cnn.py cs231n

Posted

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了cnn.py cs231n相关的知识,希望对你有一定的参考价值。

n

import numpy as np

from cs231n.layers import *
from cs231n.fast_layers import *
from cs231n.layer_utils import *


class ThreeLayerConvNet(object):
  """
  A three-layer convolutional network with the following architecture:
  
  conv - relu - 2x2 max pool - affine - relu - affine - softmax
  
  The network operates on minibatches of data that have shape (N, C, H, W)
  consisting of N images, each with height H and width W and with C input
  channels.
  """
  
  def __init__(self, input_dim=(3, 32, 32), num_filters=32, filter_size=7,
               hidden_dim=100, num_classes=10, weight_scale=1e-3, reg=0.0,
               dtype=np.float32):
    """
    Initialize a new network.
    
    Inputs:
    - input_dim: Tuple (C, H, W) giving size of input data
    - num_filters: Number of filters to use in the convolutional layer
    - filter_size: Size of filters to use in the convolutional layer
    - hidden_dim: Number of units to use in the fully-connected hidden layer
    - num_classes: Number of scores to produce from the final affine layer.
    - weight_scale: Scalar giving standard deviation for random initialization
      of weights.
    - reg: Scalar giving L2 regularization strength
    - dtype: numpy datatype to use for computation.
    """
    C,H,W=input_dim
    
    self.params = {}
    self.reg = reg
    self.dtype = dtype
    self.params[‘W1‘]=np.random.randn(num_filters,C,filter_size,filter_size)*weight_scale
    self.params[‘b1‘]=np.zeros(num_filters,)
    self.params[‘W2‘]=np.random.randn(num_filters*H*W/4,hidden_dim)*weight_scale
    self.params[‘b2‘]=np.zeros(hidden_dim,)
    self.params[‘W3‘]=np.random.randn(hidden_dim,num_classes)*weight_scale
    self.params[‘b3‘]=np.zeros(num_classes,)
    # why randn needs int while seros needs tuple!!!!
    for k, v in self.params.iteritems():
      self.params[k] = v.astype(dtype)
     
 
  def loss(self, X, y=None):
    """
    Evaluate loss and gradient for the three-layer convolutional network.
    
    Input / output: Same API as TwoLayerNet in fc_net.py.
    """
    W1, b1 = self.params[‘W1‘], self.params[‘b1‘]
    W2, b2 = self.params[‘W2‘], self.params[‘b2‘]
    W3, b3 = self.params[‘W3‘], self.params[‘b3‘]
    
    # pass conv_param to the forward pass for the convolutional layer
    filter_size = W1.shape[2]
    conv_param = {‘stride‘: 1, ‘pad‘: (filter_size - 1) / 2}

    # pass pool_param to the forward pass for the max-pooling layer
    pool_param = {‘pool_height‘: 2, ‘pool_width‘: 2, ‘stride‘: 2}

    scores = None
out1,cache1=conv_relu_pool_forward(X,W1,b1,conv_param,pool_param) out=out1.reshape(out1.shape[0],-1) out,cache2=affine_relu_forward(out,W2,b2) scores,cache3=affine_forward(out,W3,b3) if y is None: return scores loss, grads = 0, {}
loss,dout=softmax_loss(scores,y) loss+=self.reg*0.5*np.sum(W3**2) loss+=self.reg*0.5*np.sum(W2**2) loss+=self.reg*0.5*np.sum(W1**2) dout,grads[‘W3‘],grads[‘b3‘]=affine_backward(dout,cache3) grads[‘W3‘]+=W3*self.reg dout,grads[‘W2‘],grads[‘b2‘]=affine_relu_backward(dout,cache2) grads[‘W2‘]+=W2*self.reg dout=dout.reshape(*out1.shape) dout,grads[‘W1‘],grads[‘b1‘]=conv_relu_pool_backward(dout,cache1) grads[‘W1‘]+=W1*self.reg ############################################################################ # END OF YOUR CODE # ############################################################################ return loss, grads pass

  

n



以上是关于cnn.py cs231n的主要内容,如果未能解决你的问题,请参考以下文章

『cs231n』作业2选讲_通过代码理解卷积层&池化层

『cs231n』计算机视觉基础

『cs231n』作业2选讲_通过代码理解优化器

Python 代码CS231n中Softmax线性分类器非线性分类器对比举例(含python绘图显示结果)

『cs231n』无监督学习

[转] 贺完结!CS231n官方笔记授权翻译总集篇发布