Rename function * Fix one more * Don't init sample_to_key_frame_map * Fix lambda expression * Fix inconsistent naming * Fix indexing bug * Select all lidar tokens * Fix lidar extension * Add depth rendering to tutorial * Rework rendering of next image * Return projected points as 2d, set tutorial to val split, spelling * Workaround for wrong intrinsics format * Fix projection bug * Standardize out_path options * Remove intrinsics workaround, align tutorials, add schema to tutorial * Remove deprecated nuim.sample_to_key_frame method * Typo * Use get_sample_content, simplify table loading * Add test for prev/next pointers * Fix typo in driveable * Adjust test for new database fields * Fix sorting bug * Change output string * Output message * Add script to render random images to disk * Fix bug, improve output messages * Fix wrong path, remove title for better visibility, disable lazy * Debug numerical overflow, improve render script, filter by camera, align render_depth output size * Avoid overflow and remove special cases * Simplify depth completion options * Cleanup * Implemented pointcloud rendering * Color by height * Adjust distort settings, add shortcut function * Reorganize and add method for trajectory * Fancy rendering method for trajectories * Cleanup * Rename tutorials, remove the word basic * Move all docs to docs folder and rename some * Throw error if sweeps does not exist * Revamp tutorial * Add arguments in render, fix bugs * Use typing throughout, improve documentation * Improve installation instructions * Auto-clean and updated comments * More cleanup * Address some review comments * Rename variable * Remove deprecated output argument * Add new functions to tutorial * FIX CRITICAL BUG IN MASK_DECODE, Add list_anns, dynamic bow_line_width, change rendering order, improve tutorial * nuImages videos (#432) * Fix automatic test discover and disable test outputs * Add nuImages schema * Add function to render videos * Unified image and video rendering * Further improvements to render script * Fix bug around unchanged mode * Check number of sample_datas * Add new function to tutorial * Add sort order argument to list_categories * Fix sorting * Garbage collection to avoid memory overflow * Format * Reorganize render_images, add render_rare_classes * Rename has_rider attribute in test * Minor fix for tests on test set * Replace val with mini * Address review comments * Fix merge conflicts, remove warnings, change rendered car * Fix test for mini * Remove todo * Added filtering options to various scripts * Updated render_depth method (v2) (#437) * Separate methods for dense and sparse depth * More parameters for dense depth * Print velocity, fix fisheye * Workaround when no key_lidar_token is known * Fix previous modification * Filter by fileformat * Handle missing lidar * Same for depth_sparse * Update nuImages documentation, add ability to get segmentation masks, improve listing and rendering functions (#438) * Shift section of lazy loading * Remove sentence in README saying that files will not be available for public download * Inform user in tutorial that with_category must be True in order to set We can also set with_attributes=True * Inform user in tutorial that with_category must be True in order to set with_attributes=True * Section on setup before section on verifying install in installation.md * Shift lazy description back and just state at intro that it will be discussed later * Improve docstring and add assertion for render_image, allow list_attributes to be sorted * Change to in list_cameras * Change cones and barriers from black to gray in tutorial * Change foreground to object and background to surface * Allow user to choose to draw only boxes, surfaces, both, or all in render_image * Update tutorial to mention with_annotations options in render_image * Give user abiity to adjust font size in render_image * Add get_segmentation method * Classes are 1-indexed in masks * Address comments for nuimages and util * Address comments for tutorial * Tidy up tutorial * More content for instructions, improve structure of instructions * Address comments * Address some comments for instructions * Address more comments on instructions * Tidy up instructions a bit * Edits from proofreading * Re-introduce fonts_valid param in get_font * Align class indices in lidarseg and get_semgentation * Remove class descriptions, add attributes to instructions * Only include added attributes * Add link to attributes in instructions * Tidy up somemore * Proofread * Proofread again * Proofread more * Address more comments on instructions * Do not assume category.json is sorted when creating index map in get_segmentation * Add links for images for instructions * Fix list_anns * Add samples images for surface classes * Remove images * Add links to images * Address comments for phrasing * Added empty line before last image * Attempt to resolve requirements issue * Revert * Copy entire requirements folder * Fix wrong folder Co-authored-by: Holger Caesar <holger@nutonomy.com> * Resolve some warnings, adapt to new render function arguments * Add log name to the output path * Use future ego pose * Debug output * Don't do ego compensation * Remove lidar code in nuImages (#442) * Purge depth from code * Update documentation * Simplify variable names * Wording * Wording * Fix wrong assertion * Typo * Install pycocotools from conda-forge (#441) * install pycocotools from conda-forge * less verbose output * Minor corrections * Address review comments Co-authored-by: whyekit-aptiv <62535720+whyekit-aptiv@users.noreply.github.com> Co-authored-by: Valentyn Klindukh <valentyn.klindukh@nutonomy.com> * nuScenes 2.0 tutorial revamp (#446) * Add list_sample_data * Fix indexing bug * Fix type * Fix columns * Type conversion * Type conversion * Fix bug with different length of values and bins * By default, use standard font size * Workaround for mini split * Fix swapped dimensions * Add nuim.list_sample_data_histogram() * More verbose * Make matplotlib style attributes case-sensitive * Fix rendering issue in map expansion * Change figure alignment in prediction tutorial * nuImages data export (#447) * Add boilerplate * Add export script * Print status * Typo * Add mini split to all * Rename files * Skip only individual files * Fix file paths in mini * Remove redundant path * Add assert_download for nuImages * Clarification on past sweeps * VERY SLOW RENDERING with alpa composite * Simplify alpha composite * Cleanup * Update links and silence test * Update more links * Update FAQ * Fix requirements for new pip package (#449) * nuScenes v2.0 alpha (#452) * Fix broken link in readme * aummy typo * Add a note on bicycle rcks * Fix render_rare_classes, additional checks for object_tokens in render_image * Fix tutorials link * Address comments from nuScenes-lidarseg alpha testing (#451) * Fix broken link in readme * aummy typo * Add a note on bicycle rcks * Fix render_rare_classes, additional checks for object_tokens in render_image * Amend classes shown in tutorial * Add note for MacOSX users * Shift matplotlib macOSX tip to installaton.md instead * Updated backend instructions Co-authored-by: Holger Caesar <holger@nutonomy.com> * Update requirements * Address review comments * Address review comments * Address review comments Co-authored-by: whyekit-aptiv <62535720+whyekit-aptiv@users.noreply.github.com> Co-authored-by: Valentyn Klindukh <valentyn.klindukh@nutonomy.com> 01 September 2020, 08:45:09 UTC
274725a Sunil Chomal 07 July 2020, 09:37:42 UTC Update the script export_poses.py (#430) Update the script export_poses.py to correct variable name error. 'format' used instead of 'output_format' 07 July 2020, 09:37:42 UTC
261ec77 Holger Caesar 07 July 2020, 01:42:20 UTC Increment version number (#428) 07 July 2020, 01:42:20 UTC
e5aec76 Mohamed Zahran 06 July 2020, 00:15:02 UTC Function documentation typo (#426) Update the documentation of the function "convert_to_pixel_coords" from :param resolution: Center of image. to :param resolution: Resolution of image in pixels / meters. 06 July 2020, 00:15:02 UTC
20ab9c7 Holger Caesar 22 June 2020, 09:11:44 UTC Remove false known issue (#422) 22 June 2020, 09:11:44 UTC
709d77c Holger Caesar 19 June 2020, 02:40:10 UTC Add render_centerlines method (#421) * Added render_connectivity method, automatically determine figure size * Fix bug with high discretization resolution * Fix hollandvillage bug because one line is empty * Address review comments 19 June 2020, 02:40:10 UTC
da3630a Holger Caesar 09 June 2020, 00:52:33 UTC Detection eval - Fix bug if first key has no boxes (#408) * Fix bug if first key has no boxes * Outsource and test _get_box_class_field * Revert accidentally committed notebook update 09 June 2020, 00:52:33 UTC
ef1f1bd Holger Caesar 05 June 2020, 05:05:27 UTC Improved wording 05 June 2020, 05:05:27 UTC
2a60fea Holger Caesar 30 May 2020, 04:31:56 UTC Add known issues section (#402) * Add known issues section * Add to toc 30 May 2020, 04:31:56 UTC
0fddd0c HongyiSun 20 May 2020, 00:59:32 UTC Fix basic_tutorial name (#398) 20 May 2020, 00:59:32 UTC
a1bc4ca Freddy Boulton 19 May 2020, 05:58:57 UTC Clarifying that the first challenge is focused solely on vehicles (#395) 19 May 2020, 05:58:57 UTC
10bf48d Freddy Boulton 13 May 2020, 18:40:09 UTC Clarifying report length for prediction challenge (#391) 13 May 2020, 18:40:09 UTC
5341ceb Holger Caesar 11 May 2020, 02:43:31 UTC Link to EvalAI server (#387) 11 May 2020, 02:43:31 UTC
a0acd98 Holger Caesar 06 May 2020, 05:38:07 UTC Fix broken tutorial links (#385) * Fix broken links * Clarifications 06 May 2020, 05:38:07 UTC
be551d8 Holger Caesar 05 May 2020, 15:45:56 UTC Add dataroot to prediction tutorial, see #382 (#384) 05 May 2020, 15:45:56 UTC
3211ed8 jonahthelion 05 May 2020, 14:00:02 UTC make unit tests compatible with pytorch 1.2 + torchvision 0.4.0 (#374) 05 May 2020, 14:00:02 UTC
d97dd6b Holger Caesar 28 April 2020, 15:48:45 UTC Flip left and right in can bus readme (#373) 28 April 2020, 15:48:45 UTC
ae022ab Holger Caesar 21 April 2020, 09:38:21 UTC Addresses #358 (#360) 21 April 2020, 09:38:21 UTC
3758022 Freddy Boulton 08 April 2020, 02:56:46 UTC Adding information to the tutorial on doing inference with CoverNet (#353) 08 April 2020, 02:56:46 UTC
50bc5f2 Holger Caesar 08 April 2020, 02:40:10 UTC Export egoposes as latlon in json or kml format (#352) * Add script to export pose data (#347) * Added code to export as kml * Cleanup * Improved outputs * Less precision * Address review comments Co-authored-by: Jean Lucas <jeanlpf@hotmail.com> 08 April 2020, 02:40:10 UTC
1050c3d Holger Caesar 01 April 2020, 12:43:44 UTC Relax pip package requirements (#345) * Implementing mean pointwise l2 distance * Make torch and torchvision flexible, limit pillow to compatible versions Co-authored-by: freddy <freddy.boulton@nutonomy.com> 01 April 2020, 12:43:44 UTC
711b2eb Freddy Boulton 01 April 2020, 12:39:25 UTC Implementing mean pointwise l2 distance (#339) 01 April 2020, 12:39:25 UTC
6888661 Jean Lucas 01 April 2020, 08:34:55 UTC Update map origins docstring in map_api.py (#344) When loading the map layers through the new map layers API, we can see that these reference coordinates originate from the bottom left, (ie: south-western) corner, instead of south-eastern. A small change, but can cause some confusion. 01 April 2020, 08:34:55 UTC
e5370b6 Freddy Boulton 31 March 2020, 00:45:22 UTC Remove extra exclamation point from predict readme logo (#342) 31 March 2020, 00:45:22 UTC
784217e Freddy Boulton 27 March 2020, 13:00:52 UTC Adding logo to prediction README (#340) * Adding logo to prediction README * challenge -> task * Remove empty line * Remove boilerplate text at the top of the readmes * Logo name Co-authored-by: Holger Caesar <holger@nutonomy.com> 27 March 2020, 13:00:52 UTC
d578e7f Freddy Boulton 24 March 2020, 21:06:27 UTC Rename predict to prediction (#337) * Clarify that there are more than 4 map files now * Increment devkit version to v1.0.7 * Notes on the 2020 detection challenge * Note on covid * Adding update on COVID-19 to prediction readme * renaming predict directories to prediction * Rename predict -> prediction * add nuscenes/dev-challenge:9.2 image * Changing name of image in example command Co-authored-by: Holger Caesar <holger@nutonomy.com> Co-authored-by: Valentyn Klindukh <valentyn.klindukh@nutonomy.com> 24 March 2020, 21:06:27 UTC
b2f9b7d Holger Caesar 24 March 2020, 12:54:02 UTC Information on the 2020 detection challenge, pip version v1.0.7 (#335) * Clarify that there are more than 4 map files now * Increment devkit version to v1.0.7 * Notes on the 2020 detection challenge * Note on covid * Adding update on COVID-19 to prediction readme * Rewording Co-authored-by: freddy <freddy.boulton@nutonomy.com> 24 March 2020, 12:54:02 UTC
