wip: depth_anything_v2 initial implementation

invokeai/backend/image_util/depth_anything/__init__.py

@@ -1,66 +1,46 @@
 from pathlib import Path
 from typing import Literal
 
-import cv2
 import numpy as np
 import torch
-import torch.nn.functional as F
 from einops import repeat
 from PIL import Image
-from torchvision.transforms import Compose
 
 from invokeai.app.services.config.config_default import get_config
-from invokeai.backend.image_util.depth_anything.model.dpt import DPT_DINOv2
+from invokeai.backend.image_util.depth_anything.v2.dpt import DepthAnythingV2
-from invokeai.backend.image_util.depth_anything.utilities.util import NormalizeImage, PrepareForNet, Resize
 from invokeai.backend.util.logging import InvokeAILogger
 
 config = get_config()
 logger = InvokeAILogger.get_logger(config=config)
 
 DEPTH_ANYTHING_MODELS = {
-    "large": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitl14.pth?download=true",
+    "large": "https://huggingface.co/depth-anything/Depth-Anything-V2-Large/resolve/main/depth_anything_v2_vitl.pth?download=true",
-    "base": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitb14.pth?download=true",
+    "base": "https://huggingface.co/depth-anything/Depth-Anything-V2-Base/resolve/main/depth_anything_v2_vitb.pth?download=true",
-    "small": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vits14.pth?download=true",
+    "small": "https://huggingface.co/depth-anything/Depth-Anything-V2-Small/resolve/main/depth_anything_v2_vits.pth?download=true",
 }
 
 
-transform = Compose(
-    [
-        Resize(
-            width=518,
-            height=518,
-            resize_target=False,
-            keep_aspect_ratio=True,
-            ensure_multiple_of=14,
-            resize_method="lower_bound",
-            image_interpolation_method=cv2.INTER_CUBIC,
-        ),
-        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-        PrepareForNet(),
-    ]
-)
-
-
 class DepthAnythingDetector:
-    def __init__(self, model: DPT_DINOv2, device: torch.device) -> None:
+    def __init__(self, model: DepthAnythingV2, device: torch.device) -> None:
         self.model = model
         self.device = device
 
     @staticmethod
     def load_model(
-        model_path: Path, device: torch.device, model_size: Literal["large", "base", "small"] = "small"
+        model_path: Path, device: torch.device, model_size: Literal["large", "base", "small", "giant"] = "small"
-    ) -> DPT_DINOv2:
+    ) -> DepthAnythingV2:
         match model_size:
             case "small":
-                model = DPT_DINOv2(encoder="vits", features=64, out_channels=[48, 96, 192, 384])
+                model = DepthAnythingV2(encoder="vits", features=64, out_channels=[48, 96, 192, 384])
             case "base":
-                model = DPT_DINOv2(encoder="vitb", features=128, out_channels=[96, 192, 384, 768])
+                model = DepthAnythingV2(encoder="vitb", features=128, out_channels=[96, 192, 384, 768])
             case "large":
-                model = DPT_DINOv2(encoder="vitl", features=256, out_channels=[256, 512, 1024, 1024])
+                model = DepthAnythingV2(encoder="vitl", features=256, out_channels=[256, 512, 1024, 1024])
+            case "giant":
+                model = DepthAnythingV2(encoder="vitg", features=384, out_channels=[1536, 1536, 1536, 1536])
 
         model.load_state_dict(torch.load(model_path.as_posix(), map_location="cpu"))
         model.eval()
-
         model.to(device)
         return model
 
@@ -70,18 +50,13 @@ class DepthAnythingDetector:
             return image
 
         np_image = np.array(image, dtype=np.uint8)
-        np_image = np_image[:, :, ::-1] / 255.0
-
         image_height, image_width = np_image.shape[:2]
-        np_image = transform({"image": np_image})["image"]
-        tensor_image = torch.from_numpy(np_image).unsqueeze(0).to(self.device)
 
         with torch.no_grad():
-            depth = self.model(tensor_image)
+            depth = self.model.infer_image(np_image)
-            depth = F.interpolate(depth[None], (image_height, image_width), mode="bilinear", align_corners=False)[0, 0]
             depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
 
-        depth_map = repeat(depth, "h w -> h w 3").cpu().numpy().astype(np.uint8)
+        depth_map = repeat(depth, "h w -> h w 3").astype(np.uint8)
         depth_map = Image.fromarray(depth_map)
 
         new_height = int(image_height * (resolution / image_width))

