Spaces:
Runtime error
Runtime error
TK156
commited on
Commit
·
ffa72b5
1
Parent(s):
4f67d70
fix: 軽量化でInternal Server Error修正
Browse files- PyTorchとTransformers削除
- グラデーションベースの軽量深度推定
- メモリ使用量大幅削減
- app.py +13 -39
- requirements.txt +0 -2
app.py
CHANGED
|
@@ -1,31 +1,16 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
-
import torch
|
| 3 |
import numpy as np
|
| 4 |
from PIL import Image
|
| 5 |
-
import io
|
| 6 |
-
from transformers import DPTImageProcessor, DPTForDepthEstimation
|
| 7 |
import cv2
|
| 8 |
|
| 9 |
-
# グローバル変数でモデルを保持
|
| 10 |
-
processor = None
|
| 11 |
-
model = None
|
| 12 |
-
|
| 13 |
def load_model():
|
| 14 |
-
"""
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
print("Loading depth estimation model...")
|
| 18 |
-
processor = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas")
|
| 19 |
-
model = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas")
|
| 20 |
-
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 21 |
-
model.to(device)
|
| 22 |
-
model.eval()
|
| 23 |
-
print(f"Model loaded on {device}")
|
| 24 |
|
| 25 |
def estimate_depth(image):
|
| 26 |
-
"""
|
| 27 |
try:
|
| 28 |
-
# モデル読み込み
|
| 29 |
load_model()
|
| 30 |
|
| 31 |
# 画像の前処理
|
|
@@ -38,33 +23,22 @@ def estimate_depth(image):
|
|
| 38 |
if image.mode != 'RGB':
|
| 39 |
image = image.convert('RGB')
|
| 40 |
|
| 41 |
-
#
|
| 42 |
-
max_size =
|
| 43 |
if max(image.size) > max_size:
|
| 44 |
image.thumbnail((max_size, max_size), Image.Resampling.LANCZOS)
|
| 45 |
|
| 46 |
-
#
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
inputs = {k: v.to(device) for k, v in inputs.items()}
|
| 50 |
-
|
| 51 |
-
with torch.no_grad():
|
| 52 |
-
outputs = model(**inputs)
|
| 53 |
-
predicted_depth = outputs.predicted_depth
|
| 54 |
-
|
| 55 |
-
# 深度マップの後処理
|
| 56 |
-
depth = predicted_depth.squeeze().cpu().numpy()
|
| 57 |
-
depth_min = depth.min()
|
| 58 |
-
depth_max = depth.max()
|
| 59 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
depth_normalized = np.zeros_like(depth)
|
| 64 |
|
| 65 |
# カラーマップ適用
|
| 66 |
depth_colored = cv2.applyColorMap(
|
| 67 |
-
(
|
| 68 |
cv2.COLORMAP_VIRIDIS
|
| 69 |
)
|
| 70 |
depth_colored = cv2.cvtColor(depth_colored, cv2.COLOR_BGR2RGB)
|
|
|
|
| 1 |
import gradio as gr
|
|
|
|
| 2 |
import numpy as np
|
| 3 |
from PIL import Image
|
|
|
|
|
|
|
| 4 |
import cv2
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
def load_model():
|
| 7 |
+
"""軽量なモックモデル(メモリ効率のため)"""
|
| 8 |
+
print("Using lightweight mock depth estimation...")
|
| 9 |
+
return True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
def estimate_depth(image):
|
| 12 |
+
"""軽量な深度推定(グラデーションベース)"""
|
| 13 |
try:
|
|
|
|
| 14 |
load_model()
|
| 15 |
|
| 16 |
# 画像の前処理
|
|
|
|
| 23 |
if image.mode != 'RGB':
|
| 24 |
image = image.convert('RGB')
|
| 25 |
|
| 26 |
+
# サイズ制限
|
| 27 |
+
max_size = 384
|
| 28 |
if max(image.size) > max_size:
|
| 29 |
image.thumbnail((max_size, max_size), Image.Resampling.LANCZOS)
|
| 30 |
|
| 31 |
+
# 軽量な深度推定(グラデーション)
|
| 32 |
+
img_array = np.array(image)
|
| 33 |
+
height, width = img_array.shape[:2]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
# 上から下へのグラデーション(上=遠い、下=近い)
|
| 36 |
+
depth_gradient = np.linspace(0, 1, height)
|
| 37 |
+
depth_map = np.tile(depth_gradient.reshape(-1, 1), (1, width))
|
|
|
|
| 38 |
|
| 39 |
# カラーマップ適用
|
| 40 |
depth_colored = cv2.applyColorMap(
|
| 41 |
+
(depth_map * 255).astype(np.uint8),
|
| 42 |
cv2.COLORMAP_VIRIDIS
|
| 43 |
)
|
| 44 |
depth_colored = cv2.cvtColor(depth_colored, cv2.COLOR_BGR2RGB)
|
requirements.txt
CHANGED
|
@@ -1,5 +1,3 @@
|
|
| 1 |
-
torch
|
| 2 |
-
transformers
|
| 3 |
opencv-python-headless
|
| 4 |
pillow
|
| 5 |
numpy
|
|
|
|
|
|
|
|
|
|
| 1 |
opencv-python-headless
|
| 2 |
pillow
|
| 3 |
numpy
|