From ea370e306eec3a5191bd838f7f650658e0fbb115 Mon Sep 17 00:00:00 2001 From: Jordan Gong Date: Fri, 26 Aug 2022 17:30:37 +0800 Subject: Rewrite SimCLR-based PosRecon model with some tweaks - No inheritance, encapsulation and immutability, making code more readable - Remove mask token and encode visible patches only, inspired from MAE and MSN - Switch from batch-level randomization (shuffling and masking) to sample-level, and remove shuffle ratio for simplicity - Compute loss during forward --- posrecon/pos_embed.py | 97 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 97 insertions(+) create mode 100644 posrecon/pos_embed.py (limited to 'posrecon/pos_embed.py') diff --git a/posrecon/pos_embed.py b/posrecon/pos_embed.py new file mode 100644 index 0000000..ea3fe7d --- /dev/null +++ b/posrecon/pos_embed.py @@ -0,0 +1,97 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. + +# This source code is licensed under the license found in the +# LICENSE file in the root directory of this source tree. +# -------------------------------------------------------- +# Position embedding utils +# -------------------------------------------------------- + +import numpy as np + +import torch + + +# -------------------------------------------------------- +# 2D sine-cosine position embedding +# References: +# Transformer: https://github.com/tensorflow/models/blob/master/official/nlp/transformer/model_utils.py +# MoCo v3: https://github.com/facebookresearch/moco-v3 +# -------------------------------------------------------- +def get_2d_sincos_pos_embed(embed_dim, grid_size, cls_token=False): + """ + grid_size: int of the grid height and width + return: + pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/ or w/o cls_token) + """ + grid_h = np.arange(grid_size, dtype=np.float32) + grid_w = np.arange(grid_size, dtype=np.float32) + grid = np.meshgrid(grid_w, grid_h) # here w goes first + grid = np.stack(grid, axis=0) + + grid = grid.reshape([2, 1, grid_size, grid_size]) + pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid) + if cls_token: + pos_embed = np.concatenate([np.zeros([1, embed_dim]), pos_embed], axis=0) + return pos_embed + + +def get_2d_sincos_pos_embed_from_grid(embed_dim, grid): + assert embed_dim % 2 == 0 + + # use half of dimensions to encode grid_h + emb_h = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[0]) # (H*W, D/2) + emb_w = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[1]) # (H*W, D/2) + + emb = np.concatenate([emb_h, emb_w], axis=1) # (H*W, D) + return emb + + +def get_1d_sincos_pos_embed_from_grid(embed_dim, pos): + """ + embed_dim: output dimension for each position + pos: a list of positions to be encoded: size (M,) + out: (M, D) + """ + assert embed_dim % 2 == 0 + omega = np.arange(embed_dim // 2, dtype=np.float) + omega /= embed_dim / 2. + omega = 1. / 10000 ** omega # (D/2,) + + pos = pos.reshape(-1) # (M,) + out = np.einsum('m,d->md', pos, omega) # (M, D/2), outer product + + emb_sin = np.sin(out) # (M, D/2) + emb_cos = np.cos(out) # (M, D/2) + + emb = np.concatenate([emb_sin, emb_cos], axis=1) # (M, D) + return emb + + +# -------------------------------------------------------- +# Interpolate position embeddings for high-resolution +# References: +# DeiT: https://github.com/facebookresearch/deit +# -------------------------------------------------------- +def interpolate_pos_embed(model, checkpoint_model): + if 'pos_embed' in checkpoint_model: + pos_embed_checkpoint = checkpoint_model['pos_embed'] + embedding_size = pos_embed_checkpoint.shape[-1] + num_patches = model.patch_embed.num_patches + num_extra_tokens = model.pos_embed.shape[-2] - num_patches + # height (== width) for the checkpoint position embedding + orig_size = int((pos_embed_checkpoint.shape[-2] - num_extra_tokens) ** 0.5) + # height (== width) for the new position embedding + new_size = int(num_patches ** 0.5) + # class_token and dist_token are kept unchanged + if orig_size != new_size: + print("Position interpolate from %dx%d to %dx%d" % (orig_size, orig_size, new_size, new_size)) + extra_tokens = pos_embed_checkpoint[:, :num_extra_tokens] + # only the position tokens are interpolated + pos_tokens = pos_embed_checkpoint[:, num_extra_tokens:] + pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2) + pos_tokens = torch.nn.functional.interpolate( + pos_tokens, size=(new_size, new_size), mode='bicubic', align_corners=False) + pos_tokens = pos_tokens.permute(0, 2, 3, 1).flatten(1, 2) + new_pos_embed = torch.cat((extra_tokens, pos_tokens), dim=1) + checkpoint_model['pos_embed'] = new_pos_embed -- cgit v1.2.3