wangtong/rscder-pub
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fixed bugs mentioned in update-0503.xlsx

Browse Source
This commit is contained in:
陈逸飞 2023-07-05 17:14:26 +08:00
parent 5c2e6f4e73
commit fde841c037
6 changed files with 120 additions and 108 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
plugins/ai_method/basic_cd.py
View File

@ -125,16 +125,24 @@ class BasicAICD(AlgFrontend):
block_size = (xsize, cell_size[1]) block_size = (xsize, cell_size[1])
if block_xy[1] + block_size[1] > ysize: if block_xy[1] + block_size[1] > ysize:
block_size = (xsize, ysize - block_xy[1]) block_size = (xsize, ysize - block_xy[1])
np.seterr(divide='ignore',invalid='ignore')
block_data = temp_in_ds.ReadAsArray(*block_xy, *block_size) block_data = temp_in_ds.ReadAsArray(*block_xy, *block_size)
max_diff=block_data.max()
min_diff=block_data.min()
block_data = (block_data - min_diff) / (max_diff - min_diff) * 255 block_data = (block_data - min_diff) / (max_diff - min_diff) * 255
block_data = block_data.astype(np.uint8) block_data = block_data.astype(np.uint8)
out_normal_ds.GetRasterBand(1).WriteArray(block_data, *block_xy) out_normal_ds.GetRasterBand(1).WriteArray(block_data, *block_xy)
# os.system('pause')
# hist_t, _ = np.histogram(block_data, bins=256, range=(0, 256)) # hist_t, _ = np.histogram(block_data, bins=256, range=(0, 256))
# hist += hist_t # hist += hist_t
# print(hist) # print(hist)
del temp_in_ds del temp_in_ds
del out_normal_ds del out_normal_ds
try: try:
# os.system('pause')
os.remove(out_tif) os.remove(out_tif)
except: except:
pass pass

25
plugins/evaluation/main.py
View File

@ -144,7 +144,8 @@ class EvaluationPlugin(BasicPlugin):
for k in range(2): for k in range(2):
for l in range(2): for l in range(2):
cfm[k,l] += np.sum((pred_block == k) & (gt_block >= l)) # cfm[k,l] += np.sum((pred_block == k) & (gt_block >= l))
cfm[k,l] += np.sum((pred_block == k) & (gt_block == l))
result_path = os.path.join(Project().other_path, f'{layer.name}_{os.path.basename(gt)}_evaluation.txt') result_path = os.path.join(Project().other_path, f'{layer.name}_{os.path.basename(gt)}_evaluation.txt')
with open(result_path, 'w', encoding='utf-8') as f: with open(result_path, 'w', encoding='utf-8') as f:
@ -169,7 +170,7 @@ class EvaluationPlugin(BasicPlugin):
Kappa: {kappa(cfm)} Kappa: {kappa(cfm)}
''') ''')
f.flush() f.flush()
# os.system('pause')
txt=f''' txt=f'''
预测结果：{layer.path}\n 预测结果：{layer.path}\n
@ -194,11 +195,12 @@ class EvaluationPlugin(BasicPlugin):
Kappa: {kappa(cfm)} Kappa: {kappa(cfm)}
''' '''
self.msgbox = Win(txt) # self.msgbox = Win(txt)
self.msgbox.show() # self.msgbox.show()
# os.system(f'c:/windows/notepad.exe "{result_path}"') # os.system(f'c:/windows/notepad.exe "{result_path}"')
# self.send_message.emit('精度评估完成') self.send_message.emit('精度评估完成,结果保存在'+result_path)
def show_dialog(self): def show_dialog(self):
dialog = EvalutationDialog(self.mainwindow) dialog = EvalutationDialog(self.mainwindow)
@ -212,10 +214,13 @@ class EvaluationPlugin(BasicPlugin):
t.start() t.start()
from .window import Ui_Form from .window import Ui_Form
class Win(QWidget,Ui_Form): # class Win(QWidget,Ui_Form):
# def __init__(self,txt):
# super().__init__()
# self.setupUi(self)
# self.label.setText(txt)
def __init__(self,txt):
super().__init__()
self.setupUi(self)
self.label.setText(txt)

