Architectures / Computer Vision

👁️ ViT-B/16

Vision Transformer — patch embedding stem + 1 encoder block (768D, 12 heads)

Every number on this page is computed from the graph by the same functions the app runs, not written by hand.

When to pick it

Structure

13 layers. Output shapes are propagated from the input shape, batch dimension excluded.

What the verifier says

The same 41 structural checks that run on every edit in the app, on this graph.

The PyTorch it exports

Generated from the graph above. First 46 lines; the app exports the whole file, plus the training loop, the data contract and a deploy bundle.

# Architecture designed with Neurarch: https://neurarch.com
# PyTorch: compatible with Python 3.8+ and torch>=1.12
# Colab: pip install torch torchvision  (usually pre-installed)

import torch
import torch.nn as nn
import torch.nn.functional as F
from typing import Tuple

class ViT_B16(nn.Module):
    def __init__(self):
        super().__init__()

        self.patchEmbed_1 = nn.Conv2d(3, 768, kernel_size=16, stride=16)  # Patch embedding (ViT-style)
        self.dropout_1 = nn.Dropout(p=0.5)
        self.layerNorm_1 = nn.LayerNorm(768)
        self.multiHeadAttention_1 = nn.MultiheadAttention(embed_dim=768, num_heads=12, batch_first=True)
        self.layerNorm_2 = nn.LayerNorm(768)
        self.feedForward_1 = nn.Sequential(
            nn.Linear(768, 3072),
            nn.ReLU(),
            nn.Linear(3072, 768)
        )
        self.layerNorm_3 = nn.LayerNorm(768)
        self.linear_1 = nn.Linear(768, 1000)

    def forward(self, x):
        # image shape: [3,224,224]
        patch_embed_mbed_1 = self.patchEmbed_1(x).flatten(2).transpose(1, 2)  # [B, num_patches, embed_dim]
        # positionalEncoding: add positional encoding externally (e.g. sinusoidal or learned PE)
        dropout_pout_1 = self.dropout_1(patch_embed_mbed_1)
        layer_norm_Norm_1 = self.layerNorm_1(dropout_pout_1)
        multi_head_attention_tion_1 = self.multiHeadAttention_1(layer_norm_Norm_1, layer_norm_Norm_1, layer_norm_Norm_1)[0]
        add_add_1 = multi_head_attention_tion_1 + dropout_pout_1
        layer_norm_Norm_2 = self.layerNorm_2(add_add_1)
        feed_forward_ward_1 = self.feedForward_1(layer_norm_Norm_2)
        add_add_2 = feed_forward_ward_1 + add_add_1
        layer_norm_Norm_3 = self.layerNorm_3(add_add_2)
        linear_near_1 = self.linear_1(layer_norm_Norm_3)
        # Output
        return linear_near_1


if __name__ == '__main__':
    model = ViT_B16()
    model.eval()

For agents

Also in Computer Vision