小编Dev*_*Dev的帖子

我对皮肤组织的多类分割感兴趣，我将 3000 个皮肤组织标签分为 4 个类别，我创建了一个 CNN 分类算法来训练我的分类模型。我想将分类模型用于新皮肤组织图像的分割任务，并对属于每个类的皮肤组织进行特征提取

以下是为训练我的分类模型而编写的代码

from tensorflow.keras.layers import Input, Concatenate, Dropout, Flatten, Dense, GlobalAveragePooling2D, Conv2D
from tensorflow.keras import backend as K
#from tensorflow.keras.utils import np_utils
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras import optimizers
from tensorflow.keras.metrics import top_k_categorical_accuracy
from tensorflow.keras.models import Sequential, Model, load_model
import tensorflow as tf
from tensorflow.keras.initializers import he_uniform
from tensorflow.keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard, EarlyStopping, CSVLogger, ReduceLROnPlateau
#from tensorflow.compat.keras.backend import KTF
#import keras.backend.tensorflow_backend as KTF
from tensorflow.keras.applications.resnet50 import ResNet50
from …

我想从 python 脚本启动 docker 容器。当我通过我的代码调用 docker 镜像时，我无法启动 docker 容器

import subprocess
import docker


from subprocess import Popen, PIPE


def kill_and_remove(ctr_name):
    for action in ('kill', 'rm'):
        p = Popen('docker %s %s' % (action, ctr_name), shell=True,
                  stdout=PIPE, stderr=PIPE)
        if p.wait() != 0:
            raise RuntimeError(p.stderr.read())


def execute():
    ctr_name = 'sml/tools:8' # docker image file name
    p = Popen(['docker', 'run', '-v','/lib/modules:/lib/modules',
               '--cap-add','NET_ADMIN','--name','o-9000','--restart',
               'always', ctr_name ,'startup',' --base-port',
               9000,' --orchestrator-integration-license',
               ' --orchestrator-integration-license','jaVl7qdgLyxo6WRY5ykUTWNRl7Y8IzJxhRjEUpKCC9Q='
               ,'--orchestrator-integration-mode'],
              stdin=PIPE)
    out = p.stdin.write('Something')

    if p.wait() == -20:  # Happens on timeout

        kill_and_remove(ctr_name) …

我有一个 U-Net 模型，带有来自自动编码器的预训练权重，自动编码器构建了包含 1400 张图像的图像数据集。我正在尝试使用临床数据集的 1400 个标记图像执行语义分割。该模型在我的测试图像数据集上表现良好iou_score=0.97，但是当我尝试在数据集之外的随机图像上测试它时，我得到了非常糟糕的分割结果。我不明白其中的原因。请检查我的代码并建议我哪里错了。

对我的数据集和标签进行训练：

import cv2
import numpy as np
from matplotlib import pyplot as plt
#########################################################################
#Load data for U-net training. 
#################################################################
import os

os.environ['CUDA_VISIBLE_DEVICES'] = '0'
os.environ["SM_FRAMEWORK"] = "tf.keras"
import glob
import cv2
import os
import numpy as np
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
train_images = []
#Resizing images is optional, CNNs are ok with large images
SIZE_X = 256 #Resize images (height  = X, width = …