invokeai/backend/image_util/depth_anything/v2/dinov2.py

@@ -0,0 +1,411 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+#
+# This source code is licensed under the Apache License, Version 2.0
+# found in the LICENSE file in the root directory of this source tree.
+
+# References:
+#   https://github.com/facebookresearch/dino/blob/main/vision_transformer.py
+#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/models/vision_transformer.py
+
+import logging
+import math
+from functools import partial
+from typing import Callable, Sequence, Tuple, Union
+
+import torch
+import torch.nn as nn
+import torch.utils.checkpoint
+from torch.nn.init import trunc_normal_
+
+from .dinov2_layers import MemEffAttention, Mlp
+from .dinov2_layers import NestedTensorBlock as Block
+from .dinov2_layers import PatchEmbed, SwiGLUFFNFused
+
+logger = logging.getLogger("dinov2")
+
+
+def named_apply(fn: Callable, module: nn.Module, name="", depth_first=True, include_root=False) -> nn.Module:
+    if not depth_first and include_root:
+        fn(module=module, name=name)
+    for child_name, child_module in module.named_children():
+        child_name = ".".join((name, child_name)) if name else child_name
+        named_apply(fn=fn, module=child_module, name=child_name, depth_first=depth_first, include_root=True)
+    if depth_first and include_root:
+        fn(module=module, name=name)
+    return module
+
+
+class BlockChunk(nn.ModuleList):
+    def forward(self, x):
+        for b in self:
+            x = b(x)
+        return x
+
+
+class DinoVisionTransformer(nn.Module):
+    def __init__(
+        self,
+        img_size=224,
+        patch_size=16,
+        in_chans=3,
+        embed_dim=768,
+        depth=12,
+        num_heads=12,
+        mlp_ratio=4.0,
+        qkv_bias=True,
+        ffn_bias=True,
+        proj_bias=True,
+        drop_path_rate=0.0,
+        drop_path_uniform=False,
+        init_values=None,  # for layerscale: None or 0 => no layerscale
+        embed_layer=PatchEmbed,
+        act_layer=nn.GELU,
+        block_fn=Block,
+        ffn_layer="mlp",
+        block_chunks=1,
+        num_register_tokens=0,
+        interpolate_antialias=False,
+        interpolate_offset=0.1,
+    ):
+        """
+        Args:
+            img_size (int, tuple): input image size
+            patch_size (int, tuple): patch size
+            in_chans (int): number of input channels
+            embed_dim (int): embedding dimension
+            depth (int): depth of transformer
+            num_heads (int): number of attention heads
+            mlp_ratio (int): ratio of mlp hidden dim to embedding dim
+            qkv_bias (bool): enable bias for qkv if True
+            proj_bias (bool): enable bias for proj in attn if True
+            ffn_bias (bool): enable bias for ffn if True
+            drop_path_rate (float): stochastic depth rate
+            drop_path_uniform (bool): apply uniform drop rate across blocks
+            weight_init (str): weight init scheme
+            init_values (float): layer-scale init values
+            embed_layer (nn.Module): patch embedding layer
+            act_layer (nn.Module): MLP activation layer
+            block_fn (nn.Module): transformer block class
+            ffn_layer (str): "mlp", "swiglu", "swiglufused" or "identity"
+            block_chunks: (int) split block sequence into block_chunks units for FSDP wrap
+            num_register_tokens: (int) number of extra cls tokens (so-called "registers")
+            interpolate_antialias: (str) flag to apply anti-aliasing when interpolating positional embeddings
+            interpolate_offset: (float) work-around offset to apply when interpolating positional embeddings
+        """
+        super().__init__()
+        norm_layer = partial(nn.LayerNorm, eps=1e-6)
+
+        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
+        self.num_tokens = 1
+        self.n_blocks = depth
+        self.num_heads = num_heads
+        self.patch_size = patch_size
+        self.num_register_tokens = num_register_tokens
+        self.interpolate_antialias = interpolate_antialias
+        self.interpolate_offset = interpolate_offset
+
+        self.patch_embed = embed_layer(img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim)
+        num_patches = self.patch_embed.num_patches
+
+        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
+        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
+        assert num_register_tokens >= 0
+        self.register_tokens = (
+            nn.Parameter(torch.zeros(1, num_register_tokens, embed_dim)) if num_register_tokens else None
+        )
+
+        if drop_path_uniform is True:
+            dpr = [drop_path_rate] * depth
+        else:
+            dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]  # stochastic depth decay rule
+
+        if ffn_layer == "mlp":
+            logger.info("using MLP layer as FFN")
+            ffn_layer = Mlp
+        elif ffn_layer == "swiglufused" or ffn_layer == "swiglu":
+            logger.info("using SwiGLU layer as FFN")
+            ffn_layer = SwiGLUFFNFused
+        elif ffn_layer == "identity":
+            logger.info("using Identity layer as FFN")
+
+            def f(*args, **kwargs):
+                return nn.Identity()
+
+            ffn_layer = f
+        else:
+            raise NotImplementedError
+
+        blocks_list = [
+            block_fn(
+                dim=embed_dim,
+                num_heads=num_heads,
+                mlp_ratio=mlp_ratio,
+                qkv_bias=qkv_bias,
+                proj_bias=proj_bias,
+                ffn_bias=ffn_bias,
+                drop_path=dpr[i],
+                norm_layer=norm_layer,
+                act_layer=act_layer,
+                ffn_layer=ffn_layer,
+                init_values=init_values,
+            )
+            for i in range(depth)
+        ]
+        if block_chunks > 0:
+            self.chunked_blocks = True
+            chunked_blocks = []
+            chunksize = depth // block_chunks
+            for i in range(0, depth, chunksize):
+                # this is to keep the block index consistent if we chunk the block list
+                chunked_blocks.append([nn.Identity()] * i + blocks_list[i : i + chunksize])
+            self.blocks = nn.ModuleList([BlockChunk(p) for p in chunked_blocks])
+        else:
+            self.chunked_blocks = False
+            self.blocks = nn.ModuleList(blocks_list)
+
+        self.norm = norm_layer(embed_dim)
+        self.head = nn.Identity()
+
+        self.mask_token = nn.Parameter(torch.zeros(1, embed_dim))
+
+        self.init_weights()
+
+    def init_weights(self):
+        trunc_normal_(self.pos_embed, std=0.02)
+        nn.init.normal_(self.cls_token, std=1e-6)
+        if self.register_tokens is not None:
+            nn.init.normal_(self.register_tokens, std=1e-6)
+        named_apply(init_weights_vit_timm, self)
+
+    def interpolate_pos_encoding(self, x, w, h):
+        previous_dtype = x.dtype
+        npatch = x.shape[1] - 1
+        N = self.pos_embed.shape[1] - 1
+        if npatch == N and w == h:
+            return self.pos_embed
+        pos_embed = self.pos_embed.float()
+        class_pos_embed = pos_embed[:, 0]
+        patch_pos_embed = pos_embed[:, 1:]
+        dim = x.shape[-1]
+        w0 = w // self.patch_size
+        h0 = h // self.patch_size
+        # we add a small number to avoid floating point error in the interpolation
+        # see discussion at https://github.com/facebookresearch/dino/issues/8
+        # DINOv2 with register modify the interpolate_offset from 0.1 to 0.0
+        w0, h0 = w0 + self.interpolate_offset, h0 + self.interpolate_offset
+        # w0, h0 = w0 + 0.1, h0 + 0.1