a835768 Holger Caesar 23 March 2020, 15:10:25 UTC Move all tutorials to common folder (#331) * Move all tutorials to common folder * Fix file extension * Add other notebooks for testing * Adding prediction tutorial to tutorial directory * Removing cell output from tutorial notebook * Removing imshow from prediction tutorial * Uncommented tutorial tests * Disable rendering * Added a test for each nuScenes map * Increment version number to 1.2 * Modifying sed commands to comment out plots in can bus * Fixing typo in map_expansion sed command * Commenting out ego_poses Co-authored-by: freddy <freddy.boulton@nutonomy.com> 23 March 2020, 15:10:25 UTC
42d0c25 Freddy Boulton 20 March 2020, 14:03:19 UTC nuScenes prediction challenge (#326) * Adding PredictHelper class and unit tests (#280) * Adding PredictHelper class and unit tests * Adding docstring to convert_global_coords_to_local * Refactored get_future and get_past for agent and sample to reduce code duplication * Adding copyright header to source files * Adding typehint for _timestamp_for_sample * Raise error when seconds is negative. Ensure we do not return data when seconds is 0 * Cleanup * More formatting suggestions * Change argument format * Cleanup. Add _token suffix to variable names. * Moving tests/test_predict_helper.py to predict/tests/test_predict_helper.py * Fleshing out docstrings for PredictHelper * Adding return type for _get_past_or_future_for_sample Co-authored-by: holger-nutonomy <39502217+holger-nutonomy@users.noreply.github.com> * nuScenes-predict evaluation code (#283) * Adding PredictHelper class and unit tests * Adding docstring to convert_global_coords_to_local * Adding methods to helper to get velocity, hcr, and acceleration * Adding utility function to get instances in each split * Adding prediction scenes json file for determining train-val splits * Adding implementations of ConstantVelocityHeading and PhysicsOracle * Adding skeleton of eval/predict folder * Removing commoent from predict/models * Refactored get_future and get_past for agent and sample to reduce code duplication * Adding copyright header to source files * Adding typehint for _timestamp_for_sample * Raise error when seconds is negative. Ensure we do not return data when seconds is 0 * Adding Metrics, config, and eval_pipeline * sec_from_now is now a parameter for models * Fixing type hints in physics models and adding docstrings to Model classes * Adding dataroot param to compute_metrics * Adding data_root to do_inference * Adding dataroot as command line argument * Adding updated train val split for nuscenes-predict * Organize imports * Cleanup * Cleanup Models * Adding Attributes to Prediction dataclass docstring * Adding docstring to main method * Adding docstrings to baseline_model_inference.py * Adding docstrings to models.py * Fixing unittests that got deleted * Moving splits to eval/predict/splits.py * Adding docstrings to eval scripts. Fixing split import * Adding docstrings for do_inference.py * Adding data_root param to baseline_model_inference.py * Fixing bug in test Co-authored-by: holger-nutonomy <39502217+holger-nutonomy@users.noreply.github.com> * Mtp baseline (#291) * Adding implementation of MTP model and unit tests * Adding unit tests for the unimodal case * batch_losses are a list. Avoiding autograd errors this way * Adding script to see if mtp can overfit on a single example * Making modifications to mtp and run_mtp to use cuda * Adding comments to predict/config * Adding type hints for mtp * Fixing typo in trim_network_at_index * Format changes * Reorganize imports * Adding comments, fixing docstring * Adding default parameter to regression_loss_weight Co-authored-by: Holger Caesar <39502217+holger-nutonomy@users.noreply.github.com> * Module for Input Representation (#295) * Adding implementation of MTP model and unit tests * Adding unit tests for the unimodal case * batch_losses are a list. Avoiding autograd errors this way * Adding script to see if mtp can overfit on a single example * Making modifications to mtp and run_mtp to use cuda * Fix bug where the canvas_size was not retrieved from the patch_box * Adding get_map_name_from_sample_token to PredictHelper * Adding interface for input representation and static map layer representation * Removing get_2d_rotation function * Adding comments * Adding stress test for memory consumption of image generation * Fixing small typo bugs in run_image_generation * Adding option to predict helper to return the entire record as opposed to just xy * Adding unit tests for agents, combinators, static_layers, utils in input_representation * Adding comments and check for resolution > 0 Co-authored-by: Holger Caesar <39502217+holger-nutonomy@users.noreply.github.com> * Predict Challenge README (#296) * Adding first draft of README to explain rules of prediction challenge * Adding README for predict challenge * Removing link to eval ai since it is not set up yet * Fixing typos and clarifying general rules * Typo * Evaluation is now based on val set Co-authored-by: Holger Caesar <39502217+holger-nutonomy@users.noreply.github.com> * Add lane center lines to map json files (#301) * Adding code to draw lanes * Removing print statement * Adding arcline path utils module to discretize lanes * Adding ability to color by the yaw difference and splitting functions up a little bit * Adding unit tests * Adding lookup_polygon_layers list so that lane_connectors can be searched for but not rendered * Adding comments to arcline path util functions * Adding unit tests to map_expansion arcline_path_utils module * Adding more informative print statement to load_all_maps * Changing function names in discrete_path_utils * Added stylistic changes * Fixing type signatures and docstrings * Adding comment explaining how the pose is represented as a tuple Co-authored-by: Holger Caesar <39502217+holger-nutonomy@users.noreply.github.com> * Add Lane Connectivity Clean (#308) * Adding methods to map api for querying for connected_lanes * Loading the connectivity in its own function so the types are consistent * Extra spline utilities clean (#309) * Adding spline utilities * Adding tests * Calculating canvas_size in StaticLayerRasterizer so custom resolution can be used (#310) * Covernet baseline (#305) * Adding code to draw lanes * Removing print statement * Adding arcline path utils module to discretize lanes * Adding ability to color by