new project from v0.0.1

scepter/modules/model/backbone/utils/__init__.py

@@ -0,0 +1,2 @@
+# -*- coding: utf-8 -*-
+# Copyright (c) Alibaba, Inc. and its affiliates.

scepter/modules/model/backbone/utils/transformer.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+# Copyright (c) Alibaba, Inc. and its affiliates.
+from collections import OrderedDict
+
+import torch
+from torch import nn
+
+
+class LayerNorm(nn.LayerNorm):
+    """Subclass torch's LayerNorm to handle fp16."""
+    def forward(self, x: torch.Tensor):
+        orig_type = x.dtype
+        ret = super().forward(x.type(torch.float32))
+        return ret.type(orig_type)
+
+
+class QuickGELU(nn.Module):
+    def forward(self, x: torch.Tensor):
+        return x * torch.sigmoid(1.702 * x)
+
+
+class ResidualAttentionBlock(nn.Module):
+    def __init__(self,
+                 d_model: int,
+                 n_head: int,
+                 attn_mask: torch.Tensor = None):
+        super().__init__()
+
+        self.attn = nn.MultiheadAttention(d_model, n_head)
+        self.ln_1 = LayerNorm(d_model)
+        self.mlp = nn.Sequential(
+            OrderedDict([('c_fc', nn.Linear(d_model, d_model * 4)),
+                         ('gelu', QuickGELU()),
+                         ('c_proj', nn.Linear(d_model * 4, d_model))]))
+        self.ln_2 = LayerNorm(d_model)
+        self.attn_mask = attn_mask
+
+    def attention(self, x: torch.Tensor):
+        self.attn_mask = self.attn_mask.to(
+            dtype=x.dtype,
+            device=x.device) if self.attn_mask is not None else None
+        return self.attn(x, x, x, need_weights=False,
+                         attn_mask=self.attn_mask)[0]
+
+    def forward(self, x: torch.Tensor):
+        x = x + self.attention(self.ln_1(x))
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+
+class Transformer(nn.Module):
+    def __init__(self,
+                 width: int,
+                 layers: int,
+                 heads: int,
+                 attn_mask: torch.Tensor = None):
+        super().__init__()
+        self.width = width
+        self.layers = layers
+        self.resblocks = nn.Sequential(*[
+            ResidualAttentionBlock(width, heads, attn_mask)
+            for _ in range(layers)
+        ])
+
+    def forward(self, x: torch.Tensor):
+        return self.resblocks(x)