小编Rya*_*an 的帖子

我正在尝试运行 cv2，当我尝试导入它时，我得到了

ImportError: libGL.so.1: cannot open shared object file: No such file or directory

在线建议的解决方案是安装

apt install libgl1-mesa-glx

但这已经安装并且是最新版本。任何帮助都会非常有帮助。提前致谢。

我正在运行Keras模型,提交截止日期为36小时,如果我在cpu上训练我的模型需要大约50个小时,有没有办法在gpu上运行Keras？

我正在使用Tensorflow后端并在我的Jupyter笔记本上运行它,没有安装anaconda.

我试图从我训练过的模型中保存和加载重量.

用于保存模型的代码是.

TensorBoard(log_dir='/output')
model.fit_generator(image_a_b_gen(batch_size), steps_per_epoch=1, epochs=1)
model.save_weights('model.hdf5')
model.save_weights('myModel.h5')

如果这是一种不正确的方式,或者是否有更好的方法,请告诉我.

但当我尝试加载它们时,使用它,

from keras.models import load_model
model = load_model('myModel.h5')

但我得到这个错误:

ValueError                                Traceback (most recent call 
last)
<ipython-input-7-27d58dc8bb48> in <module>()
      1 from keras.models import load_model
----> 2 model = load_model('myModel.h5')

/home/decentmakeover2/anaconda3/lib/python3.5/site-
packages/keras/models.py in load_model(filepath, custom_objects, compile)
    235         model_config = f.attrs.get('model_config')
    236         if model_config is None:
--> 237             raise ValueError('No model found in config file.')
    238         model_config = json.loads(model_config.decode('utf-8'))
    239         model = model_from_config(model_config, 
custom_objects=custom_objects)

ValueError: No model found in config file.

关于我可能做错什么的任何建议？先感谢您.

我试图运行keras模型,尝试使用预先训练的VGGnet-当我运行此命令 base_model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(img_rows, img_cols, img_channel))

我收到此错误:

  ``------------------------------------------------------------------
---------
ImportError                               Traceback (most recent call 
last)
<ipython-input-79-9b18deb3bc0f> in <module>()
  1 
----> 2 base_model = applications.VGG16(weights='imagenet', 
include_top=False, input_shape=(img_rows, img_cols, img_channel))

/usr/local/lib/python3.5/dist-packages/keras/applications/vgg16.py in 
VGG16(include_top, weights, input_tensor, input_shape, pooling, 
classes)
167                                     WEIGHTS_PATH_NO_TOP,
168                                     cache_subdir='models')
--> 169         model.load_weights(weights_path)
170         if K.backend() == 'theano':
171             layer_utils.convert_all_kernels_in_model(model)

/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py in 
load_weights(self, filepath, by_name)
   2563         """
   2564         if h5py is None:
-> 2565             raise ImportError('`load_weights` requires h5py.')
   2566         f = h5py.File(filepath, mode='r')
   2567         if 'layer_names' not in …

class torch.FloatStorage[source]
    byte()
        Casts this storage to byte type
    char()
        Casts this storage to char type

我正在尝试完成一些文档，我设法获得了如上所示的格式，但我不确定如何提供该函数末尾的源代码链接！该链接将人带到包含代码的文件，但我不知道该怎么做，

我有一个模型文件,看起来像这样

OrderedDict([('inp.conv1.conv.weight', 
          (0 ,0 ,0 ,.,.) = 
           -1.5073e-01  6.4760e-02  1.9156e-01
            1.2175e-01  3.5886e-02  1.3992e-01
           -1.5903e-01  8.2055e-02  1.7820e-01

          (0 ,0 ,1 ,.,.) = 
            1.0604e-01 -1.3653e-01  1.4803e-01
            6.0276e-02 -1.4674e-02  2.3059e-06
           -6.2192e-02 -5.1061e-03 -7.4145e-03

          (0 ,0 ,2 ,.,.) = 
           -5.5632e-02  3.5326e-02  6.5108e-02
            1.1411e-01 -4.4160e-02  8.2610e-02
            8.9979e-02 -3.5454e-02  4.2549e-02