the yaw difference and splitting functions up a little bit * Adding unit tests * Adding lookup_polygon_layers list so that lane_connectors can be searched for but not rendered * Adding comments to arcline path util functions * Adding unit tests to map_expansion arcline_path_utils module * Adding more informative print statement to load_all_maps * Adding backbones to own module. Adding covernet implementation * Covernet implementation and unittests * Adding unit tests for covernet and script to test if it can overfit on single image * Making covernet compatible with the GPU * Fixing copyright headers * Addressing Corina's comments * CV Baseline Bug (#317) * Fixing bug in ConstantVelocityHeading baseline * Fixing docstring for sampled_at in kinematics functions * Add off road rate metric (#318) * Adding convert_local_coords_to_global utility function * Fixing bug in ConstantVelocityHeading baseline * Implementing OffRoadRate metric. Updating metric deserialization and adding unit tests * Rewritting test for OffRoadRate to no longer use polygons * Setting the proper dataroot in _do_test * Removing polygon json files * Adding docstring and comment to load_drivable_area_polygons method * Tutorial + Finishing Touches (#325) * Adding is_valid method to prediction. Adding tutorial * Being clear that the model prediction must be in the global frame * Updating baseline_model_inference and compute_metrics * Adding prediction scenes split * Implementing MissRate metric * Correcting typos, adding docstrings, standardizing copyright * Adding docker_container and submission directories * Updating docker README * updating split * OffRoadRate uses the masks instead of polygons * Submission period starts april 1 * Removing PredictionConfig from config_factory * Removing PredictionConfig Import * Minor cleanup * Incorporating Holger's feedback v1 * Adding lane methods to nuscenes map demo * Changing hit to miss in nuScenes predict challenge * Organize imports * Cleanup, remove notebook outputs * Rename onenorth to nusc_map * Organize imports * Rewording of the tutorial * Cleanup * Removing MAINTAINER from docker file * Clearing map demo * Adding docstrings to metrics and other misc edits * Condensing cells in tutorial and adding a visualization * Changing the location of prediction_scenes.json * Adding checks the PhysicsOracle is called with the right amount of ground truth data * Fix markdown * Minor typo in README * Making docstrings consistent Co-authored-by: holger-nutonomy <39502217+holger-nutonomy@users.noreply.github.com> Co-authored-by: Holger Caesar <holger@nutonomy.com> 20 March 2020, 14:03:19 UTC
14573b0 Holger Caesar 19 March 2020, 00:51:03 UTC Improve readability of CAN bus readme (#332) 19 March 2020, 00:51:03 UTC
336397e Holger Caesar 17 March 2020, 07:33:51 UTC CAN bus refactor (#330) * Refactor plot_can_message_stats, add to tutorial * Render vehicle speed vs wheel speed * Corrected wrong radius 17 March 2020, 07:33:51 UTC
e99d463 Holger Caesar 16 March 2020, 09:33:41 UTC Removed firetruck from instructions (#329) 16 March 2020, 09:33:41 UTC
41605aa Holger Caesar 05 March 2020, 03:53:53 UTC Get next roads function (#315) * Add function to get next road(s) from x,y coordinates (#306) * add function to get next road(s) from x,y coordinates * add docstring * add docstring * Cleanup * New method to render next roads * Raise an exception if an old version * Add get_next_roads to tutorial Co-authored-by: bobcchen <47989178+bobcchen@users.noreply.github.com> 05 March 2020, 03:53:53 UTC
4e9e0a9 Holger Caesar 18 February 2020, 03:45:07 UTC Fix motmetrics version (#300) 18 February 2020, 03:45:07 UTC
8542a60 Holger Caesar 13 February 2020, 09:36:09 UTC Fix bug in new version of setuptools (#297) 13 February 2020, 09:36:09 UTC
3758f71 Holger Caesar 13 February 2020, 08:30:50 UTC nuScenes CAN bus extension (#294) * CAN bus expansion * Renamed folder * Improved documentation * Change folder name * Fix broken link and improved rendering * Rewording and typos * Add notes in main nuScenes readme * Improve readme * Increment devkit version 13 February 2020, 08:30:50 UTC
8877b19 Holger Caesar 07 February 2020, 06:52:52 UTC Fix bug where points close to ego vehicle were filtered after transformation (#288) 07 February 2020, 06:52:52 UTC
0f7c50f Holger Caesar 07 February 2020, 00:14:34 UTC Fix bug where the canvas_size was not retrieved from the patch_box (#292) 07 February 2020, 00:14:34 UTC
4ca77b0 holger-nutonomy 31 January 2020, 10:12:40 UTC Add an option to disable all radar filters (#289) * Add an option to disable all radar filters * Add an example to the tutorial on how to change the filter settings 31 January 2020, 10:12:40 UTC
02e9200 holger-nutonomy 30 January 2020, 08:56:57 UTC Disable slow unittests (#286) * Skip slow unit tests * Reorganize improts 30 January 2020, 08:56:57 UTC
0534384 holger-nutonomy 28 January 2020, 08:32:06 UTC Fix _is_line_record_in_patch bug (#284) 28 January 2020, 08:32:06 UTC
06485f7 holger-nutonomy 28 January 2020, 08:31:48 UTC Map API: Return all axes, not just one (#285) * Return all axes, not just one * Rewording 28 January 2020, 08:31:48 UTC
db2df52 holger-nutonomy 17 January 2020, 06:07:36 UTC Update code to map version 1.1. Most scenes now fit (#279) 17 January 2020, 06:07:36 UTC
fc57a70 holger-nutonomy 13 January 2020, 02:56:38 UTC Add requirements on pandas version as older versions are not supported (#275) 13 January 2020, 02:56:38 UTC
9fa456a holger-nutonomy 07 January 2020, 06:52:13 UTC Standardize ego_dist and ego_translation (#270) 07 January 2020, 06:52:13 UTC
07c06dc Valentyn Klindukh 20 December 2019, 06:11:47 UTC switch to new cloud (#261) 20 December 2019, 06:11:47 UTC
3c872ca holger-nutonomy 17 December 2019, 00:33:58 UTC Instructions how to use Yonohub (#267) * Update readme to v1.0.5 * Update to v1.0.5 * Add a section with references to Yonohub 17 December 2019, 00:33:58 UTC
a9c16ed holger-nutonomy 10 December 2019, 16:44:07 UTC Remove weighting factor from AMOTA (#266) * Remove weighting factor in AMOTA * Update test targets with new amota weighting * Update baseline results after removing amota weighting 10 December 2019, 16:44:07 UTC
e2d8c4b holger-nutonomy 06 December 2019, 09:42:19 UTC Add tracking eval server link, adjust challenge deadline (#262) * Add tracking eval server link, adjust challenge deadline * Replace tracking challenge logo * Adjust deadline 06 December 2019, 09:42:19 UTC
7149db1 holger-nutonomy 19 November 2019, 10:20:48 UTC Misc - Tracking output format and missing requirements (#258) * Updated results table * Increment version, add authors, reformat table * Add missing requirement * Additional comments and assertions * Align tracking return type to detection return type * Increment version * Rewording * Drop unnecessary argument from deserialize * Added comment, corrected syntax 19 November 2019, 10:20:48 UTC
e73cda8 Caglayan (Cha) Dicle 18 November 2019, 15:27:11 UTC Implement edge case test scenarios (#256) * Implement edge case test scenarios * Cleanup * Add a test that causes switches, fix setup for unachieved recall values 18 November 2019, 15:27:11 UTC
d60d7b1 Caglayan (Cha) Dicle 13 November 2019, 08:13:28 UTC Tracking eval BEV visualization (#254) * Replace ego_diff by ego_translation * Implement basic visualization * Render each object with unique color * Encapsulate and expose renderer * Pass output directory to renderer * Visualize switches by changing front-back color * Cleanup * Remove warnings * Fixed all but one unittest * Fixed bug where ego_dist was not set * Change output folder name 13 November 2019, 08:13:28 UTC
a093f3a holger-nutonomy 05 November 2019, 20:06:49 UTC nuScenes tracking evaluation improvements (#251) * Remove lap solver which is slower and causes issues in continuous integration * Switch to 20 point evaluation for more accurate results * Switch to 40 point evaluation * Remove unused config fields * Make test_algo independent of the number of recall thresholds * Update test target values after changing number of recall thresholds * Optimize memory usage by freeing up NuScenes object * Update readme to reflect val results and 40 point interpolation 05 November 2019, 20:06:49 UTC
0e32541 holger-nutonomy 04 November 2019, 10:25:10 UTC Tracking eval (#227) * Initial tracking readme * Added KITTI classes and some other details * AMOTA definition and misc * Added AMOTP eq * Clarification of metrics * Initial object detection baselines * Updated AIDO link * Added detections download links * Fixed equation dpi * Improved eq rendering * Improved AMOTA explanation * Metric clarifications * Addressed review comments * Added clarification on confidence thresholding * Initial commit that moves out code common to detection and tracking; passes all previously existing tests * Adding new tracking classes * Start adding structure to evaluate function * Simplified code * Major refactor, split EvalBox in TrackingBox and DetectionBox * Fixed bug that made detection code irreproducible * Move DetectionBox class to detection folder, create TrackingBox class * Fixed GT loading, created dummy metric functions * Fixed type warnings in EvalBoxes, major cleanup * Start integrating external code * Applied snake case and fixed method names * Add munkres requirement * Create tracks (#231) * create tracks grouped by scene * Minor restructuring * Fixed broken logic to select box class, changed tracking_id to be a string * Use create_tracks for preds and gt * Major reorg, outsourced Hungarian method and metric compuation to separate methods * Reorganized distance function and threshold * Pass tracks instead of boxes * Fixed Hungarian method * Cleanup * First outputs, moved all external code in one file, removed unused code * Renamed file * Cleanup and remove Mail class * Reorganize compute_all_metrics * Fix metric computation * Meaningful thresholds, remove unused metrics * Using py-motmetrics for evaluation (#234) * Calculate metrics per threshold * Print all threshold results together * Implement track initialization duration custom metric * Add distance thresholding * Fixed bug where acc is reset for every scene, cleanup * Cleanup * Reworked create_tracks to guarantee every timestamp is present * Add mapping from timestamp to frameid, augment test pred tokens with "_pred" for better debugging * Update TID calculation wrt new frame indexing * Implement average longest gap duration (LGD) and correct TID calculation * Add test_diff with ground truth * Fixed bug where all scenes were used rather than only from the chosen split, sort results by timestamp, remove unneeded timestamp field * Setup TrackingMetrics * Fix bug for classes without GT, fix bug where class was not filtered, sort classes by name, compute mean metrics, set target metric value for tests * Fix error when serializing ndarray * Updated requirements * Compute recall thresholds * Add other metrics * Penalize unachieved recall values * Implemented amota/amotp metrics * Init raw_metrics to nan, outsource print statements * Fix error due to lowercase and uppercase metric names * Simplify best threshold name query * Refactor best value query * Print metrics in test, improve printing, fix bug due to GT scores being all 1 * Move metrics to a separate file and implement custom MOTA skeleton * Fixed bug as we need both MOTA and MOTAp (MOTA') * Implemented MOTA' outside motmetrics * Deleting idf1 metric altogether from the challenge * Move MetricDataList to detection-only code, refactoring * Remove references to deprecated license * Revamped and outsourced printing metrics * More intuitive outputs and consistency checks on some metrics * Simplified frame retrieval * Opposite sort order for thresholds * Fixed bug where all test GT examples have score close to 0.5, fixed bug where some metrics were not initialized as nan, better error handling * Clarified in readme that we are averaging over classes * Change type of tracking_id to str * Compute MOTAP inside motmetrics, avoid bug in mh.compute_many * Fix frame_id collusion * Adapted test targets after previous bugfix, Print num_frames, Assertion takes into account IDS * Use exact recall in MOTAP rather than "desired" recall * Wrong sign in AMOTA equation * Escape braces as required by some markdown interpreters * Clarifications on the AMOTA/AMOTP equations * Add a faster linear assignment solver * Handle case where sample has no boxes to avoid warning * Punish unachieved recall values by setting worst possible value for MOTA/MOTP * Define standard motmetrics without global metrics which are slower * Significantly speed up accumulate * Use verbose flag, cleanup * Outsource content from compute_all_metrics * Fix circular dependency bug * Progress bar and cleanup * Move motmetrics into the repo * Delete unneeded file * Overwrite single method from