CLIP视觉编码器

最新推荐文章于 2024-07-26 14:22:52 发布
Bella_wanna_Better
最新推荐文章于 2024-07-26 14:22:52 发布
阅读量1k
点赞数
分类专栏： Pytorch源码学习文章标签：深度学习 python Powered by 金山文档
本文链接：https://blog.csdn.net/bairw_Bella/article/details/128784456
版权
Pytorch源码学习专栏收录该内容
10 篇文章 1 订阅
订阅专栏
VisionTransformer(
  (conv1): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16), bias=False)
  (ln_pre): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
  (transformer): Transformer(
    (resblocks): Sequential(
      (0): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (1): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (2): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (3): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (4): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (5): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (6): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (7): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (8): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (9): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (10): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (11): ResidualAttentionBlock(
        (attn): MultiheadAttention(
          (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
        )
        (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (mlp): Sequential(
          (c_fc): Linear(in_features=768, out_features=3072, bias=True)
          (gelu): QuickGELU()
          (c_proj): Linear(in_features=3072, out_features=768, bias=True)
        )
        (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
    )
  )
  (ln_post): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
)