小编Deb*_*eba的帖子

安装软件时,我的终端收到了一条消息: You are using pip version 8.1.1, however version 10.0.0 is available. You should consider upgrading via the 'pip install --upgrade pip' command.

所以我升级了pip版本: $ pip install --upgrade pip

现在我收到此错误:

~$ pip install ipython
Traceback (most recent call last):
  File "/usr/bin/pip", line 9, in <module>
    from pip import main
ImportError: cannot import name main

当我在Ubuntu 16.04中键入以下命令时

$ pip install mysqlclient

我收到以下错误:

`enter code here`Collecting mysqlclient
  Downloading https://files.pythonhosted.org/packages/6f/86/bad31f1c1bb0cc99e88ca2adb7cb5c71f7a6540c1bb001480513de76a931/mysqlclient-1.3.12.tar.gz (89kB)
    100% |????????????????????????????????| 92kB 136kB/s 
    Complete output from command python setup.py egg_info:
    /bin/sh: 1: mysql_config: not found
    Traceback (most recent call last):
      File "<string>", line 1, in <module>
      File "/tmp/pip-install-fs0wmmw4/mysqlclient/setup.py", line 17, in <module>
        metadata, options = get_config()
      File "/tmp/pip-install-fs0wmmw4/mysqlclient/setup_posix.py", line 44, in get_config
        libs = mysql_config("libs_r")
      File "/tmp/pip-install-fs0wmmw4/mysqlclient/setup_posix.py", line 26, in mysql_config
        raise EnvironmentError("%s not found" % (mysql_config.path,))
    OSError: mysql_config not found

    ----------------------------------------
Command "python setup.py …

根据Keras的骰子系数损失函数的实现，损失为骰子系数计算值的负值。损失应该随着时期的减少而减少，但是通过这种实现，我自然会总是得到负损失，并且损失随着时期的减少而减少，即从0移向负无穷大，而不是接近于0。如果我使用（1-骰子co-eff）而不是（-dice co-eff）作为损失，这是错误的吗？ 这是完整的Keras实现（我正在谈论）：https : //github.com/jocicmarko/ultrasound-nerve-segmentation/blob/master/train.py

smooth = 1.

def dice_coef(y_true, y_pred):
    y_true_f = K.flatten(y_true)
    y_pred_f = K.flatten(y_pred)
    intersection = K.sum(y_true_f * y_pred_f)
    return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)


def dice_coef_loss(y_true, y_pred):
return -dice_coef(y_true, y_pred)

我已经与您分享了我的实验日志，尽管仅记录了2个纪元：

Train on 2001 samples, validate on 501 samples
Epoch 1/2
Epoch 00001: loss improved from inf to -0.73789, saving model to unet.hdf5
 - 3229s - loss: -7.3789e-01 - dice_coef: 0.7379 - val_loss: -7.9304e-01 - val_dice_coef: 0.7930
Epoch …