wangzixiang
/
lerobot
mirror of https://github.com/huggingface/lerobot.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

clarifying math

This commit is contained in:
Alexander Soare 2024-04-03 09:47:38 +01:00
parent e9eb262293
commit c50a62dd6d
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lerobot/common/datasets/abstract.py
View File

@ -187,7 +187,8 @@ class AbstractDataset(TensorDictReplayBuffer):
# Hint: to update the mean we need x̄ₙ = (Nₙ₋₁x̄ₙ₋₁ + Bₙxₙ) / Nₙ, where the subscript represents # Hint: to update the mean we need x̄ₙ = (Nₙ₋₁x̄ₙ₋₁ + Bₙxₙ) / Nₙ, where the subscript represents
# the update step, N is the running item count, B is this batch size, x̄ is the running mean, # the update step, N is the running item count, B is this batch size, x̄ is the running mean,
# and x is the current batch mean. Some rearrangement is then required to avoid risking # and x is the current batch mean. Some rearrangement is then required to avoid risking
# numerical overflow. Another hint: Nₙ₋₁ = Nₙ - Bₙ. # numerical overflow. Another hint: Nₙ₋₁ = Nₙ - Bₙ. Rearrangement yields
# x̄ₙ = x̄ₙ₋₁ + Bₙ * (xₙ - x̄ₙ₋₁) / Nₙ
mean[key] = mean[key] + this_batch_size * (batch_mean - mean[key]) / running_item_count mean[key] = mean[key] + this_batch_size * (batch_mean - mean[key]) / running_item_count
max[key] = torch.maximum(max[key], einops.reduce(batch[key], pattern, "max")) max[key] = torch.maximum(max[key], einops.reduce(batch[key], pattern, "max"))
min[key] = torch.minimum(min[key], einops.reduce(batch[key], pattern, "min")) min[key] = torch.minimum(min[key], einops.reduce(batch[key], pattern, "min"))