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