+
+        sqrt_N = math.sqrt(N)
+        sx, sy = float(w0) / sqrt_N, float(h0) / sqrt_N
+        patch_pos_embed = nn.functional.interpolate(
+            patch_pos_embed.reshape(1, int(sqrt_N), int(sqrt_N), dim).permute(0, 3, 1, 2),
+            scale_factor=(sx, sy),
+            # (int(w0), int(h0)), # to solve the upsampling shape issue
+            mode="bicubic",
+            antialias=self.interpolate_antialias,
+        )
+
+        assert int(w0) == patch_pos_embed.shape[-2]
+        assert int(h0) == patch_pos_embed.shape[-1]
+        patch_pos_embed = patch_pos_embed.permute(0, 2, 3, 1).view(1, -1, dim)
+        return torch.cat((class_pos_embed.unsqueeze(0), patch_pos_embed), dim=1).to(previous_dtype)
+
+    def prepare_tokens_with_masks(self, x, masks=None):
+        B, nc, w, h = x.shape
+        x = self.patch_embed(x)
+        if masks is not None:
+            x = torch.where(masks.unsqueeze(-1), self.mask_token.to(x.dtype).unsqueeze(0), x)
+
+        x = torch.cat((self.cls_token.expand(x.shape[0], -1, -1), x), dim=1)
+        x = x + self.interpolate_pos_encoding(x, w, h)
+
+        if self.register_tokens is not None:
+            x = torch.cat(
+                (
+                    x[:, :1],
+                    self.register_tokens.expand(x.shape[0], -1, -1),
+                    x[:, 1:],
+                ),
+                dim=1,
+            )
+
+        return x
+
+    def forward_features_list(self, x_list, masks_list):
+        x = [self.prepare_tokens_with_masks(x, masks) for x, masks in zip(x_list, masks_list)]
+        for blk in self.blocks:
+            x = blk(x)
+
+        all_x = x
+        output = []
+        for x, masks in zip(all_x, masks_list):
+            x_norm = self.norm(x)
+            output.append(
+                {
+                    "x_norm_clstoken": x_norm[:, 0],
+                    "x_norm_regtokens": x_norm[:, 1 : self.num_register_tokens + 1],
+                    "x_norm_patchtokens": x_norm[:, self.num_register_tokens + 1 :],
+                    "x_prenorm": x,
+                    "masks": masks,
+                }
+            )
+        return output
+
+    def forward_features(self, x, masks=None):
+        if isinstance(x, list):
+            return self.forward_features_list(x, masks)
+
+        x = self.prepare_tokens_with_masks(x, masks)
+
+        for blk in self.blocks:
+            x = blk(x)
+
+        x_norm = self.norm(x)
+        return {
+            "x_norm_clstoken": x_norm[:, 0],
+            "x_norm_regtokens": x_norm[:, 1 : self.num_register_tokens + 1],
+            "x_norm_patchtokens": x_norm[:, self.num_register_tokens + 1 :],
+            "x_prenorm": x,
+            "masks": masks,
+        }
+
+    def _get_intermediate_layers_not_chunked(self, x, n=1):
+        x = self.prepare_tokens_with_masks(x)
+        # If n is an int, take the n last blocks. If it's a list, take them
+        output, total_block_len = [], len(self.blocks)
+        blocks_to_take = range(total_block_len - n, total_block_len) if isinstance(n, int) else n
+        for i, blk in enumerate(self.blocks):
+            x = blk(x)
+            if i in blocks_to_take:
+                output.append(x)
+        assert len(output) == len(blocks_to_take), f"only {len(output)} / {len(blocks_to_take)} blocks found"
+        return output
+
+    def _get_intermediate_layers_chunked(self, x, n=1):
+        x = self.prepare_tokens_with_masks(x)
+        output, i, total_block_len = [], 0, len(self.blocks[-1])
+        # If n is an int, take the n last blocks. If it's a list, take them
+        blocks_to_take = range(total_block_len - n, total_block_len) if isinstance(n, int) else n
+        for block_chunk in self.blocks:
+            for blk in block_chunk[i:]:  # Passing the nn.Identity()
+                x = blk(x)
+                if i in blocks_to_take:
+                    output.append(x)
+                i += 1
+        assert len(output) == len(blocks_to_take), f"only {len(output)} / {len(blocks_to_take)} blocks found"
+        return output
+
+    def get_intermediate_layers(
+        self,
+        x: torch.Tensor,
+        n: Union[int, Sequence] = 1,  # Layers or n last layers to take
+        reshape: bool = False,
+        return_class_token: bool = False,
+        norm=True,
+    ) -> Tuple[Union[torch.Tensor, Tuple[torch.Tensor]]]:
+        if self.chunked_blocks:
+            outputs = self._get_intermediate_layers_chunked(x, n)
+        else:
+            outputs = self._get_intermediate_layers_not_chunked(x, n)
+        if norm:
+            outputs = [self.norm(out) for out in outputs]
+        class_tokens = [out[:, 0] for out in outputs]
+        outputs = [out[:, 1 + self.num_register_tokens :] for out in outputs]
+        if reshape:
+            B, _, w, h = x.shape
+            outputs = [
+                out.reshape(B, w // self.patch_size, h // self.patch_size, -1).permute(0, 3, 1, 2).contiguous()
+                for out in outputs
+            ]
+        if return_class_token:
+            return tuple(zip(outputs, class_tokens))
+        return tuple(outputs)
+
+    def forward(self, *args, is_training=False, **kwargs):
+        ret = self.forward_features(*args, **kwargs)
+        if is_training:
+            return ret
+        else:
+            return self.head(ret["x_norm_clstoken"])
+
+
+def init_weights_vit_timm(module: nn.Module, name: str = ""):
+    """ViT weight initialization, original timm impl (for reproducibility)"""
+    if isinstance(module, nn.Linear):
+        trunc_normal_(module.weight, std=0.02)
+        if module.bias is not None:
+            nn.init.zeros_(module.bias)
+
+
+def vit_small(patch_size=16, num_register_tokens=0, **kwargs):
+    model = DinoVisionTransformer(
+        patch_size=patch_size,
+        embed_dim=384,
+        depth=12,
+        num_heads=6,
+        mlp_ratio=4,
+        block_fn=partial(Block, attn_class=MemEffAttention),
+        num_register_tokens=num_register_tokens,
+        **kwargs,
+    )
+    return model
+
+
+def vit_base(patch_size=16, num_register_tokens=0, **kwargs):
+    model = DinoVisionTransformer(
+        patch_size=patch_size,
+        embed_dim=768,
+        depth=12,
+        num_heads=12,
+        mlp_ratio=4,
+        block_fn=partial(Block, attn_class=MemEffAttention),
+        num_register_tokens=num_register_tokens,
+        **kwargs,
+    )
+    return model
+
+
+def vit_large(patch_size=16, num_register_tokens=0, **kwargs):
+    model = DinoVisionTransformer(
+        patch_size=patch_size,
+        embed_dim=1024,
+        depth=24,
+        num_heads=16,
+        mlp_ratio=4,
+        block_fn=partial(Block, attn_class=MemEffAttention),
+        num_register_tokens=num_register_tokens,
+        **kwargs,
+    )
+    return model
+
+
+def vit_giant2(patch_size=16, num_register_tokens=0, **kwargs):
+    """
+    Close to ViT-giant, with embed-dim 1536 and 24 heads => embed-dim per head 64
+    """
+    model = DinoVisionTransformer(
+        patch_size=patch_size,
+        embed_dim=1536,
+        depth=40,
+        num_heads=24,
+        mlp_ratio=4,
+        block_fn=partial(Block, attn_class=MemEffAttention),
+        num_register_tokens=num_register_tokens,
+        **kwargs,
+    )
+    return model
+
+
+def DINOv2(model_name):
+    model_zoo = {"vits": vit_small, "vitb": vit_base, "vitl": vit_large, "vitg": vit_giant2}
+
+    return model_zoo[model_name](
+        img_size=518,
+        patch_size=14,
+        init_values=1.0,
+        ffn_layer="mlp" if model_name != "vitg" else "swiglufused",
+        block_chunks=0,
+        num_register_tokens=0,
+        interpolate_antialias=False,
+        interpolate_offset=0.1,
+    )

