柚子快報(bào)邀請(qǐng)碼778899分享：Numpy實(shí)現(xiàn)Conv2D

http://yzkb.51969.com/

self.stride = stride

self.input_shape = input_shape

self.trainable = True

def initialize(self, optimizer):

Initialize the weights

filter_height, filter_width = self.filter_shape

channels = self.input_shape[0]

limit = 1 / math.sqrt(np.prod(self.filter_shape))

self.W = np.random.uniform(-limit, limit, size=(self.n_filters, channels, filter_height, filter_width))

self.w0 = np.zeros((self.n_filters, 1))

Weight optimizers

self.W_opt = copy.copy(optimizer)

self.w0_opt = copy.copy(optimizer)

def parameters(self):

return np.prod(self.W.shape) + np.prod(self.w0.shape)

def forward_pass(self, X, training=True):

batch_size, channels, height, width = X.shape

self.layer_input = X

Turn image shape into column shape

(enables dot product between input and weights)

self.X_col = image_to_column(X, self.filter_shape, stride=self.stride, output_shape=self.padding)

Turn weights into column shape

self.W_col = self.W.reshape((self.n_filters, -1))

Calculate output

output = self.W_col.dot(self.X_col) + self.w0

Reshape into (n_filters, out_height, out_width, batch_size)

output = output.reshape(self.output_shape() + (batch_size, ))

Redistribute axises so that batch size comes first

return output.transpose(3,0,1,2)

def backward_pass(self, accum_grad):

Reshape accumulated gradient into column shape

accum_grad = accum_grad.transpose(1, 2, 3, 0).reshape(self.n_filters, -1)

if self.trainable:

Take dot product between column shaped accum. gradient and column shape

layer input to determine the gradient at the layer with respect to layer weights

grad_w = accum_grad.dot(self.X_col.T).reshape(self.W.shape)

The gradient with respect to bias terms is the sum similarly to in Dense layer

grad_w0 = np.sum(accum_grad, axis=1, keepdims=True)

Update the layers weights

self.W = self.W_opt.update(self.W, grad_w)

self.w0 = self.w0_opt.update(self.w0, grad_w0)

Recalculate the gradient which will be propogated back to prev. layer

accum_grad = self.W_col.T.dot(accum_grad)

Reshape from column shape to image shape

accum_grad = column_to_image(accum_grad,

self.layer_input.shape,

self.filter_shape,

stride=self.stride,

output_shape=self.padding)

return accum_grad 自我介紹一下，小編13年上海交大畢業(yè)，曾經(jīng)在小公司待過(guò)，也去過(guò)華為、OPPO等大廠，18年進(jìn)入阿里一直到現(xiàn)在。

深知大多數(shù)Python工程師，想要提升技能，往往是自己摸索成長(zhǎng)或者是報(bào)班學(xué)習(xí)，但對(duì)于培訓(xùn)機(jī)構(gòu)動(dòng)則幾千的學(xué)費(fèi)，著實(shí)壓力不小。自己不成體系的自學(xué)效果低效又漫長(zhǎng)，而且極易碰到天花板技術(shù)停滯不前！

因此收集整理了一份《2024年P(guān)ython開(kāi)發(fā)全套學(xué)習(xí)資料》，初衷也很簡(jiǎn)單，就是希望能夠幫助到想自學(xué)提升又不知道該從何學(xué)起的朋友，同時(shí)減輕大家的負(fù)擔(dān)。

既有適合小白學(xué)習(xí)的零基礎(chǔ)資料，也有適合3年以上經(jīng)驗(yàn)的小伙伴深入學(xué)習(xí)提升的進(jìn)階課程，基本涵蓋了95%以上前端開(kāi)發(fā)知識(shí)點(diǎn)，真正體系化！

由于文件比較大，這里只是將部分目錄大綱截圖出來(lái)，每個(gè)節(jié)點(diǎn)里面都包含大廠面經(jīng)、學(xué)習(xí)筆記、源碼講義、實(shí)戰(zhàn)項(xiàng)目、講解視頻，并且后續(xù)會(huì)持續(xù)更新

如果你覺(jué)得這些內(nèi)容對(duì)你有幫助，可以?huà)叽a獲?。。。。▊渥ython）

%以上前端開(kāi)發(fā)知識(shí)點(diǎn)，真正體系化！**

由于文件比較大，這里只是將部分目錄大綱截圖出來(lái)，每個(gè)節(jié)點(diǎn)里面都包含大廠面經(jīng)、學(xué)習(xí)筆記、源碼講義、實(shí)戰(zhàn)項(xiàng)目、講解視頻，并且后續(xù)會(huì)持續(xù)更新

如果你覺(jué)得這些內(nèi)容對(duì)你有幫助，可以?huà)叽a獲取?。。。▊渥ython）

柚子快報(bào)邀請(qǐng)碼778899分享：Numpy實(shí)現(xiàn)Conv2D

http://yzkb.51969.com/

好文閱讀