小编Joe*_*Joe的帖子

我刚刚开始我的ML之旅并做了一些教程.有一点不清楚(对我来说)是如何为Keras Conv2D确定'过滤器'参数.

我读过的大多数资源都只是将参数设置为32而没有解释.这只是一个经验法则还是输入图像的尺寸起作用？例如,CIFAR-10中的图像是32x32

特别:

model = Sequential()
filters = 32
model.add(Conv2D(filters, (3, 3), padding='same', input_shape=x_train.shape[1:]))

model.add(Activation('relu'))
model.add(Conv2D(filters, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

下一层的过滤器参数为filter*2或64.再次,这是如何计算的？

TX.

乔

我能够在我的Mac上成功安装OpenCV Wheel,但是当我尝试导入模块时,我收到以下错误:

(python35) iMac > python
Python 3.5.4 |Anaconda custom (64-bit)| (default, Oct  5 2017, 
02:58:14) 
[GCC 4.2.1 Compatible Clang 4.0.1 (tags/RELEASE_401/final)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import cv2`
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File 
"/Users/AntoliMac01/Anaconda/anaconda/envs/python35/lib/python3.5/site-packages/cv2/__init__.py", line 4, in <module>
    from .cv2 import *
ImportError: dlopen(/Users/AntoliMac01/Anaconda/anaconda/envs/python35/lib/python3.5/site-packages/cv2/cv2.cpython-35m-darwin.so, 2): Library not loaded: /System/Library/Frameworks/CoreImage.framework/Versions/A/CoreImage
  Referenced from: /Users/AntoliMac01/Anaconda/anaconda/envs/python35/lib/python3.5/site-packages/cv2/.dylibs/libavcodec.57.107.100.dylib
  Reason: image not found
>>> `

我从这个网站下载了这个轮子.

OS版本:

(python35) …