Numpy實現(xiàn)卷積神經(jīng)網(wǎng)絡(luò)的方法？針對這個問題，這篇文章詳細(xì)介紹了相對應(yīng)的分析和解答，希望可以幫助更多想解決這個問題的小伙伴找到更簡單易行的方法。

創(chuàng)新互聯(lián)建站主營寧晉網(wǎng)站建設(shè)的網(wǎng)絡(luò)公司,主營網(wǎng)站建設(shè)方案,重慶APP開發(fā),寧晉h5微信小程序開發(fā)搭建,寧晉網(wǎng)站營銷推廣歡迎寧晉等地區(qū)企業(yè)咨詢

import numpy as np
import sys


def conv_(img, conv_filter):
  filter_size = conv_filter.shape[1]
  result = np.zeros((img.shape))
  # 循環(huán)遍歷圖像以應(yīng)用卷積運(yùn)算
  for r in np.uint16(np.arange(filter_size/2.0, img.shape[0]-filter_size/2.0+1)):
    for c in np.uint16(np.arange(filter_size/2.0, img.shape[1]-filter_size/2.0+1)):
      # 卷積的區(qū)域
      curr_region = img[r-np.uint16(np.floor(filter_size/2.0)):r+np.uint16(np.ceil(filter_size/2.0)),
             c-np.uint16(np.floor(filter_size/2.0)):c+np.uint16(np.ceil(filter_size/2.0))]
      # 卷積操作
      curr_result = curr_region * conv_filter
      conv_sum = np.sum(curr_result)
      # 將求和保存到特征圖中
      result[r, c] = conv_sum

    # 裁剪結(jié)果矩陣的異常值
  final_result = result[np.uint16(filter_size/2.0):result.shape[0]-np.uint16(filter_size/2.0),
          np.uint16(filter_size/2.0):result.shape[1]-np.uint16(filter_size/2.0)]
  return final_result


def conv(img, conv_filter):
  # 檢查圖像通道的數(shù)量是否與過濾器深度匹配
  if len(img.shape) > 2 or len(conv_filter.shape) > 3:
    if img.shape[-1] != conv_filter.shape[-1]:
      print("錯誤：圖像和過濾器中的通道數(shù)必須匹配")
      sys.exit()

  # 檢查過濾器是否是方陣
  if conv_filter.shape[1] != conv_filter.shape[2]:
    print('錯誤：過濾器必須是方陣')
    sys.exit()

  # 檢查過濾器大小是否是奇數(shù)
  if conv_filter.shape[1] % 2 == 0:
    print('錯誤：過濾器大小必須是奇數(shù)')
    sys.exit()

  # 定義一個空的特征圖，用于保存過濾器與圖像的卷積輸出
  feature_maps = np.zeros((img.shape[0] - conv_filter.shape[1] + 1,
               img.shape[1] - conv_filter.shape[1] + 1,
               conv_filter.shape[0]))

  # 卷積操作
  for filter_num in range(conv_filter.shape[0]):
    print("Filter ", filter_num + 1)
    curr_filter = conv_filter[filter_num, :]

    # 檢查單個過濾器是否有多個通道。如果有，那么每個通道將對圖像進(jìn)行卷積。所有卷積的結(jié)果加起來得到一個特征圖。
    if len(curr_filter.shape) > 2:
      conv_map = conv_(img[:, :, 0], curr_filter[:, :, 0])
      for ch_num in range(1, curr_filter.shape[-1]):
        conv_map = conv_map + conv_(img[:, :, ch_num], curr_filter[:, :, ch_num])
    else:
      conv_map = conv_(img, curr_filter)
    feature_maps[:, :, filter_num] = conv_map
  return feature_maps


def pooling(feature_map, size=2, stride=2):
  # 定義池化操作的輸出
  pool_out = np.zeros((np.uint16((feature_map.shape[0] - size + 1) / stride + 1),
             np.uint16((feature_map.shape[1] - size + 1) / stride + 1),
             feature_map.shape[-1]))

  for map_num in range(feature_map.shape[-1]):
    r2 = 0
    for r in np.arange(0, feature_map.shape[0] - size + 1, stride):
      c2 = 0
      for c in np.arange(0, feature_map.shape[1] - size + 1, stride):
        pool_out[r2, c2, map_num] = np.max([feature_map[r: r+size, c: c+size, map_num]])
        c2 = c2 + 1
      r2 = r2 + 1
  return pool_out

新聞名稱：Numpy實現(xiàn)卷積神經(jīng)網(wǎng)絡(luò)的方法-創(chuàng)新互聯(lián)
文章網(wǎng)址：http://weahome.cn/article/cddded.html