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/__init__.py

@@ -0,0 +1,11 @@
+# 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.
+
+from .attention import MemEffAttention
+from .block import NestedTensorBlock
+from .mlp import Mlp
+from .patch_embed import PatchEmbed
+from .swiglu_ffn import SwiGLUFFN, SwiGLUFFNFused

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/attention.py

@@ -0,0 +1,79 @@
+# 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.
+
+# References:
+#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
+#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/models/vision_transformer.py
+
+import logging
+
+from torch import Tensor, nn
+
+logger = logging.getLogger("dinov2")
+
+
+try:
+    from xformers.ops import fmha, memory_efficient_attention, unbind
+
+    XFORMERS_AVAILABLE = True
+except ImportError:
+    logger.warning("xFormers not available")
+    XFORMERS_AVAILABLE = False
+
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim: int,
+        num_heads: int = 8,
+        qkv_bias: bool = False,
+        proj_bias: bool = True,
+        attn_drop: float = 0.0,
+        proj_drop: float = 0.0,
+    ) -> None:
+        super().__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = head_dim**-0.5
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim, bias=proj_bias)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+    def forward(self, x: Tensor) -> Tensor:
+        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] * self.scale, qkv[1], qkv[2]
+        attn = q @ k.transpose(-2, -1)
+
+        attn = attn.softmax(dim=-1)
+        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 MemEffAttention(Attention):
+    def forward(self, x: Tensor, attn_bias=None) -> Tensor:
+        if not XFORMERS_AVAILABLE:
+            assert attn_bias is None, "xFormers is required for nested tensors usage"
+            return super().forward(x)
+
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads)
+
+        q, k, v = unbind(qkv, 2)
+
+        x = memory_efficient_attention(q, k, v, attn_bias=attn_bias)
+        x = x.reshape([B, N, C])
+
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/block.py

