levit.py [205:238]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.dh, dim, bn_weight_init=0, resolution=resolution))

        points = list(itertools.product(range(resolution), range(resolution)))
        N = len(points)
        attention_offsets = {}
        idxs = []
        for p1 in points:
            for p2 in points:
                offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1]))
                if offset not in attention_offsets:
                    attention_offsets[offset] = len(attention_offsets)
                idxs.append(attention_offsets[offset])
        self.attention_biases = torch.nn.Parameter(
            torch.zeros(num_heads, len(attention_offsets)))
        self.register_buffer('attention_bias_idxs',
                             torch.LongTensor(idxs).view(N, N))

        global FLOPS_COUNTER
        #queries * keys
        FLOPS_COUNTER += num_heads * (resolution**4) * key_dim
        # softmax
        FLOPS_COUNTER += num_heads * (resolution**4)
        #attention * v
        FLOPS_COUNTER += num_heads * self.d * (resolution**4)

    @torch.no_grad()
    def train(self, mode=True):
        super().train(mode)
        if mode and hasattr(self, 'ab'):
            del self.ab
        else:
            self.ab = self.attention_biases[:, self.attention_bias_idxs]

    def forward(self, x):  # x (B,N,C)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



levit_c.py [174:207]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.dh, dim, bn_weight_init=0, resolution=resolution))

        points = list(itertools.product(range(resolution), range(resolution)))
        N = len(points)
        attention_offsets = {}
        idxs = []
        for p1 in points:
            for p2 in points:
                offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1]))
                if offset not in attention_offsets:
                    attention_offsets[offset] = len(attention_offsets)
                idxs.append(attention_offsets[offset])
        self.attention_biases = torch.nn.Parameter(
            torch.zeros(num_heads, len(attention_offsets)))
        self.register_buffer('attention_bias_idxs',
                             torch.LongTensor(idxs).view(N, N))

        global FLOPS_COUNTER
        #queries * keys
        FLOPS_COUNTER += num_heads * (resolution**4) * key_dim
        # softmax
        FLOPS_COUNTER += num_heads * (resolution**4)
        #attention * v
        FLOPS_COUNTER += num_heads * self.d * (resolution**4)

    @torch.no_grad()
    def train(self, mode=True):
        super().train(mode)
        if mode and hasattr(self, 'ab'):
            del self.ab
        else:
            self.ab = self.attention_biases[:, self.attention_bias_idxs]

    def forward(self, x):  # x (B,C,H,W)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -