Hi,
Please I am new to ML and trying to add the WindowAttention to the self.conv_first layer and it’s showing the error “mat1 and mat2 shapes cannot be multiplied (288000x64 and 180x540)”. Please helpppp
Below is the WindowAttention class and OneChan class
class WindowAttention(nn.Module):
def init(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
super().__init__()
self.dim = dim
self.window_size = window_size # Wh, Ww
self.num_heads = num_heads
head_dim = dim // num_heads
self.scale = qk_scale or head_dim ** -0.5
# define a parameter table of relative position bias
self.relative_position_bias_table = nn.Parameter(
torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # 2*Wh-1 * 2*Ww-1, nH
# get pair-wise relative position index for each token inside the window
coords_h = torch.arange(self.window_size[0])
coords_w = torch.arange(self.window_size[1])
coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Ww
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2
relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0
relative_coords[:, :, 1] += self.window_size[1] - 1
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
self.register_buffer("relative_position_index", relative_position_index)
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop)
trunc_normal_(self.relative_position_bias_table, std=.02)
self.softmax = nn.Softmax(dim=-1)
def forward(self, x, mask=None):
B_, N, C = x.shape
qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
q = q * self.scale
attn = (q @ k.transpose(-2, -1))
relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) # Wh*Ww,Wh*Ww,nH
relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
attn = attn + relative_position_bias.unsqueeze(0)
if mask is not None:
nW = mask.shape[0]
attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
attn = attn.view(-1, self.num_heads, N, N)
attn = self.softmax(attn)
else:
attn = self.softmax(attn)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class OneChan(nn.Module):
def init(self, img_size=64, patch_size=1, in_chans=3,
embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
use_checkpoint=False, upscale=2, img_range=1., upsampler=‘’, resi_connection=‘1conv’,
**kwargs):
super(OneChan, self).init()
num_in_ch = in_chans
num_out_ch = in_chans
num_feat = 64
self.img_range = img_range
if in_chans == 3:
rgb_mean = (0.4488, 0.4371, 0.4040)
self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)
else:
self.mean = torch.zeros(1, 1, 1, 1)
self.upscale = upscale
self.upsampler = upsampler
self.window_size = window_size
#####################################################################################################
################################### 1, shallow feature extraction ###################################
**self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1)**
** self.multi_attn = WindowAttention(embed_dim, (window_size, window_size), num_heads[0], qkv_bias, qk_scale, attn_drop_rate, drop_rate)**
def forward(self, x):
H, W = x.shape[2:]
x = self.check_image_size(x)
self.mean = self.mean.type_as(x)
x = (x - self.mean) * self.img_range
if self.upsampler == 'nearest+conv':
# for real-world SR
**x_f = self.conv_first(x)**
**x = self.multi_attn(x_f)**
x = self.conv_after_body(self.forward_features(x)) + x
x = self.conv_before_upsample(x)
x = self.lrelu(self.conv_up1(torch.nn.functional.interpolate(x, scale_factor=2, mode='nearest')))
x = self.lrelu(self.conv_up2(torch.nn.functional.interpolate(x, scale_factor=2, mode='nearest')))
x = self.conv_last(self.lrelu(self.conv_hr(x)))