Spaces:
Configuration error
Configuration error
File size: 4,123 Bytes
0034848 |
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 |
import os
import cv2
import numpy as np
import torch
from einops import rearrange
from PIL import Image
from custom_controlnet_aux.util import HWC3, common_input_validate, resize_image_with_pad, custom_hf_download, HF_MODEL_NAME, DEPTH_ANYTHING_MODEL_NAME
from .zoedepth.models.zoedepth.zoedepth_v1 import ZoeDepth
from .zoedepth.models.zoedepth_anything.zoedepth_v1 import ZoeDepth as ZoeDepthAnything
from .zoedepth.utils.config import get_config
class ZoeDetector:
def __init__(self, model):
self.model = model
self.device = "cpu"
@classmethod
def from_pretrained(cls, pretrained_model_or_path=HF_MODEL_NAME, filename="ZoeD_M12_N.pt"):
model_path = custom_hf_download(pretrained_model_or_path, filename)
conf = get_config("zoedepth", "infer")
model = ZoeDepth.build_from_config(conf)
model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu'))['model'])
model.eval()
return cls(model)
def to(self, device):
self.model.to(device)
self.device = device
return self
def __call__(self, input_image, detect_resolution=512, output_type=None, upscale_method="INTER_CUBIC", **kwargs):
input_image, output_type = common_input_validate(input_image, output_type, **kwargs)
input_image, remove_pad = resize_image_with_pad(input_image, detect_resolution, upscale_method)
image_depth = input_image
with torch.no_grad():
image_depth = torch.from_numpy(image_depth).float().to(self.device)
image_depth = image_depth / 255.0
image_depth = rearrange(image_depth, 'h w c -> 1 c h w')
depth = self.model.infer(image_depth)
depth = depth[0, 0].cpu().numpy()
vmin = np.percentile(depth, 2)
vmax = np.percentile(depth, 85)
depth -= vmin
depth /= vmax - vmin
depth = 1.0 - depth
depth_image = (depth * 255.0).clip(0, 255).astype(np.uint8)
detected_map = remove_pad(HWC3(depth_image))
if output_type == "pil":
detected_map = Image.fromarray(detected_map)
return detected_map
class ZoeDepthAnythingDetector:
def __init__(self, model):
self.model = model
self.device = "cpu"
@classmethod
def from_pretrained(cls, pretrained_model_or_path=DEPTH_ANYTHING_MODEL_NAME, filename="depth_anything_metric_depth_indoor.pt"):
model_path = custom_hf_download(pretrained_model_or_path, filename, subfolder="checkpoints_metric_depth", repo_type="space")
conf = get_config("zoedepth", "infer")
model = ZoeDepthAnything.build_from_config(conf)
model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu'))['model'])
model.eval()
return cls(model)
def to(self, device):
self.model.to(device)
self.device = device
return self
def __call__(self, input_image, detect_resolution=512, output_type=None, upscale_method="INTER_CUBIC", **kwargs):
input_image, output_type = common_input_validate(input_image, output_type, **kwargs)
input_image, remove_pad = resize_image_with_pad(input_image, detect_resolution, upscale_method)
image_depth = input_image
with torch.no_grad():
image_depth = torch.from_numpy(image_depth).float().to(self.device)
image_depth = image_depth / 255.0
image_depth = rearrange(image_depth, 'h w c -> 1 c h w')
depth = self.model.infer(image_depth)
depth = depth[0, 0].cpu().numpy()
vmin = np.percentile(depth, 2)
vmax = np.percentile(depth, 85)
depth -= vmin
depth /= vmax - vmin
depth = 1.0 - depth
depth_image = (depth * 255.0).clip(0, 255).astype(np.uint8)
detected_map = remove_pad(HWC3(depth_image))
if output_type == "pil":
detected_map = Image.fromarray(detected_map)
return detected_map |