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

Merge branch '2025_02_20_add_dexvla' of https://github.com/JayceWen/lerobot into 2025_02_20_add_dexvla

This commit is contained in:
wk 2025-03-11 14:31:17 +08:00
parent e2a41716a4 bf954dc715
commit a13072f72f
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/policies/dexvla/policy_heads/modeling_scaledp.py
View File

@ -5,7 +5,6 @@ import math
from typing import Tuple from typing import Tuple
import numpy as np import numpy as np
import torch import torch
import torch.nn as nn import torch.nn as nn
import torch.nn.functional as func import torch.nn.functional as func
@ -158,8 +157,10 @@ class ScaleDPBlock(nn.Module):
self.attn = Attention(hidden_size, num_heads=num_heads, qkv_bias=True, **block_kwargs) self.attn = Attention(hidden_size, num_heads=num_heads, qkv_bias=True, **block_kwargs)
self.norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6) self.norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
mlp_hidden_dim = int(hidden_size * mlp_ratio) mlp_hidden_dim = int(hidden_size * mlp_ratio)
def approx_gelu(): def approx_gelu():
return nn.GELU(approximate="tanh") return nn.GELU(approximate="tanh")
self.mlp = Mlp(in_features=hidden_size, hidden_features=mlp_hidden_dim, act_layer=approx_gelu, drop=0) self.mlp = Mlp(in_features=hidden_size, hidden_features=mlp_hidden_dim, act_layer=approx_gelu, drop=0)
self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True)) self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True))