Sampling points process in Pointrend #965
Assignees
Labels
Comments
aravind-h-v
pushed a commit
to aravind-h-v/mmsegmentation
that referenced
this issue
Mar 27, 2023
* re-add RL model code * match model forward api * add register_to_config, pass training tests * fix tests, update forward outputs * remove unused code, some comments * add to docs * remove extra embedding code * unify time embedding * remove conv1d output sequential * remove sequential from conv1dblock * style and deleting duplicated code * clean files * remove unused variables * clean variables * add 1d resnet block structure for downsample * rename as unet1d * fix renaming * rename files * add get_block(...) api * unify args for model1d like model2d * minor cleaning * fix docs * improve 1d resnet blocks * fix tests, remove permuts * fix style * add output activation * rename flax blocks file * Add Value Function and corresponding example script to Diffuser implementation (open-mmlab#884) * valuefunction code * start example scripts * missing imports * bug fixes and placeholder example script * add value function scheduler * load value function from hub and get best actions in example * very close to working example * larger batch size for planning * more tests * merge unet1d changes * wandb for debugging, use newer models * success! * turns out we just need more diffusion steps * run on modal * merge and code cleanup * use same api for rl model * fix variance type * wrong normalization function * add tests * style * style and quality * edits based on comments * style and quality * remove unused var * hack unet1d into a value function * add pipeline * fix arg order * add pipeline to core library * community pipeline * fix couple shape bugs * style * Apply suggestions from code review Co-authored-by: Nathan Lambert <nathan@huggingface.co> * update post merge of scripts * add mdiblock / outblock architecture * Pipeline cleanup (open-mmlab#947) * valuefunction code * start example scripts * missing imports * bug fixes and placeholder example script * add value function scheduler * load value function from hub and get best actions in example * very close to working example * larger batch size for planning * more tests * merge unet1d changes * wandb for debugging, use newer models * success! * turns out we just need more diffusion steps * run on modal * merge and code cleanup * use same api for rl model * fix variance type * wrong normalization function * add tests * style * style and quality * edits based on comments * style and quality * remove unused var * hack unet1d into a value function * add pipeline * fix arg order * add pipeline to core library * community pipeline * fix couple shape bugs * style * Apply suggestions from code review * clean up comments * convert older script to using pipeline and add readme * rename scripts * style, update tests * delete unet rl model file * remove imports in src Co-authored-by: Nathan Lambert <nathan@huggingface.co> * Update src/diffusers/models/unet_1d_blocks.py * Update tests/test_models_unet.py * RL Cleanup v2 (open-mmlab#965) * valuefunction code * start example scripts * missing imports * bug fixes and placeholder example script * add value function scheduler * load value function from hub and get best actions in example * very close to working example * larger batch size for planning * more tests * merge unet1d changes * wandb for debugging, use newer models * success! * turns out we just need more diffusion steps * run on modal * merge and code cleanup * use same api for rl model * fix variance type * wrong normalization function * add tests * style * style and quality * edits based on comments * style and quality * remove unused var * hack unet1d into a value function * add pipeline * fix arg order * add pipeline to core library * community pipeline * fix couple shape bugs * style * Apply suggestions from code review * clean up comments * convert older script to using pipeline and add readme * rename scripts * style, update tests * delete unet rl model file * remove imports in src * add specific vf block and update tests * style * Update tests/test_models_unet.py Co-authored-by: Nathan Lambert <nathan@huggingface.co> * fix quality in tests * fix quality style, split test file * fix checks / tests * make timesteps closer to main * unify block API * unify forward api * delete lines in examples * style * examples style * all tests pass * make style * make dance_diff test pass * Refactoring RL PR (open-mmlab#1200) * init file changes * add import utils * finish cleaning files, imports * remove import flags * clean examples * fix imports, tests for merge * update readmes * hotfix for tests * quality * fix some tests * change defaults * more mps test fixes * unet1d defaults * do not default import experimental * defaults for tests * fix tests * fix-copies * fix * changes per Patrik's comments (open-mmlab#1285) * changes per Patrik's comments * update conversion script * fix renaming * skip more mps tests * last test fix * Update examples/rl/README.md Co-authored-by: Ben Glickenhaus <benglickenhaus@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The process of sampling points described in the paper is as follows:
In each iteration, PointRend upsamples its previously predicted segmentation using bilinear interpolation and then selects the N most uncertain points (e.g., those with probabilities closest to 0.5 for a binary mask) on this denser grid.
But I find that implementation in Detectron2 and MMSegmentation both add some extra factors.
In ''detectron2/projects/PointRend/point_rend/point_features.py, line 141&142":
point_coords[:, :, 0] = w_step / 2.0 + (point_indices % W).to(torch.float) * w_step
point_coords[:, :, 1] = h_step / 2.0 + (point_indices // W).to(torch.float) * h_step
In "mmsegmentation/mmseg/models/decode_heads/point_head.py, line347&349":
point_coords[:, :, 0] = w_step / 2.0 + (point_indices %
width).float() * w_step
point_coords[:, :, 1] = h_step / 2.0 + (point_indices //
width).float() * h_step
Why should point_coords add offset "w_setp/2.0" and "h_step / 2.0"?
The text was updated successfully, but these errors were encountered: