File size: 5,527 Bytes
7f43945
 
 
 
9ff21bd
7f43945
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ff21bd
7f43945
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ff21bd
7f43945
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
import torch
import torch.nn as nn

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

class MoCo(nn.Module):
    """
    Build a MoCo model with: a query encoder, a key encoder, and a queue
    https://arxiv.org/abs/1911.05722
    """
    def __init__(self, base_encoder, dim=256, K=3*256, m=0.999, T=0.07, mlp=False):
        """
        dim: feature dimension (default: 128)
        K: queue size; number of negative keys (default: 65536)
        m: moco momentum of updating key encoder (default: 0.999)
        T: softmax temperature (default: 0.07)
        """
        super(MoCo, self).__init__()

        self.K = K
        self.m = m
        self.T = T

        # create the encoders
        # num_classes is the output fc dimension
        self.encoder_q = base_encoder()
        self.encoder_k = base_encoder()

        for param_q, param_k in zip(self.encoder_q.parameters(), self.encoder_k.parameters()):
            param_k.data.copy_(param_q.data)  # initialize
            param_k.requires_grad = False  # not update by gradient

        # create the queue
        self.register_buffer("queue", torch.randn(dim, K))
        self.queue = nn.functional.normalize(self.queue, dim=0)

        self.register_buffer("queue_ptr", torch.zeros(1, dtype=torch.long))

    @torch.no_grad()
    def _momentum_update_key_encoder(self):
        """
        Momentum update of the key encoder
        """
        for param_q, param_k in zip(self.encoder_q.parameters(), self.encoder_k.parameters()):
            param_k.data = param_k.data * self.m + param_q.data * (1. - self.m)

    @torch.no_grad()
    def _dequeue_and_enqueue(self, keys):
        # gather keys before updating queue
        # keys = concat_all_gather(keys)
        batch_size = keys.shape[0]

        ptr = int(self.queue_ptr)
        assert self.K % batch_size == 0  # for simplicity

        # replace the keys at ptr (dequeue and enqueue)
        self.queue[:, ptr:ptr + batch_size] = keys.transpose(0, 1)
        ptr = (ptr + batch_size) % self.K  # move pointer

        self.queue_ptr[0] = ptr

    @torch.no_grad()
    def _batch_shuffle_ddp(self, x):
        """
        Batch shuffle, for making use of BatchNorm.
        *** Only support DistributedDataParallel (DDP) model. ***
        """
        # gather from all gpus
        batch_size_this = x.shape[0]
        x_gather = concat_all_gather(x)
        batch_size_all = x_gather.shape[0]

        num_gpus = batch_size_all // batch_size_this

        # random shuffle index
        idx_shuffle = torch.randperm(batch_size_all).to(device)

        # broadcast to all gpus
        torch.distributed.broadcast(idx_shuffle, src=0)

        # index for restoring
        idx_unshuffle = torch.argsort(idx_shuffle)

        # shuffled index for this gpu
        gpu_idx = torch.distributed.get_rank()
        idx_this = idx_shuffle.view(num_gpus, -1)[gpu_idx]

        return x_gather[idx_this], idx_unshuffle

    @torch.no_grad()
    def _batch_unshuffle_ddp(self, x, idx_unshuffle):
        """
        Undo batch shuffle.
        *** Only support DistributedDataParallel (DDP) model. ***
        """
        # gather from all gpus
        batch_size_this = x.shape[0]
        x_gather = concat_all_gather(x)
        batch_size_all = x_gather.shape[0]

        num_gpus = batch_size_all // batch_size_this

        # restored index for this gpu
        gpu_idx = torch.distributed.get_rank()
        idx_this = idx_unshuffle.view(num_gpus, -1)[gpu_idx]

        return x_gather[idx_this]

    def forward(self, im_q, im_k):
        """
        Input:
            im_q: a batch of query images
            im_k: a batch of key images
        Output:
            logits, targets
        """
        if self.training:
            # compute query features
            embedding, q, inter = self.encoder_q(im_q)  # queries: NxC
            q = nn.functional.normalize(q, dim=1)

            # compute key features
            with torch.no_grad():  # no gradient to keys
                self._momentum_update_key_encoder()  # update the key encoder

                _, k, _ = self.encoder_k(im_k)  # keys: NxC
                k = nn.functional.normalize(k, dim=1)

            # compute logits
            # Einstein sum is more intuitive
            # positive logits: Nx1
            l_pos = torch.einsum('nc,nc->n', [q, k]).unsqueeze(-1)
            # negative logits: NxK
            l_neg = torch.einsum('nc,ck->nk', [q, self.queue.clone().detach()])

            # logits: Nx(1+K)
            logits = torch.cat([l_pos, l_neg], dim=1)

            # apply temperature
            logits /= self.T

            # labels: positive key indicators
            labels = torch.zeros(logits.shape[0], dtype=torch.long).to(device)
            # dequeue and enqueue
            self._dequeue_and_enqueue(k)

            return embedding, logits, labels, inter
        else:
            embedding, _, inter = self.encoder_q(im_q)

            return embedding, inter


# utils
@torch.no_grad()
def concat_all_gather(tensor):
    """
    Performs all_gather operation on the provided tensors.
    *** Warning ***: torch.distributed.all_gather has no gradient.
    """
    tensors_gather = [torch.ones_like(tensor)
        for _ in range(torch.distributed.get_world_size())]
    torch.distributed.all_gather(tensors_gather, tensor, async_op=False)

    output = torch.cat(tensors_gather, dim=0)
    return output