          (1 ,0 ,0 ,.,.) = 
            4.8523e-02 -4.3961e-02  5.3614e-02
           -1.2644e-01  1.2777e-01  8.9547e-02
            3.8392e-02  2.7016e-02 -1.4552e-01

          (1 ,0 ,1 ,.,.) = 
            9.5537e-02  2.8748e-02  3.9772e-02
           -6.2410e-02  1.1264e-01  7.8663e-02
           -2.6374e-02  1.4401e-01 -1.7109e-01

          (1 ,0 ,2 ,.,.) = 
            5.1791e-02 -1.6388e-01 -1.7605e-01 …

我正在尝试训练一个网络，但我得到了，我将批量大小设置为 300，并且收到此错误，但即使我将其减少到 100，我仍然收到此错误，更令人沮丧的是，在 ~1200 个图像上运行 10 epoch大约需要 40 分钟，请提出问题所在以及如何加快该过程！任何提示都会非常有帮助，提前致谢。

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-31-3b43ff4eea72> in <module>()
      5         labels = Variable(labels).cuda()
      6 
----> 7         optimizer.zero_grad()
      8         outputs = cnn(images)
      9         loss = criterion(outputs, labels)

/usr/local/lib/python3.5/dist-packages/torch/optim/optimizer.py in     zero_grad(self)
    114                 if p.grad is not None:
    115                     if p.grad.volatile:
--> 116                         p.grad.data.zero_()
    117                     else:
    118                         data = p.grad.data

RuntimeError: cuda runtime error (2) : out of memory at /pytorch  /torch/lib/THC/generic/THCTensorMath.cu:35`

即使我的 GPU 是免费的

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.111                Driver Version: 384.111                       | …

尝试为多标签分类编写焦点损失

class FocalLoss(nn.Module):
    def __init__(self, gamma=2, alpha=0.25):
        self._gamma = gamma
        self._alpha = alpha

    def forward(self, y_true, y_pred):
        cross_entropy_loss = torch.nn.BCELoss(y_true, y_pred)
        p_t = ((y_true * y_pred) +
               ((1 - y_true) * (1 - y_pred)))
        modulating_factor = 1.0
        if self._gamma:
            modulating_factor = torch.pow(1.0 - p_t, self._gamma)
        alpha_weight_factor = 1.0
        if self._alpha is not None:
            alpha_weight_factor = (y_true * self._alpha +
                                   (1 - y_true) * (1 - self._alpha))
        focal_cross_entropy_loss = (modulating_factor * alpha_weight_factor *
                                    cross_entropy_loss)
        return focal_cross_entropy_loss.mean()

但是当我运行这个时，我得到

  File "train.py", line 82, …

我已经显示了下面的代码，但是当我尝试执行它时，得到

Traceback (most recent call last):
  File "/home/decentmakeover2/Code/cv.py", line 22, in <module>
    img = cv2.circle(img,center, radius, (0,255, 0), 2)
TypeError: integer argument expected, got float

我不确定问题是什么，minEnclosingCircle值已转换为int，但我仍然遇到相同的错误，关于可能是什么问题的任何想法？

import numpy as np
import cv2
import os
from scipy import ndimage

img = cv2.pyrDown(cv2.imread('img.jpeg'))
ret, thresh  = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY), 127, 255, cv2.THRESH_BINARY)
image, contours, heir = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

for c in contours:
    x, y , w, h = cv2.boundingRect(c)
    cv2.rectangle(img, (x,y), (x+w, y+h), (0, 255, 0), 2)

    rect …

我正在尝试解决一个回归问题，这是一个带有 8 个标签的多标签，我正在使用均方误差损失，但是数据集不平衡，我想将权重传递给损失函数。目前我正在编译这个模型道路。

model.compile(loss='mse', optimizer=Adam(lr=0.0001), metrics=['mse', 'acc'])

有人可以建议是否可以为均方误差添加权重，如果可以，我该怎么做？

提前致谢

标签看起来像这样

model = Sequential()    
model.add(effnet)
model.add(GlobalAveragePooling2D())
model.add(Dropout(0.5))
model.add(Dense(8,name = 'nelu', activation=elu))
model.compile(loss=custom_mse(class_weights), 
optimizer=Adam(lr=0.0001), metrics=['mse', 'acc'])