@@ -0,0 +1,250 @@
+# 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.
+
+# References:
+#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
+#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/patch_embed.py
+
+import logging
+from typing import Any, Callable, Dict, List, Tuple
+
+import torch
+from torch import Tensor, nn
+
+from .attention import Attention, MemEffAttention
+from .drop_path import DropPath
+from .layer_scale import LayerScale
+from .mlp import Mlp
+
+logger = logging.getLogger("dinov2")
+
+
+try:
+    from xformers.ops import fmha, index_select_cat, scaled_index_add
+
+    XFORMERS_AVAILABLE = True
+except ImportError:
+    logger.warning("xFormers not available")
+    XFORMERS_AVAILABLE = False
+
+
+class Block(nn.Module):
+    def __init__(
+        self,
+        dim: int,
+        num_heads: int,
+        mlp_ratio: float = 4.0,
+        qkv_bias: bool = False,
+        proj_bias: bool = True,
+        ffn_bias: bool = True,
+        drop: float = 0.0,
+        attn_drop: float = 0.0,
+        init_values=None,
+        drop_path: float = 0.0,
+        act_layer: Callable[..., nn.Module] = nn.GELU,
+        norm_layer: Callable[..., nn.Module] = nn.LayerNorm,
+        attn_class: Callable[..., nn.Module] = Attention,
+        ffn_layer: Callable[..., nn.Module] = Mlp,
+    ) -> None:
+        super().__init__()
+        # print(f"biases: qkv: {qkv_bias}, proj: {proj_bias}, ffn: {ffn_bias}")
+        self.norm1 = norm_layer(dim)
+        self.attn = attn_class(
+            dim,
+            num_heads=num_heads,
+            qkv_bias=qkv_bias,
+            proj_bias=proj_bias,
+            attn_drop=attn_drop,
+            proj_drop=drop,
+        )
+        self.ls1 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
+        self.drop_path1 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
+
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = ffn_layer(
+            in_features=dim,
+            hidden_features=mlp_hidden_dim,
+            act_layer=act_layer,
+            drop=drop,
+            bias=ffn_bias,
+        )
+        self.ls2 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
+        self.drop_path2 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
+
+        self.sample_drop_ratio = drop_path
+
+    def forward(self, x: Tensor) -> Tensor:
+        def attn_residual_func(x: Tensor) -> Tensor:
+            return self.ls1(self.attn(self.norm1(x)))
+
+        def ffn_residual_func(x: Tensor) -> Tensor:
+            return self.ls2(self.mlp(self.norm2(x)))
+
+        if self.training and self.sample_drop_ratio > 0.1:
+            # the overhead is compensated only for a drop path rate larger than 0.1
+            x = drop_add_residual_stochastic_depth(
+                x,
+                residual_func=attn_residual_func,
+                sample_drop_ratio=self.sample_drop_ratio,
+            )
+            x = drop_add_residual_stochastic_depth(
+                x,
+                residual_func=ffn_residual_func,
+                sample_drop_ratio=self.sample_drop_ratio,
+            )
+        elif self.training and self.sample_drop_ratio > 0.0:
+            x = x + self.drop_path1(attn_residual_func(x))
+            x = x + self.drop_path1(ffn_residual_func(x))  # FIXME: drop_path2
+        else:
+            x = x + attn_residual_func(x)
+            x = x + ffn_residual_func(x)
+        return x
+
+
+def drop_add_residual_stochastic_depth(
+    x: Tensor,
+    residual_func: Callable[[Tensor], Tensor],
+    sample_drop_ratio: float = 0.0,
+) -> Tensor:
+    # 1) extract subset using permutation
+    b, n, d = x.shape
+    sample_subset_size = max(int(b * (1 - sample_drop_ratio)), 1)
+    brange = (torch.randperm(b, device=x.device))[:sample_subset_size]
+    x_subset = x[brange]
+
+    # 2) apply residual_func to get residual
+    residual = residual_func(x_subset)
+
+    x_flat = x.flatten(1)
+    residual = residual.flatten(1)
+
+    residual_scale_factor = b / sample_subset_size
+
+    # 3) add the residual
+    x_plus_residual = torch.index_add(x_flat, 0, brange, residual.to(dtype=x.dtype), alpha=residual_scale_factor)
+    return x_plus_residual.view_as(x)
+
+
+def get_branges_scales(x, sample_drop_ratio=0.0):
+    b, n, d = x.shape
+    sample_subset_size = max(int(b * (1 - sample_drop_ratio)), 1)
+    brange = (torch.randperm(b, device=x.device))[:sample_subset_size]
+    residual_scale_factor = b / sample_subset_size
+    return brange, residual_scale_factor
+
+
+def add_residual(x, brange, residual, residual_scale_factor, scaling_vector=None):
+    if scaling_vector is None:
+        x_flat = x.flatten(1)
+        residual = residual.flatten(1)
+        x_plus_residual = torch.index_add(x_flat, 0, brange, residual.to(dtype=x.dtype), alpha=residual_scale_factor)
+    else:
+        x_plus_residual = scaled_index_add(
+            x, brange, residual.to(dtype=x.dtype), scaling=scaling_vector, alpha=residual_scale_factor
+        )
+    return x_plus_residual
+
+
+attn_bias_cache: Dict[Tuple, Any] = {}
+
+
+def get_attn_bias_and_cat(x_list, branges=None):
+    """
+    this will perform the index select, cat the tensors, and provide the attn_bias from cache
+    """
+    batch_sizes = [b.shape[0] for b in branges] if branges is not None else [x.shape[0] for x in x_list]
+    all_shapes = tuple((b, x.shape[1]) for b, x in zip(batch_sizes, x_list))
+    if all_shapes not in attn_bias_cache.keys():
+        seqlens = []
+        for b, x in zip(batch_sizes, x_list):
+            for _ in range(b):
+                seqlens.append(x.shape[1])
+        attn_bias = fmha.BlockDiagonalMask.from_seqlens(seqlens)
+        attn_bias._batch_sizes = batch_sizes
+        attn_bias_cache[all_shapes] = attn_bias
+
+    if branges is not None:
+        cat_tensors = index_select_cat([x.flatten(1) for x in x_list], branges).view(1, -1, x_list[0].shape[-1])
+    else:
+        tensors_bs1 = tuple(x.reshape([1, -1, *x.shape[2:]]) for x in x_list)
+        cat_tensors = torch.cat(tensors_bs1, dim=1)
+
+    return attn_bias_cache[all_shapes], cat_tensors
+
+
+def drop_add_residual_stochastic_depth_list(
+    x_list: List[Tensor],
+    residual_func: Callable[[Tensor, Any], Tensor],
+    sample_drop_ratio: float = 0.0,
+    scaling_vector=None,
+) -> Tensor:
+    # 1) generate random set of indices for dropping samples in the batch
+    branges_scales = [get_branges_scales(x, sample_drop_ratio=sample_drop_ratio) for x in x_list]
+    branges = [s[0] for s in branges_scales]
+    residual_scale_factors = [s[1] for s in branges_scales]
+
+    # 2) get attention bias and index+concat the tensors
+    attn_bias, x_cat = get_attn_bias_and_cat(x_list, branges)
+
+    # 3) apply residual_func to get residual, and split the result
+    residual_list = attn_bias.split(residual_func(x_cat, attn_bias=attn_bias))  # type: ignore
+
+    outputs = []
+    for x, brange, residual, residual_scale_factor in zip(x_list, branges, residual_list, residual_scale_factors):
+        outputs.append(add_residual(x, brange, residual, residual_scale_factor, scaling_vector).view_as(x))
+    return outputs
+
+
+class NestedTensorBlock(Block):
+    def forward_nested(self, x_list: List[Tensor]) -> List[Tensor]:
+        """
+        x_list contains a list of tensors to nest together and run
+        """
+        assert isinstance(self.attn, MemEffAttention)
+
+        if self.training and self.sample_drop_ratio > 0.0:
+
+            def attn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
+                return self.attn(self.norm1(x), attn_bias=attn_bias)
+
+            def ffn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
+                return self.mlp(self.norm2(x))
+
+            x_list = drop_add_residual_stochastic_depth_list(
+                x_list,
+                residual_func=attn_residual_func,
+                sample_drop_ratio=self.sample_drop_ratio,
+                scaling_vector=self.ls1.gamma if isinstance(self.ls1, LayerScale) else None,
+            )
+            x_list = drop_add_residual_stochastic_depth_list(
+                x_list,
+                residual_func=ffn_residual_func,
+                sample_drop_ratio=self.sample_drop_ratio,
+                scaling_vector=self.ls2.gamma if isinstance(self.ls1, LayerScale) else None,
+            )
+            return x_list
+        else:
+
+            def attn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
+                return self.ls1(self.attn(self.norm1(x), attn_bias=attn_bias))
+
+            def ffn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
+                return self.ls2(self.mlp(self.norm2(x)))
+
+            attn_bias, x = get_attn_bias_and_cat(x_list)
+            x = x + attn_residual_func(x, attn_bias=attn_bias)
+            x = x + ffn_residual_func(x)
+            return attn_bias.split(x)
+
+    def forward(self, x_or_x_list):
+        if isinstance(x_or_x_list, Tensor):
+            return super().forward(x_or_x_list)
+        elif isinstance(x_or_x_list, list):
+            assert XFORMERS_AVAILABLE, "Please install xFormers for nested tensors usage"
+            return self.forward_nested(x_or_x_list)
+        else:
+            raise AssertionError

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/drop_path.py

@@ -0,0 +1,35 @@
+# 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.
+
+# References:
+#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
+#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/drop.py
+
+
+from torch import nn
+
+
+def drop_path(x, drop_prob: float = 0.0, training: bool = False):
+    if drop_prob == 0.0 or not training:
+        return x
+    keep_prob = 1 - drop_prob
+    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
+    random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
+    if keep_prob > 0.0:
+        random_tensor.div_(keep_prob)
+    output = x * random_tensor
+    return output
+
+
+class DropPath(nn.Module):
+    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks)."""
+
+    def __init__(self, drop_prob=None):
+        super(DropPath, self).__init__()
+        self.drop_prob = drop_prob
+
+    def forward(self, x):
+        return drop_path(x, self.drop_prob, self.training)

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/layer_scale.py

@@ -0,0 +1,27 @@
+# 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.
+
+# Modified from: https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py#L103-L110
+
+from typing import Union
+
+import torch
+from torch import Tensor, nn
+
+
+class LayerScale(nn.Module):
+    def __init__(
+        self,
+        dim: int,
+        init_values: Union[float, Tensor] = 1e-5,
+        inplace: bool = False,
+    ) -> None:
+        super().__init__()
+        self.inplace = inplace
+        self.gamma = nn.Parameter(init_values * torch.ones(dim))
+
+    def forward(self, x: Tensor) -> Tensor:
+        return x.mul_(self.gamma) if self.inplace else x * self.gamma

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/mlp.py

@@ -0,0 +1,41 @@
+# 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.
+
+# References:
+#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
+#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/mlp.py
+
+
+from typing import Callable, Optional
+
+from torch import Tensor, nn
+
+
+class Mlp(nn.Module):
+    def __init__(
+        self,
+        in_features: int,
+        hidden_features: Optional[int] = None,
+        out_features: Optional[int] = None,
+        act_layer: Callable[..., nn.Module] = nn.GELU,
+        drop: float = 0.0,
+        bias: bool = True,
+    ) -> None:
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features, bias=bias)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features, bias=bias)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x: Tensor) -> Tensor:
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/patch_embed.py

@@ -0,0 +1,89 @@
+# 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.
+
+# References:
+#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
+#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/patch_embed.py
+
+from typing import Callable, Optional, Tuple, Union
+
+import torch.nn as nn
+from torch import Tensor
+
+
+def make_2tuple(x):
+    if isinstance(x, tuple):
+        assert len(x) == 2
+        return x
+
+    assert isinstance(x, int)
+    return (x, x)
+
+
+class PatchEmbed(nn.Module):
+    """
+    2D image to patch embedding: (B,C,H,W) -> (B,N,D)
+
+    Args:
+        img_size: Image size.
+        patch_size: Patch token size.
+        in_chans: Number of input image channels.
+        embed_dim: Number of linear projection output channels.
+        norm_layer: Normalization layer.
+    """
+
+    def __init__(
+        self,
+        img_size: Union[int, Tuple[int, int]] = 224,
+        patch_size: Union[int, Tuple[int, int]] = 16,
+        in_chans: int = 3,
+        embed_dim: int = 768,
+        norm_layer: Optional[Callable] = None,
+        flatten_embedding: bool = True,
+    ) -> None:
+        super().__init__()
+
+        image_HW = make_2tuple(img_size)
+        patch_HW = make_2tuple(patch_size)
+        patch_grid_size = (
+            image_HW[0] // patch_HW[0],
+            image_HW[1] // patch_HW[1],
+        )
+
+        self.img_size = image_HW
+        self.patch_size = patch_HW
+        self.patches_resolution = patch_grid_size
+        self.num_patches = patch_grid_size[0] * patch_grid_size[1]
+
+        self.in_chans = in_chans
+        self.embed_dim = embed_dim
+
+        self.flatten_embedding = flatten_embedding
+
+        self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_HW, stride=patch_HW)
+        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
+
+    def forward(self, x: Tensor) -> Tensor:
+        _, _, H, W = x.shape
+        patch_H, patch_W = self.patch_size
+
+        assert H % patch_H == 0, f"Input image height {H} is not a multiple of patch height {patch_H}"
+        assert W % patch_W == 0, f"Input image width {W} is not a multiple of patch width: {patch_W}"
+
+        x = self.proj(x)  # B C H W
+        H, W = x.size(2), x.size(3)
+        x = x.flatten(2).transpose(1, 2)  # B HW C
+        x = self.norm(x)
+        if not self.flatten_embedding:
+            x = x.reshape(-1, H, W, self.embed_dim)  # B H W C
+        return x
+
+    def flops(self) -> float:
+        Ho, Wo = self.patches_resolution
+        flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1])
+        if self.norm is not None:
+            flops += Ho * Wo * self.embed_dim
+        return flops

invokeai/backend/image_util/depth_anything/v2/dinov2_layers/swiglu_ffn.py

@@ -0,0 +1,63 @@
+# 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.
+
+from typing import Callable, Optional
+
+import torch.nn.functional as F
+from torch import Tensor, nn
+
+
+class SwiGLUFFN(nn.Module):
+    def __init__(
+        self,
+        in_features: int,
+        hidden_features: Optional[int] = None,
+        out_features: Optional[int] = None,
+        act_layer: Callable[..., nn.Module] = None,
+        drop: float = 0.0,
+        bias: bool = True,
+    ) -> None:
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.w12 = nn.Linear(in_features, 2 * hidden_features, bias=bias)
+        self.w3 = nn.Linear(hidden_features, out_features, bias=bias)
+
+    def forward(self, x: Tensor) -> Tensor:
+        x12 = self.w12(x)
+        x1, x2 = x12.chunk(2, dim=-1)
+        hidden = F.silu(x1) * x2
+        return self.w3(hidden)
+
+
+try:
+    from xformers.ops import SwiGLU
+
+    XFORMERS_AVAILABLE = True
+except ImportError:
+    SwiGLU = SwiGLUFFN
+    XFORMERS_AVAILABLE = False
+
+
+class SwiGLUFFNFused(SwiGLU):
+    def __init__(
+        self,
+        in_features: int,
+        hidden_features: Optional[int] = None,
+        out_features: Optional[int] = None,
+        act_layer: Callable[..., nn.Module] = None,
+        drop: float = 0.0,
+        bias: bool = True,
+    ) -> None:
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        hidden_features = (int(hidden_features * 2 / 3) + 7) // 8 * 8
+        super().__init__(
+            in_features=in_features,
+            hidden_features=hidden_features,
+            out_features=out_features,
+            bias=bias,
+        )

invokeai/backend/image_util/depth_anything/v2/dpt.py

@@ -1,12 +1,12 @@
-from pathlib import Path
+import cv2
-
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
+from torchvision.transforms import Compose
 
