Akash Chowdhury
e9ef5dcea7
- Load Visual Chronometer model with device selection (auto/cpu/cuda) - Predict PhyFPS from video frames using sliding window analysis - Batch prediction with per-segment FPS breakdown - SDPA-optimized attention for better speed and memory efficiency - Auto-downloads model checkpoint from HuggingFace on first use - Progress bar and detailed terminal logging - Input tooltips and node descriptions
298 lines
11 KiB
Python
298 lines
11 KiB
Python
"""Base 2D encoder/decoder modules for the video autoencoder."""
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
|
|
def nonlinearity(x):
|
|
return x * torch.sigmoid(x)
|
|
|
|
|
|
def Normalize(in_channels, num_groups=32):
|
|
return torch.nn.GroupNorm(
|
|
num_groups=num_groups, num_channels=in_channels, eps=1e-6, affine=True
|
|
)
|
|
|
|
|
|
class AttnBlock(nn.Module):
|
|
def __init__(self, in_channels):
|
|
super().__init__()
|
|
self.in_channels = in_channels
|
|
self.norm = Normalize(in_channels)
|
|
self.q = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
|
|
self.k = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
|
|
self.v = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
|
|
self.proj_out = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
|
|
|
|
def forward(self, x):
|
|
h_ = x
|
|
h_ = self.norm(h_)
|
|
q = self.q(h_)
|
|
k = self.k(h_)
|
|
v = self.v(h_)
|
|
|
|
b, c, h, w = q.shape
|
|
# SDPA expects (batch, num_heads, seq_len, head_dim) — use 1 head with dim=c
|
|
q = q.reshape(b, 1, c, h * w).permute(0, 1, 3, 2) # (b, 1, h*w, c)
|
|
k = k.reshape(b, 1, c, h * w).permute(0, 1, 3, 2) # (b, 1, h*w, c)
|
|
v = v.reshape(b, 1, c, h * w).permute(0, 1, 3, 2) # (b, 1, h*w, c)
|
|
|
|
h_ = torch.nn.functional.scaled_dot_product_attention(q, k, v)
|
|
|
|
h_ = h_.permute(0, 1, 3, 2).reshape(b, c, h, w) # (b, c, h, w)
|
|
h_ = self.proj_out(h_)
|
|
return x + h_
|
|
|
|
|
|
def make_attn(in_channels, attn_type="vanilla"):
|
|
if attn_type == "vanilla":
|
|
return AttnBlock(in_channels)
|
|
elif attn_type == "none":
|
|
return nn.Identity(in_channels)
|
|
else:
|
|
raise ValueError(f"Unknown attn_type: {attn_type}")
|
|
|
|
|
|
class Downsample(nn.Module):
|
|
def __init__(self, in_channels, with_conv):
|
|
super().__init__()
|
|
self.with_conv = with_conv
|
|
if self.with_conv:
|
|
self.conv = torch.nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=2, padding=0)
|
|
|
|
def forward(self, x):
|
|
if self.with_conv:
|
|
pad = (0, 1, 0, 1)
|
|
x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
|
|
x = self.conv(x)
|
|
else:
|
|
x = torch.nn.functional.avg_pool2d(x, kernel_size=2, stride=2)
|
|
return x
|
|
|
|
|
|
class Upsample(nn.Module):
|
|
def __init__(self, in_channels, with_conv):
|
|
super().__init__()
|
|
self.with_conv = with_conv
|
|
if self.with_conv:
|
|
self.conv = torch.nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=1, padding=1)
|
|
|
|
def forward(self, x):
|
|
x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
|
|
if self.with_conv:
|
|
x = self.conv(x)
|
|
return x
|
|
|
|
|
|
class ResnetBlock(nn.Module):
|
|
def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False, dropout, temb_channels=512):
|
|
super().__init__()
|
|
self.in_channels = in_channels
|
|
out_channels = in_channels if out_channels is None else out_channels
|
|
self.out_channels = out_channels
|
|
self.use_conv_shortcut = conv_shortcut
|
|
|
|
self.norm1 = Normalize(in_channels)
|
|
self.conv1 = torch.nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1)
|
|
if temb_channels > 0:
|
|
self.temb_proj = torch.nn.Linear(temb_channels, out_channels)
|
|
self.norm2 = Normalize(out_channels)
|
|
self.dropout = torch.nn.Dropout(dropout)
|
|
self.conv2 = torch.nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1)
|
|
if self.in_channels != self.out_channels:
|
|
if self.use_conv_shortcut:
|
|
self.conv_shortcut = torch.nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1)
|
|
else:
|
|
self.nin_shortcut = torch.nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)
|
|
|
|
def forward(self, x, temb):
|
|
h = x
|
|
h = self.norm1(h)
|
|
h = nonlinearity(h)
|
|
h = self.conv1(h)
|
|
if temb is not None:
|
|
h = h + self.temb_proj(nonlinearity(temb))[:, :, None, None]
|
|
h = self.norm2(h)
|
|
h = nonlinearity(h)
|
|
h = self.dropout(h)
|
|
h = self.conv2(h)
|
|
if self.in_channels != self.out_channels:
|
|
if self.use_conv_shortcut:
|
|
x = self.conv_shortcut(x)
|
|
else:
|
|
x = self.nin_shortcut(x)
|
|
return x + h
|
|
|
|
|
|
class Encoder(nn.Module):
|
|
def __init__(
|
|
self,
|
|
*,
|
|
ch,
|
|
out_ch,
|
|
ch_mult=(1, 2, 4, 8),
|
|
num_res_blocks,
|
|
attn_resolutions,
|
|
dropout=0.0,
|
|
resamp_with_conv=True,
|
|
in_channels,
|
|
resolution,
|
|
z_channels,
|
|
double_z=True,
|
|
use_linear_attn=False,
|
|
attn_type="vanilla",
|
|
**ignore_kwargs,
|
|
):
|
|
super().__init__()
|
|
if use_linear_attn:
|
|
attn_type = "linear"
|
|
self.ch = ch
|
|
self.temb_ch = 0
|
|
self.num_resolutions = len(ch_mult)
|
|
self.num_res_blocks = num_res_blocks
|
|
self.resolution = resolution
|
|
self.in_channels = in_channels
|
|
|
|
self.conv_in = torch.nn.Conv2d(in_channels, self.ch, kernel_size=3, stride=1, padding=1)
|
|
|
|
curr_res = resolution
|
|
in_ch_mult = (1,) + tuple(ch_mult)
|
|
self.in_ch_mult = in_ch_mult
|
|
self.down = nn.ModuleList()
|
|
for i_level in range(self.num_resolutions):
|
|
block = nn.ModuleList()
|
|
attn = nn.ModuleList()
|
|
block_in = ch * in_ch_mult[i_level]
|
|
block_out = ch * ch_mult[i_level]
|
|
for i_block in range(self.num_res_blocks):
|
|
block.append(
|
|
ResnetBlock(in_channels=block_in, out_channels=block_out, temb_channels=self.temb_ch, dropout=dropout)
|
|
)
|
|
block_in = block_out
|
|
if curr_res in attn_resolutions:
|
|
attn.append(make_attn(block_in, attn_type=attn_type))
|
|
down = nn.Module()
|
|
down.block = block
|
|
down.attn = attn
|
|
if i_level != self.num_resolutions - 1:
|
|
down.downsample = Downsample(block_in, resamp_with_conv)
|
|
curr_res = curr_res // 2
|
|
self.down.append(down)
|
|
|
|
self.mid = nn.Module()
|
|
self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in, temb_channels=self.temb_ch, dropout=dropout)
|
|
self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
|
|
self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in, temb_channels=self.temb_ch, dropout=dropout)
|
|
|
|
self.norm_out = Normalize(block_in)
|
|
self.conv_out = torch.nn.Conv2d(
|
|
block_in, 2 * z_channels if double_z else z_channels, kernel_size=3, stride=1, padding=1
|
|
)
|
|
|
|