53
plugins/export_to/main.py
View File

@ -138,7 +138,7 @@ class ExportPlugin(BasicPlugin):
[1, 255, 0, 0] [1, 255, 0, 0]
] ]
if self.style_path is '': if self.style_path == '':
style = default_style style = default_style
else: else:
style = np.loadtxt(self.style_path, comments='#', delimiter=',') style = np.loadtxt(self.style_path, comments='#', delimiter=',')
@ -160,27 +160,42 @@ class ExportPlugin(BasicPlugin):
# TODO: check data range is 0-1 # TODO: check data range is 0-1
def get_color(v): def get_color(v):
first_color = [] # first_color = []
second_color = [] # second_color = []
first_value = 0 # first_value = 0
second_value = 1 # second_value = 1
for s in style: # for s in style:
if s[0] <= v: # if s[0] <= v:
first_value = s[0] # first_value = s[0]
first_color = s[1:] # first_color = s[1:]
else: # else:
second_value = s[0] # second_value = s[0]
second_color = s[1:] # second_color = s[1:]
break # break
if second_value == 1: # if second_value == 1:
return np.array(style[-1][1:]) # return np.array(style[-1][1:])
# first_dis = (v - first_value) / (second_value - first_value)
# second_dis = (second_value - v) / (second_value - first_value)
# first_color = np.array(first_color)
# second_color = np.array(second_color)
# color = first_color* first_dis + second_color * second_dis
# return np.floor(color)
if v==0:
return np.array(style[-1][1:])
elif v==1:
return np.array(style[-2][1:])
else:
first_color =style[-1][1:]
second_color=style[-2][1:]
first_dis = (v - first_value) / (second_value - first_value)
second_dis = (second_value - v) / (second_value - first_value)
first_color = np.array(first_color) first_color = np.array(first_color)
second_color=np.array(second_color) second_color=np.array(second_color)
color = first_color* first_dis + second_color * second_dis color_inter=first_color*(1-v)+second_color*v
return np.floor(color) return color_inter
get_color = np.frompyfunc(get_color, nin=1, nout=1) get_color = np.frompyfunc(get_color, nin=1, nout=1)

63
plugins/filter_collection/lms_filter.py
View File

@ -13,46 +13,37 @@ from datetime import datetime
import numpy as np import numpy as np
import torch import torch
import torch.nn.functional as F import torch.nn.functional as F
def adaptiveMedianDeNoise(count, original): import cv2
# 初始窗口大小 from tqdm import tqdm
startWindow = 3 def adaptiveMedianDeNoise(count, image):
# 卷积范围 origen = 3 # 初始窗口大小
c = count // 2 board = origen//2 # 初始应扩充的边界
rows, cols = original.shape # max_board = max_size//2 # 最大可扩充的边界
newI = np.zeros(original.shape) copy = cv2.copyMakeBorder(image, *[board]*4, borderType=cv2.BORDER_DEFAULT) # 扩充边界
# median = out_img = np.zeros(image.shape)
for i in tqdm(range(image.shape[0])):
for i in range(c, rows - c): for j in range(image.shape[1]):
for j in range(c, cols - c): def sub_func(src, size): # 两个层次的子函数
startWindow = 3 kernel = src[i:i+size, j:j+size]
k = int(startWindow / 2) # print(kernel)
median = np.median(original[i - k:i + k + 1, j - k:j + k + 1]) z_med = np.median(kernel)
mi = np.min(original[i - k:i + k + 1, j - k:j + k + 1]) z_max = np.max(kernel)
ma = np.max(original[i - k:i + k + 1, j - k:j + k + 1]) z_min = np.min(kernel)
if mi < median < ma: if z_min < z_med < z_max: # 层次A
if mi < original[i, j] < ma: if z_min < image[i][j] < z_max: # 层次B
newI[i, j] = original[i, j] return image[i][j]
else: else:
newI[i, j] = median return z_med
else: else:
while True: next_size = cv2.copyMakeBorder(src, *[1]*4, borderType=cv2.BORDER_DEFAULT) # 增尺寸
startWindow = startWindow + 2 size = size+2 # 奇数的核找中值才准确
k = int(startWindow / 2) if size <= count:
median = np.median(original[i - k:i + k + 1, j - k:j + k + 1]) return sub_func(next_size, size) # 重复层次A
mi = np.min(original[i - k:i + k + 1, j - k:j + k + 1])
ma = np.max(original[i - k:i + k + 1, j - k:j + k + 1])
if mi < median < ma or startWindow >= count:
break
if mi < median < ma or startWindow > count:
if mi < original[i, j] < ma:
newI[i, j] = original[i, j]
else: else:
newI[i, j] = median return z_med
out_img[i][j] = sub_func(copy, origen)
return newI return out_img
@FILTER.register @FILTER.register
class AdaptiveFilter(AlgFrontend): class AdaptiveFilter(AlgFrontend):