-from invokeai.backend.image_util.depth_anything.model.blocks import FeatureFusionBlock, _make_scratch
+from .dinov2 import DINOv2
-
+from .utils.blocks import FeatureFusionBlock, _make_scratch
-torchhub_path = Path(__file__).parent.parent / "torchhub"
+from .utils.transform import NormalizeImage, PrepareForNet, Resize
 
 
 def _make_fusion_block(features, use_bn, size=None):
@@ -21,11 +21,26 @@ def _make_fusion_block(features, use_bn, size=None):
     )
 
 
+class ConvBlock(nn.Module):
+    def __init__(self, in_feature, out_feature):
+        super().__init__()
+
+        self.conv_block = nn.Sequential(
+            nn.Conv2d(in_feature, out_feature, kernel_size=3, stride=1, padding=1),
+            nn.BatchNorm2d(out_feature),
+            nn.ReLU(True),
+        )
+
+    def forward(self, x):
+        return self.conv_block(x)
+
+
 class DPTHead(nn.Module):
-    def __init__(self, nclass, in_channels, features, out_channels, use_bn=False, use_clstoken=False):
+    def __init__(
+        self, in_channels, features=256, use_bn=False, out_channels=[256, 512, 1024, 1024], use_clstoken=False
+    ):
         super(DPTHead, self).__init__()
 
-        self.nclass = nclass
         self.use_clstoken = use_clstoken
 
         self.projects = nn.ModuleList(
@@ -78,24 +93,14 @@ class DPTHead(nn.Module):
         head_features_1 = features
         head_features_2 = 32
 
-        if nclass > 1:
+        self.scratch.output_conv1 = nn.Conv2d(head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1)
-            self.scratch.output_conv = nn.Sequential(
+        self.scratch.output_conv2 = nn.Sequential(
-                nn.Conv2d(head_features_1, head_features_1, kernel_size=3, stride=1, padding=1),
+            nn.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1),
-                nn.ReLU(True),
+            nn.ReLU(True),
-                nn.Conv2d(head_features_1, nclass, kernel_size=1, stride=1, padding=0),
+            nn.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0),
-            )
+            nn.ReLU(True),
-        else:
+            nn.Identity(),
-            self.scratch.output_conv1 = nn.Conv2d(
+        )
-                head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1
-            )
-
-            self.scratch.output_conv2 = nn.Sequential(
-                nn.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1),
-                nn.ReLU(True),
-                nn.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0),
-                nn.ReLU(True),
-                nn.Identity(),
-            )
 
     def forward(self, out_features, patch_h, patch_w):
         out = []
@@ -133,51 +138,73 @@ class DPTHead(nn.Module):
         return out
 
 
-class DPT_DINOv2(nn.Module):
+class DepthAnythingV2(nn.Module):
     def __init__(
-        self,
+        self, encoder="vitl", features=256, out_channels=[256, 512, 1024, 1024], use_bn=False, use_clstoken=False
-        features,
-        out_channels,
-        encoder="vitl",
-        use_bn=False,
-        use_clstoken=False,
     ):
-        super(DPT_DINOv2, self).__init__()
+        super(DepthAnythingV2, self).__init__()
 
-        assert encoder in ["vits", "vitb", "vitl"]
+        self.intermediate_layer_idx = {
+            "vits": [2, 5, 8, 11],
+            "vitb": [2, 5, 8, 11],
+            "vitl": [4, 11, 17, 23],
+            "vitg": [9, 19, 29, 39],
+        }
 
-        # # in case the Internet connection is not stable, please load the DINOv2 locally
+        self.encoder = encoder
-        # if use_local:
+        self.pretrained = DINOv2(model_name=encoder)
-        #     self.pretrained = torch.hub.load(
-        #         torchhub_path / "facebookresearch_dinov2_main",
-        #         "dinov2_{:}14".format(encoder),
-        #         source="local",
-        #         pretrained=False,
-        #     )
-        # else:
-        #     self.pretrained = torch.hub.load(
-        #         "facebookresearch/dinov2",
-        #         "dinov2_{:}14".format(encoder),
-        #     )
 
-        self.pretrained = torch.hub.load(
+        self.depth_head = DPTHead(
-            "facebookresearch/dinov2",
+            self.pretrained.embed_dim, features, use_bn, out_channels=out_channels, use_clstoken=use_clstoken
-            "dinov2_{:}14".format(encoder),
         )
 
-        dim = self.pretrained.blocks[0].attn.qkv.in_features
-
-        self.depth_head = DPTHead(1, dim, features, out_channels=out_channels, use_bn=use_bn, use_clstoken=use_clstoken)
-
     def forward(self, x):
-        h, w = x.shape[-2:]
+        patch_h, patch_w = x.shape[-2] // 14, x.shape[-1] // 14
 
-        features = self.pretrained.get_intermediate_layers(x, 4, return_class_token=True)
+        features = self.pretrained.get_intermediate_layers(
-
+            x, self.intermediate_layer_idx[self.encoder], return_class_token=True
-        patch_h, patch_w = h // 14, w // 14
+        )
 
         depth = self.depth_head(features, patch_h, patch_w)
-        depth = F.interpolate(depth, size=(h, w), mode="bilinear", align_corners=True)
         depth = F.relu(depth)
 
