瀏覽代碼

autoshape() update for PIL greyscale inputs (#1279)

* autoshape update for PIL greyscale inputs

* autoshape update for PIL greyscale inputs
5.0
Glenn Jocher GitHub 4 年之前
父節點
當前提交
15a10609fe
沒有發現已知的金鑰在資料庫的簽署中 GPG 金鑰 ID: 4AEE18F83AFDEB23
共有 1 個檔案被更改,包括 3 行新增1 行删除
  1. +3
    -1
      models/common.py

+ 3
- 1
models/common.py 查看文件

@@ -1,6 +1,7 @@
# This file contains modules common to various models

import math

import numpy as np
import torch
import torch.nn as nn
@@ -144,7 +145,8 @@ class autoShape(nn.Module):
shape0, shape1 = [], [] # image and inference shapes
batch = range(len(x)) # batch size
for i in batch:
x[i] = np.array(x[i])[:, :, :3] # up to 3 channels if png
x[i] = np.array(x[i]) # to numpy
x[i] = x[i][:, :, :3] if x[i].ndim == 3 else np.tile(x[i][:, :, None], 3) # enforce 3ch input
s = x[i].shape[:2] # HWC
shape0.append(s) # image shape
g = (size / max(s)) # gain

Loading…
取消
儲存