63
plugins/filter_collection/lmsnp_filter.py
View File

@ -13,45 +13,38 @@ from datetime import datetime
import numpy as np import numpy as np
import torch import torch
import torch.nn.functional as F import torch.nn.functional as F
def adaptiveMedianDeNoise(count, original): import pandas as pd
# 初始窗口大小 import cv2
startWindow = 3 from tqdm import tqdm
# 卷积范围 def adaptiveMedianDeNoise(count, image):
c = count // 2 origen = 3 # 初始窗口大小
rows, cols = original.shape board = origen//2 # 初始应扩充的边界
newI = np.zeros(original.shape) # max_board = max_size//2 # 最大可扩充的边界
# median = copy = cv2.copyMakeBorder(image, *[board]*4, borderType=cv2.BORDER_DEFAULT) # 扩充边界
out_img = np.zeros(image.shape)
for i in range(c, rows - c): for i in tqdm(range(image.shape[0])):
for j in range(c, cols - c): for j in range(image.shape[1]):
k = int(startWindow / 2) def sub_func(src, size): # 两个层次的子函数
median = np.median(original[i - k:i + k + 1, j - k:j + k + 1]) kernel = src[i:i+size, j:j+size]
mi = np.min(original[i - k:i + k + 1, j - k:j + k + 1]) # print(kernel)
ma = np.max(original[i - k:i + k + 1, j - k:j + k + 1]) z_med = np.median(kernel)
if mi < median < ma: z_max = np.max(kernel)
if mi < original[i, j] < ma: z_min = np.min(kernel)
newI[i, j] = original[i, j] if z_min < z_med < z_max: # 层次A
if z_min < image[i][j] < z_max: # 层次B
return image[i][j]
else: else:
newI[i, j] = median return z_med
else: else:
while True: next_size = cv2.copyMakeBorder(src, *[1]*4, borderType=cv2.BORDER_DEFAULT) # 增尺寸
startWindow = startWindow + 2 size = size+2 # 奇数的核找中值才准确
k = int(startWindow / 2) if size <= count:
median = np.median(original[i - k:i + k + 1, j - k:j + k + 1]) return sub_func(next_size, size) # 重复层次A
mi = np.min(original[i - k:i + k + 1, j - k:j + k + 1])
ma = np.max(original[i - k:i + k + 1, j - k:j + k + 1])
if mi < median < ma or startWindow >= count:
break
if mi < median < ma or startWindow >= count:
if mi < original[i, j] < ma:
newI[i, j] = original[i, j]
else: else:
newI[i, j] = median return z_med
out_img[i][j] = sub_func(copy, origen)
return newI return out_img
@FILTER.register @FILTER.register
class AdaptiveNPFilter(AlgFrontend): class AdaptiveNPFilter(AlgFrontend):

2
plugins/thres/main.py
View File

@ -138,7 +138,7 @@ class OTSUAlg(AlgFrontend):
band = ds.GetRasterBand(1) band = ds.GetRasterBand(1)
# band_count = ds.RasterCount # band_count = ds.RasterCount
hist = np.zeros(256, dtype=np.int) hist = np.zeros(256, dtype=np.int_)
xsize = ds.RasterXSize xsize = ds.RasterXSize
ysize = ds.RasterYSize ysize = ds.RasterYSize