def forward(self, x):
|
|
temb = None
|
|
hs = [self.conv_in(x)]
|
|
for i_level in range(self.num_resolutions):
|
|
for i_block in range(self.num_res_blocks):
|
|
h = self.down[i_level].block[i_block](hs[-1], temb)
|
|
if len(self.down[i_level].attn) > 0:
|
|
h = self.down[i_level].attn[i_block](h)
|
|
hs.append(h)
|
|
if i_level != self.num_resolutions - 1:
|
|
hs.append(self.down[i_level].downsample(hs[-1]))
|
|
h = hs[-1]
|
|
h = self.mid.block_1(h, temb)
|
|
h = self.mid.attn_1(h)
|
|
h = self.mid.block_2(h, temb)
|
|
h = self.norm_out(h)
|
|
h = nonlinearity(h)
|
|
h = self.conv_out(h)
|
|
return h
|
|
|
|
|
|
class Decoder(nn.Module):
|
|
def __init__(
|
|
self,
|
|
*,
|
|
ch,
|
|
out_ch,
|
|
ch_mult=(1, 2, 4, 8),
|
|
num_res_blocks,
|
|
attn_resolutions,
|
|
dropout=0.0,
|
|
resamp_with_conv=True,
|
|
in_channels,
|
|
resolution,
|
|
z_channels,
|
|
give_pre_end=False,
|
|
tanh_out=False,
|
|
use_linear_attn=False,
|
|
attn_type="vanilla",
|
|
**ignore_kwargs,
|
|
):
|
|
super().__init__()
|
|
if use_linear_attn:
|
|
attn_type = "linear"
|
|
self.ch = ch
|
|
self.temb_ch = 0
|
|
self.num_resolutions = len(ch_mult)
|
|
self.num_res_blocks = num_res_blocks
|
|
self.resolution = resolution
|
|
self.in_channels = in_channels
|
|
self.give_pre_end = give_pre_end
|
|
self.tanh_out = tanh_out
|
|
|
|
block_in = ch * ch_mult[self.num_resolutions - 1]
|
|
curr_res = resolution // 2 ** (self.num_resolutions - 1)
|
|
|
|
self.conv_in = torch.nn.Conv2d(z_channels, block_in, kernel_size=3, stride=1, padding=1)
|
|
self.mid = nn.Module()
|
|
self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in, temb_channels=self.temb_ch, dropout=dropout)
|
|
self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
|
|
self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in, temb_channels=self.temb_ch, dropout=dropout)
|
|
|
|
self.up = nn.ModuleList()
|
|
for i_level in reversed(range(self.num_resolutions)):
|
|
block = nn.ModuleList()
|
|
attn = nn.ModuleList()
|
|
block_out = ch * ch_mult[i_level]
|
|
for i_block in range(self.num_res_blocks + 1):
|
|
block.append(
|
|
ResnetBlock(in_channels=block_in, out_channels=block_out, temb_channels=self.temb_ch, dropout=dropout)
|
|
)
|
|
block_in = block_out
|
|
if curr_res in attn_resolutions:
|
|
attn.append(make_attn(block_in, attn_type=attn_type))
|
|
up = nn.Module()
|
|
up.block = block
|
|
up.attn = attn
|
|
if i_level != 0:
|
|
up.upsample = Upsample(block_in, resamp_with_conv)
|
|
curr_res = curr_res * 2
|
|
self.up.insert(0, up)
|
|
|
|
self.norm_out = Normalize(block_in)
|
|
self.conv_out = torch.nn.Conv2d(block_in, out_ch, kernel_size=3, stride=1, padding=1)
|
|
|
|
def forward(self, z):
|
|
temb = None
|
|
h = self.conv_in(z)
|
|
h = self.mid.block_1(h, temb)
|
|
h = self.mid.attn_1(h)
|
|
h = self.mid.block_2(h, temb)
|
|
for i_level in reversed(range(self.num_resolutions)):
|
|
for i_block in range(self.num_res_blocks + 1):
|
|
h = self.up[i_level].block[i_block](h, temb)
|
|
if len(self.up[i_level].attn) > 0:
|
|
h = self.up[i_level].attn[i_block](h)
|
|
if i_level != 0:
|
|
h = self.up[i_level].upsample(h)
|
|
if self.give_pre_end:
|
|
return h
|
|
h = self.norm_out(h)
|
|
h = nonlinearity(h)
|
|
h = self.conv_out(h)
|
|
if self.tanh_out:
|
|
h = torch.tanh(h)
|
|
return h
|