motmetrics and otherwise use pip package * Update lgd tid calculations * Fixed division by zero bug * Major refactoring to store per-threshold results used for testing and plots * Store the list of metrics in a single place, set worst value for unachieved recall * Compute recall and assertions * Cleanup * Store all metrics as lowercase, Render plots for each metric * Refactoring, fix serialization * Rewrite LGD to consider frames with no GT, some metrics are summed rather than averaged, only average for AMOTA/AMOTP if at least one valid entry, filter mock submission by num_pts, check more metrics in test * Improved metrics printing * Use hypothetical recall in plots * Create summary plot, cleanup, fix test target * Enforce MOTA >= 0 * Outsource common setup_axis method * Fix broken assertion, add tp metric, improved plotting, test on other splits * Restructure code, change outputs * Added todos, fixed bug where values were filtered, not confidence * Fix bug with uninitialized tp metric * Remove detection metrics, rename MOTA' to MOTAP * Renamed MOTAP to MOTAR * Cleanup, add render_curves option * Standardize number printing format * Fix 2 minor bugs from detection refactoring * Implement track interpolation * Correctly interpolate quaternions, disable interpolate until GT test is fixed * Add simple tests, proper treatment when less than 10 thresholds achieved * Rework test suite * Fix bug where scores were not interpolated/set * Don't store variables to reduce memory footprint * Used defaultdict to simplify loaders (#245) * used defaultdict to simplify code * Guarantee that each timestamp is initialized * Made tracking unit-tests silent and executed by default (#246) * used defaultdict to simplify code * made tracking unit-tests silent and executed by default * Suppress deprecation warning * Fix broken diff * Hide progress bar if not verbose * Address review comments, resolve some warnings * Attribute py-motmetrics * Fix critical bug in thresholding, change logic to get accurate recall thresholds * Adjust and improve tests * Fix custom accumulator misdirection * Parallelize accumulation * Use original accumulator * Extend custom accumulator * Use custom accumulator * Use individual accumulators per scene merge later * Turn off parallelization * Attribute authors, cleanup * Fix bug and simplify LGD metric, cleanup * New test * Added getting started section to readme * Minor bugfix on verbose keyword, workaround for unachieved recall thresholds, added baseline results * Assign worst possible value if we, output GT boxes, added test for empty submission * Added weighting factor in MOTAR, Print MOTA instead of MOTAR * Change plotting order * Changed weighting factor and baseline results 04 November 2019, 10:25:10 UTC
f25a166 holger-nutonomy 19 October 2019, 01:41:26 UTC Fixed visualization bug where radar returns were not rotated (#243) * Fixed visualization bug where radar returns where not rotated * Renamed variable 19 October 2019, 01:41:26 UTC
f3594b9 holger-nutonomy 11 October 2019, 00:42:34 UTC Switch devkit to Apache license (#240) * Apply Apache license * Purge reference to outdated license in every file 11 October 2019, 00:42:34 UTC
0d8874f holger-nutonomy 04 October 2019, 09:56:31 UTC Add option to render pointcloud intensities (#236) * Add option to render pointcloud intensities * Added error message in case we are plotting radar * Added example to tutorial how to render lidar intensities 04 October 2019, 09:56:31 UTC
de4d1e2 holger-nutonomy 01 October 2019, 00:27:24 UTC Addressed review comments (#232) 01 October 2019, 00:27:24 UTC
8864313 holger-nutonomy 27 September 2019, 01:38:53 UTC Added notes that CVPR challenge is over (#230) * Added notes that CVPR challenge is over * Typo * Typo 27 September 2019, 01:38:53 UTC
c2bf747 holger-nutonomy 24 September 2019, 07:57:02 UTC Lyft compatibility default settings (#226) * Enable underlay_map and use_flat_vehicle_coordinates by default. * More detailed comments * Typo * Remove ego_to_lidar option 24 September 2019, 07:57:02 UTC
54b9f81 holger-nutonomy 23 September 2019, 15:31:05 UTC Tracking task document (#220) * Initial tracking readme * Added KITTI classes and some other details * AMOTA definition and misc * Added AMOTP eq * Clarification of metrics * Initial object detection baselines * Updated AIDO link * Added detections download links * Fixed equation dpi * Improved eq rendering * Improved AMOTA explanation * Metric clarifications * Addressed review comments * Added clarification on confidence thresholding * Corrected confidence threshold, added note on average over classes * Cleanup * Cleanup and remove link 23 September 2019, 15:31:05 UTC
a28ee56 holger-nutonomy 13 September 2019, 05:47:30 UTC Lyft compatibility (#221) * Support for another nuScenes-fromated dataset. (#204) * Remove explicit version check * Cleanup * Major overhaul of render_sample_data and render_ego_centric_map * Fix color bug * Cleanup 13 September 2019, 05:47:30 UTC
cfc9ade holger-nutonomy 10 September 2019, 11:40:42 UTC Add rendering options (#223) (#224) * Add rendering options (#223) * Cleanup * Cleanup * Addressed review comments 10 September 2019, 11:40:42 UTC
c480b4f holger-nutonomy 02 September 2019, 09:39:17 UTC Miscellaneous improvements: Plot settings, default number of sweeps (#215) * Don't include pycache folders in pip package, added new author * Include license in pip package * Improve evaluation plot limits * Use known stable Docker build * Fixed deprecated link * Changed default number of sweeps to 5, cleanup * added typing 02 September 2019, 09:39:17 UTC
f157d00 Valentyn Klindukh 30 August 2019, 01:33:32 UTC Dv 720/fix jenkins failure (#216) * test env * escape dollar sign * escape dollar sign * test 30 August 2019, 01:33:32 UTC
b68ebc5 Kiwoo Shin 27 August 2019, 07:13:25 UTC Split get_map_mask into multiple functions (#208) * get geoms inside a given patch box * type error * Changed the order of arguments in _get_geom_mask and various cosmetic changes * Introduced Geometry type, cleanup * Fixed incorrect order of height and width in docstring * wip: remove duplicate * bug in using MultiLineString fixed * Removed temp file * get_map_mask * Renamed private functions, renamed patch_box to local_box where appropriate, cleanup 27 August 2019, 07:13:25 UTC
a695866 holger-nutonomy 26 August 2019, 04:06:46 UTC Split train set into train_detect and train_track (#212) * Split train set into train_track and train_detect, no modifications to train, cleanup * Using stable version of miniconda Docker to avoid errors * Clarification on different splits and added assertion 26 August 2019, 04:06:46 UTC
ac347b3 Martin Hahner 23 August 2019, 10:19:11 UTC render_annotation improved (#207) * render_annotation improved render extra information about the annotation below the CAMERA view * Minor cleanups 23 August 2019, 10:19:11 UTC
498226c holger-nutonomy 07 August 2019, 09:32:06 UTC Added link to the conda distribution issue, closes #155 (#206) 07 August 2019, 09:32:06 UTC
2bbc568 Martin Hahner 07 August 2019, 08:55:14 UTC render_instance improved (#205) render_instance with all parameters adopted from render_annotation 07 August 2019, 08:55:14 UTC
df47967 holger-nutonomy 05 August 2019, 02:35:38 UTC Render egoposes in map (#196) * Renamed NuscenesMap to NuScenesMap, setup boilerplate code for render_map_in_image * First attempt to render map on image * Different approach to init axes * Integrated render_map_in_image in ipython notebook * Rewording * Debug * Initial working projections, refine filtering * Cleanup, default arguments, adjust map height, filter polygons by area * Implemented clipping * At last a working copy * Deal with drivable_area * Added additional arguments and performed checks * Added docstrings * Finalized tutorial * Implement render_egoposes_on_fancy_map, pending transparency and lim issues * Fixed transparency issues and improved rendering * Input checks * Added ego pose rendering in map demo * Improved margins * Cleanup * Added debug flag * Added warning to scenes with bad map alignment * Remove redundant log_location field and rename debug->verbose * Reset scene filtering logic * Minor updates to tutorial * Addressed review comments 05 August 2019, 02:35:38 UTC
918a74c holger-nutonomy 30 July 2019, 04:45:52 UTC Project map to image, resolves #188 (#195) * Renamed NuscenesMap to NuScenesMap, setup boilerplate code for render_map_in_image * First attempt to render map on image * Different approach to init axes * Integrated render_map_in_image in ipython notebook * Rewording * Debug * Initial working projections, refine filtering * Cleanup, default arguments, adjust map height, filter polygons by area * Implemented clipping * At last a working copy * Deal with drivable_area * Added additional arguments and performed checks * Added docstrings * Finalized tutorial * Pass on arguments * Addressed Sourabh's comments * Bug fix for points behind the camera 30 July 2019, 04:45:52 UTC
9984e71 holger-nutonomy 22 July 2019, 08:35:56 UTC Map workaround for singapore-queenstown (#190) * Fixed bug for Queenstown map which has a line without nodes * Added warning note 22 July 2019, 08:35:56 UTC
1c70dd0 holger-nutonomy 15 July 2019, 05:48:37 UTC nuScenes map expansion pack (#172) * Initial commit * Added missing descartes requirement * Overhauled tutorial * Renamed map files * Fix wrong file extension * Renamed map extension to map expansion * Fix wrong import, clear outputs * Fixes for queenstown map * Overhauled map tutorial * Fixed wrong output message * Added detailed information on map origin and size * Reorganized readme and faq for map expansion pack * Rewording * Minor fixes to the map tutorial * Change order of the getting started bullet points * Binary map mask api and visualization example (#181) * rename map_graph to map_api * wip: rendering * rendering * map api done * visualization example * Renamed MapAPIExplorer to NuscenesMapExplorer * Reformatting * Reformatting * Undo spacing bug * Fix missing return statement * Added n_rows as argument * Pass on n_rows argument * Improved tutorial visualization * Updated naming conventions, first extract raw data then visualize, changed order * Rename `get_map_patch_mask` to `get_map_mask` and change output format to be a stacked numpy array * Added instructions for rotated map patches * Updated typing * Plot whole map by default * Typo in the map names * Round canvas size * Swapped order of arguments * Handle case where canvas_size is not given to render_map_mask * Started on semantic prior check * Fixed bug with swapped height/width * More experiments on reconstructing semantic prior * Removing comparison to semantic_prior * Delete test.py 15 July 2019, 05:48:37 UTC
4d3bab4 holger-nutonomy 28 June 2019, 05:58:28 UTC Cleanup of the export_2d script (#179) * Improved comments and added a parameter to export only a subset of the images * Cleanup 28 June 2019, 05:58:28 UTC
75ecbdc holger-nutonomy 27 June 2019, 10:55:13 UTC Pointcloud projection issue workaround (#177) * Clarification on the localization * Added a fig for the projection bug with points behind the camera #175 * Increased min distance threshold to 1m and made it a parameter 27 June 2019, 10:55:13 UTC
3c64082 Valentyn Klindukh 27 June 2019, 01:34:23 UTC Dv 530/update jenkins job (#178) * add parallel stages * update path to yamlFile * update labels * keep docker agent running 27 June 2019, 01:34:23 UTC
3770ede holger-nutonomy 26 June 2019, 23:47:26 UTC Loading image_annotations table if available (#174) 26 June 2019, 23:47:26 UTC
89af92b holger-nutonomy 20 May 2019, 23:56:46 UTC Print per class metrics after evaluation (#159) 20 May 2019, 23:56:46 UTC
57de64c holger-nutonomy 20 May 2019, 23:56:29 UTC nuScenes KITTI 2d boxes (#158) * Convert 3d boxes to 2d for kitti * Bug fix with swapped sign * Ignore boxes that are behind the camera * Fix wrong type hint * Fix order of statements * Return none if no corners in image * Added assertion for debugging and shortened output precision * Fix cropping and ignore boxes that don't fall into the image * Tools to plot 2d boxes * Debug output * Fleshed out comments * Added disclaimer to 3d-2d projection 20 May 2019, 23:56:29 UTC
5ec8a39 holger-nutonomy 20 May 2019, 05:06:50 UTC Re-added simple config factory (#157) 20 May 2019, 05:06:50 UTC
da042f3 holger-nutonomy 17 May 2019, 08:08:27 UTC nuScenes to KITTI conversion (#153) * Corrected comment * Clarification about zipped result file * Added copy method to box class * Added nuscenes to kitti conversion * Added typing hints * is_mini not currently working, attempting train/val * Removed test, more flexible splits * Documentation, command line arguments * Render example images * Render all images * Moved kitti to utils * Command line argument to choose whether to render images to disk * Added documentation, command-line argument and made a method public * Cleanup * add license * Renaming * Renaming * Simpler script for nuScenes to KITTI conversion * Set default path * Create output folder * Comments * Specify splits when loading result file * Workaround for mini splits * Fix bug when creating output folder * Indent jsons, set score to 0 by default * Parse score by default * Conversion from str to float * Set dummy velocity * Convert tuple to ndarray * Delete roundtrip script * Example code for visualization * Added separate render method * Close windows and limit number of images to render * Make only one dir * Removed image_sizes.json file and renamed label folder to label_2 * More explicit parameters, single split * Updated splits elsewhere * Updated table names * Remove verify method * Update table names * Use proper negation operator * Updated table names * Updated documentation * Use nuScenes category colors * Skip categories that are not part of the nuScenes detection challenge * Fix label colors * Updated comment * Simplify token to be nuscenes sample_token * Readd split to token * Remove tokens.txt * Remove extension from token * Fix bug if no scores are available, remove unused argument * Comment on KITTI parameters * Addressed review comments 17 May 2019, 08:08:27 UTC
3de8a5e Alex Lang 14 May 2019, 09:06:30 UTC Update CI (#151) * update ci to new folders * cleanup files * add tests on requirements * fix environments * correctly exit upon first error * reorganize tests * Adapted test to updated submission format (#150) * revert some changes * Revert "revert some changes" This reverts commit feb4eb91f2573cd7e84543645c1a1e04da77508f. * Convert config files to json (#148) * switch to json for configs * cleanup setup and file handling * fix unittests * use context manager on all open files 14 May 2019, 09:06:30 UTC
ab7256b holger-nutonomy 14 May 2019, 01:35:05 UTC Clarified the definitions and rules of the three challenge tracks (#147) * Clarified the definitions and rules of the three challenge tracks * Added sentence on using other modalities at test time * Formatting 14 May 2019, 01:35:05 UTC
27e4829 Alex Lang 13 May 2019, 07:38:16 UTC Add deserialize to DetectionMetrics (#146) * add deserialize to DetectionMetrics * Formatting 13 May 2019, 07:38:16 UTC
6761b7f holger-nutonomy 07 May 2019, 02:31:48 UTC nuScenes challenge rules, eval server link and more robust error handling (#141) * Improved error messages * Improved error messages * Compute ap over all classes, more comments * Add assertion to check for old format * Added more clarifications to the challenges * Added link to EvalAI 07 May 2019, 02:31:48 UTC
08e52c0 holger-nutonomy 03 May 2019, 01:50:19 UTC Documentation overhaul (#138) * Commented out statements that are likely to crash in notebooks * Limit length of the location string * Added units to translations and sizes, minor reformatting * Refine schema introduction and point to tutorial * Added check that result_path exists * Reworded results file instructions * Clarified that the color corresponds to the depth, not height * Added FAQs * Whats next in nuscenes * Restructured readmes * Overhauled installation instructions 03 May 2019, 01:50:19 UTC
11332fa holger-nutonomy 30 April 2019, 04:00:02 UTC Loosen PIP requirements (#136) * Make requirements less strict * Added clarification on file name, minor corrections 30 April 2019, 04:00:02 UTC
21771d6 holger-nutonomy 12 April 2019, 02:04:05 UTC Detection eval results format and readme (#115) * Added meta data to submission and rewording * Overhauled readme and comments * Make it explicit that 0.5s time window is only relevant at test time * Modified eval code for new result format * Renamed weighted_sum to nd_score * Clarification on maximum time window * Added option to use test set with annotations for eval server * Also writing meta data to output file * Write only a subset of examples to disk, create example folder * Make sure test GT is not visualized and plot 10 examples by default. * Print metrics to stdout * Standardize number format * Write more user-friendly metric names to stdout * Refactoring: Moved writing to disk/stdout one level up, renamed run() to evaluate(), made main a class method * Option to not render curves * Fixed return type and docstring * Save mean_dist_aps to directly show them in the leaderboard 12 April 2019, 02:04:05 UTC
9e4ecbb sergi-nutonomy 10 April 2019, 05:23:08 UTC Export 2d annotations (#97) * Initial commit * Removed cv2.rectangle * Use nuscenes methods, removed return * Venice's comments * Missing return docstring * Handles the instances where the box extends outside image * Addressed Oscar's comments * path, doscstring mistakes * ANY * filename * Some changes: 1. Retrieve the corners of the 3D bounding box that is in front of the camera. 2. Used the convex hull of the corners. 3. Retrieve the intersecting polygons. 4. Bounding box corners is decided from the intersecting polygons * Docstrings * Cleanup * nargs * Added shapely to the requirements 10 April 2019, 05:23:08 UTC
0611271 chris-li-nutonomy 08 April 2019, 20:06:54 UTC * Added xvfb to list of packages to install. (#103) * Re-organized Jenkins pipeline such that build and test occurs in separate stages. * Added logic to test notebooks during Jenkins pipeline. * Deleted old bash scripts for testing. 08 April 2019, 20:06:54 UTC
3e1f93e sourabh-nutonomy 08 April 2019, 18:27:19 UTC Update NuScenesExplorer (#99) * added out_path args to all render methods * assert video extensions are .avi. bugfix in cv2.VideoWriter 08 April 2019, 18:27:19 UTC
d969a17 Donghyeon Won 02 April 2019, 18:27:21 UTC EvalBoxes bug quick fix (#106) 02 April 2019, 18:27:21 UTC
99a8e5f Qiang Xu 27 March 2019, 18:29:54 UTC Remove empty lines in README. (#102) 27 March 2019, 18:29:54 UTC
a70f29c Alex Lang 27 March 2019, 16:43:02 UTC Add paper references (#101) * Added paper references to readme 27 March 2019, 16:43:02 UTC
fec7e13 Oscar Beijbom 26 March 2019, 23:08:11 UTC updated readme (#98) 26 March 2019, 23:08:11 UTC
ef32617 sourabh-nutonomy 26 March 2019, 23:06:41 UTC removed legacy map binarize (#100) 26 March 2019, 23:06:41 UTC
4561d30 Oscar Beijbom 26 March 2019, 14:57:20 UTC updated URL to WAD 26 March 2019, 14:57:20 UTC
e9f08cb Alex Lang 26 March 2019, 05:22:43 UTC preparation for pip package v1.0.0 (#96) 26 March 2019, 05:22:43 UTC
back to top