Spaces:
Build error
Build error
File size: 3,152 Bytes
9930f16 5f51879 9930f16 |
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 |
import torch
import torch.nn.functional as F
import numpy as np
import cv2
from PIL import Image
from config import SAPIENS_LITE_MODELS_PATH
def load_model(task, version):
try:
model_path = SAPIENS_LITE_MODELS_PATH[task][version]
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if torch.cuda.is_available() and torch.cuda.get_device_properties(0).major >= 8:
torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.allow_tf32 = True
model = torch.jit.load(model_path)
model.eval()
model.to(device)
return model, device
except KeyError as e:
print(f"Error: Tarea o versión inválida. {e}")
return None, None
def preprocess_image(image, input_shape):
img = cv2.resize(image, (input_shape[2], input_shape[1]), interpolation=cv2.INTER_LINEAR).transpose(2, 0, 1)
img = torch.from_numpy(img)
img = img[[2, 1, 0], ...].float()
mean = torch.tensor([123.5, 116.5, 103.5]).view(-1, 1, 1)
std = torch.tensor([58.5, 57.0, 57.5]).view(-1, 1, 1)
img = (img - mean) / std
return img.unsqueeze(0)
def post_process_normal(result, original_shape):
if result.dim() == 3:
result = result.unsqueeze(0)
elif result.dim() == 4:
pass
else:
raise ValueError(f"Unexpected result dimension: {result.dim()}")
seg_logits = F.interpolate(result, size=original_shape, mode="bilinear", align_corners=False).squeeze(0)
normal_map = seg_logits.float().cpu().numpy().transpose(1, 2, 0) # H x W x 3
return normal_map
def visualize_normal(normal_map):
normal_map_norm = np.linalg.norm(normal_map, axis=-1, keepdims=True)
normal_map_normalized = normal_map / (normal_map_norm + 1e-5) # Add a small epsilon to avoid division by zero
normal_map_vis = ((normal_map_normalized + 1) / 2 * 255).astype(np.uint8)
normal_map_vis = normal_map_vis[:, :, ::-1] # RGB to BGR
return normal_map_vis
def process_image_or_video(input_data, task='normal', version='sapiens_0.3b'):
model, device = load_model(task, version)
if model is None or device is None:
return None
input_shape = (3, 1024, 768)
def process_frame(frame):
if isinstance(frame, Image.Image):
frame = np.array(frame)
if frame.shape[2] == 4: # RGBA
frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2RGB)
img = preprocess_image(frame, input_shape)
with torch.no_grad():
result = model(img.to(device))
normal_map = post_process_normal(result, (frame.shape[0], frame.shape[1]))
normal_image = visualize_normal(normal_map)
return Image.fromarray(cv2.cvtColor(normal_image, cv2.COLOR_BGR2RGB))
if isinstance(input_data, np.ndarray): # Video frame
return process_frame(input_data)
elif isinstance(input_data, Image.Image): # Imagen
return process_frame(input_data)
else:
print("Tipo de entrada no soportado. Por favor, proporcione una imagen PIL o un frame de video numpy.")
return None |