         return depth.squeeze(1)
+
+    @torch.no_grad()
+    def infer_image(self, raw_image, input_size=518):
+        image, (h, w) = self.image2tensor(raw_image, input_size)
+
+        depth = self.forward(image)
+
+        depth = F.interpolate(depth[:, None], (h, w), mode="bilinear", align_corners=True)[0, 0]
+
+        return depth.cpu().numpy()
+
+    def image2tensor(self, raw_image, input_size=518):
+        transform = Compose(
+            [
+                Resize(
+                    width=input_size,
+                    height=input_size,
+                    resize_target=False,
+                    keep_aspect_ratio=True,
+                    ensure_multiple_of=14,
+                    resize_method="lower_bound",
+                    image_interpolation_method=cv2.INTER_CUBIC,
+                ),
+                NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+                PrepareForNet(),
+            ]
+        )
+
+        h, w = raw_image.shape[:2]
+
+        image = cv2.cvtColor(raw_image, cv2.COLOR_BGR2RGB) / 255.0
+
+        image = transform({"image": image})["image"]
+        image = torch.from_numpy(image).unsqueeze(0)
+
+        DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+        image = image.to(DEVICE)
+
+        return image, (h, w)

invokeai/backend/image_util/depth_anything/v2/utils/blocks.py

@@ -53,7 +53,7 @@ class ResidualConvUnit(nn.Module):
 
         self.conv2 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
 
-        if self.bn:
+        if self.bn == True:
             self.bn1 = nn.BatchNorm2d(features)
             self.bn2 = nn.BatchNorm2d(features)
 
@@ -73,12 +73,12 @@ class ResidualConvUnit(nn.Module):
 
         out = self.activation(x)
         out = self.conv1(out)
-        if self.bn:
+        if self.bn == True:
             out = self.bn1(out)
 
         out = self.activation(out)
         out = self.conv2(out)
-        if self.bn:
+        if self.bn == True:
             out = self.bn2(out)
 
         if self.groups > 1:
@@ -105,7 +105,7 @@ class FeatureFusionBlock(nn.Module):
 
         self.expand = expand
         out_features = features
-        if self.expand:
+        if self.expand == True:
             out_features = features // 2
 
         self.out_conv = nn.Conv2d(features, out_features, kernel_size=1, stride=1, padding=0, bias=True, groups=1)

invokeai/backend/image_util/depth_anything/v2/utils/transform.py

@@ -1,47 +1,5 @@
-import math
-
 import cv2
 import numpy as np
-import torch
-import torch.nn.functional as F
-
-
-def apply_min_size(sample, size, image_interpolation_method=cv2.INTER_AREA):
-    """Rezise the sample to ensure the given size. Keeps aspect ratio.
-
-    Args:
-        sample (dict): sample
-        size (tuple): image size
-
-    Returns:
-        tuple: new size
-    """
-    shape = list(sample["disparity"].shape)
-
-    if shape[0] >= size[0] and shape[1] >= size[1]:
-        return sample
-
-    scale = [0, 0]
-    scale[0] = size[0] / shape[0]
-    scale[1] = size[1] / shape[1]
-
-    scale = max(scale)
-
-    shape[0] = math.ceil(scale * shape[0])
-    shape[1] = math.ceil(scale * shape[1])
-
-    # resize
-    sample["image"] = cv2.resize(sample["image"], tuple(shape[::-1]), interpolation=image_interpolation_method)
-
-    sample["disparity"] = cv2.resize(sample["disparity"], tuple(shape[::-1]), interpolation=cv2.INTER_NEAREST)
-    sample["mask"] = cv2.resize(
-        sample["mask"].astype(np.float32),
-        tuple(shape[::-1]),
-        interpolation=cv2.INTER_NEAREST,
-    )
-    sample["mask"] = sample["mask"].astype(bool)
-
-    return tuple(shape)
 
 
 class Resize(object):
@@ -76,8 +34,7 @@ class Resize(object):
                 Defaults to 1.
             resize_method (str, optional):
                 "lower_bound": Output will be at least as large as the given size.
-                "upper_bound": Output will be at max as large as the given size. (Output size might be smaller
+                "upper_bound": Output will be at max as large as the given size. (Output size might be smaller than given size.)
-                    than given size.)
                 "minimal": Scale as least as possible.  (Output size might be smaller than given size.)
                 Defaults to "lower_bound".
         """
@@ -152,40 +109,17 @@ class Resize(object):
         width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0])
 
         # resize sample
-        sample["image"] = cv2.resize(
+        sample["image"] = cv2.resize(sample["image"], (width, height), interpolation=self.__image_interpolation_method)
-            sample["image"],
-            (width, height),
-            interpolation=self.__image_interpolation_method,
-        )
 
         if self.__resize_target:
-            if "disparity" in sample:
-                sample["disparity"] = cv2.resize(
-                    sample["disparity"],
-                    (width, height),
-                    interpolation=cv2.INTER_NEAREST,
-                )
-
             if "depth" in sample:
                 sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST)
 
-            if "semseg_mask" in sample:
-                # sample["semseg_mask"] = cv2.resize(
-                #     sample["semseg_mask"], (width, height), interpolation=cv2.INTER_NEAREST
-                # )
-                sample["semseg_mask"] = F.interpolate(
-                    torch.from_numpy(sample["semseg_mask"]).float()[None, None, ...], (height, width), mode="nearest"
-                ).numpy()[0, 0]
-
             if "mask" in sample:
                 sample["mask"] = cv2.resize(
-                    sample["mask"].astype(np.float32),
+                    sample["mask"].astype(np.float32), (width, height), interpolation=cv2.INTER_NEAREST
-                    (width, height),
-                    interpolation=cv2.INTER_NEAREST,
                 )
-                # sample["mask"] = sample["mask"].astype(bool)
 
-        # print(sample['image'].shape, sample['depth'].shape)
         return sample
 
 
@@ -212,16 +146,12 @@ class PrepareForNet(object):
         image = np.transpose(sample["image"], (2, 0, 1))
         sample["image"] = np.ascontiguousarray(image).astype(np.float32)
 
-        if "mask" in sample:
-            sample["mask"] = sample["mask"].astype(np.float32)
-            sample["mask"] = np.ascontiguousarray(sample["mask"])
-
         if "depth" in sample:
             depth = sample["depth"].astype(np.float32)
             sample["depth"] = np.ascontiguousarray(depth)
 
-        if "semseg_mask" in sample:
+        if "mask" in sample:
-            sample["semseg_mask"] = sample["semseg_mask"].astype(np.float32)
+            sample["mask"] = sample["mask"].astype(np.float32)
-            sample["semseg_mask"] = np.ascontiguousarray(sample["semseg_mask"])
+            sample["mask"] = np.ascontiguousarray(sample["mask"])
 
         return sample