Android 台灣中文網 › 標籤 › 二進制

標籤: 二進制

相關帖子	版塊	作者	回覆/查看	最後發表

In810更新為15WW_5_16B後 , SuperSU會出現二進制更新失敗	Android 綜合刷機	Sandersod 2014-7-18	4 2049	soon5182 2014-8-24 16:39
su二進制文件已過時	Android 綜合刷機	s10410727 2011-10-6	48 22219	s02864 2015-11-4 19:16
二進制文件無法更新！！	G8 HTC Wildfire	babyfatorz 2012-2-4	4 1480	babyfatorz 2012-3-8 21:45
ROOT 二進制檔案更新 - [!reward_solved!]	已解決或取消懸賞	k781123 2013-9-11	4 5052	k781123 2011-9-15 16:20
ROOT 二進制檔案更新	New HTC One	yen88822 2014-2-5	6 1377	nsx720321 2014-2-11 11:35
HTC NEW ONE SUPERSU二進制更新問題	New HTC One	傅宇豪 2014-2-20	3 1601	manboyhot 2014-2-20 23:35
一直出現二進制需要更新	HTC One M8	loveim 2016-7-22	3 1017	agu828 2016-8-8 01:18
HTC Butterfly 超級權限二進制如何更新問題	HTC Butterfly	zz0972797027 2016-11-26	3 1279	su378x87 2017-9-29 01:26
TWRP卡刷SUPERSU二進制檔無效	Galaxy S7/S7 Edge	chengddjack 2016-12-11	1 1053	chengddjack 2016-12-11 21:07
凌航Neo Forza DDR5-5600 24GB記憶體-非二進制容量入門新選擇，同樣給你強悍的超頻表現	電腦硬體週邊	johnuahuang 2023-7-10	0 2828	johnuahuang 2023-7-10 08:22
美光Crucial DDR5 Pro 6000 48GB kit記憶體-非二進制入門新選擇，超頻表現也大幅度提升	電腦硬體週邊	johnuahuang 2023-12-11	1 6779	balala 2024-3-17 16:19
威剛XPG LANCER BLADE RGB DDR5-6000 48GB kit記憶體-非二進制大容量，有RGB燈效加持，還有優質超頻表現！	電腦硬體週邊	johnuahuang 2024-1-26	0 3131	johnuahuang 2024-1-26 08:54

更多...

相關日誌

分享 rnn 八位元二進制加法: 嵐風 2021-7-9 11:55; import copy, numpy as np np.random.seed(0) # compute sigmoid nonlinearity def sigmoid(x): output = 1/(1+np.exp(-x)) return output # convert output of sigmoid function to its derivative def sigmoid_output_to_derivative(output): return output*(1-output) # training dataset generation int2binary = {} binary_dim = 8 largest_number = pow(2,binary_dim) binary = np.unpackbits(np.array( ,dtype=np.uint8).T,axis=1) for i in range(largest_number): int2binary = binary # input variables alpha = 0.3 input_dim = 2 hidden_dim = 16 output_dim = 1 # initialize neural network weights synapse_0 = 2*np.random.random((input_dim,hidden_dim)) - 1 synapse_1 = 2*np.random.random((hidden_dim,output_dim)) - 1 synapse_h = 2*np.random.random((hidden_dim,hidden_dim)) - 1 synapse_0_update = np.zeros_like(synapse_0) synapse_1_update = np.zeros_like(synapse_1) synapse_h_update = np.zeros_like(synapse_h) # training logic for j in range(10000): # generate a simple addition problem (a + b = c) a_int = np.random.randint(largest_number/2) # int version a = int2binary # binary encoding b_int = np.random.randint(largest_number/2) # int version b = int2binary # binary encoding # true answer c_int = a_int + b_int c = int2binary # where we"ll store our best guess (binary encoded) d = np.zeros_like(c) overallError = 0 layer_2_deltas = list() layer_1_values = list() layer_1_values.append(np.zeros(hidden_dim)) # moving along the positions in the binary encoding for position in range(binary_dim): # generate input and output X = np.array( ,b ]]) y = np.array( ]]).T # hidden layer (input ~+ prev_hidden) layer_1 = sigmoid(np.dot(X,synapse_0) + np.dot(layer_1_values ,synapse_h)) # output layer (new binary representation) layer_2 = sigmoid(np.dot(layer_1,synapse_1)) # did we miss?... if so by how much? layer_2_error = y - layer_2 layer_2_deltas.append((layer_2_error)*sigmoid_output_to_derivative(layer_2)) overallError += np.abs(layer_2_error ) # decode estimate so we can print it out d = np.round(layer_2 ) # store hidden layer so we can use it in the next timestep layer_1_values.append(copy.deepcopy(layer_1)) future_layer_1_delta = np.zeros(hidden_dim) for position in range(binary_dim): X = np.array( ,b ]]) layer_1 = layer_1_values prev_layer_1 = layer_1_values # error at output layer layer_2_delta = layer_2_deltas # error at hidden layer layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + layer_2_delta.dot(synapse_1.T)) * sigmoid_output_to_derivative(layer_1) # let"s update all our weights so we can try again synapse_1_update += np.atleast_2d(layer_1).T.dot(layer_2_delta) synapse_h_update += np.atleast_2d(prev_layer_1).T.dot(layer_1_delta) synapse_0_update += X.T.dot(layer_1_delta) future_layer_1_delta = layer_1_delta synapse_0 += synapse_0_update * alpha synapse_1 += synapse_1_update * alpha synapse_h += synapse_h_update * alpha synapse_0_update *= 0 synapse_1_update *= 0 synapse_h_update *= 0 # print out progress if(j % 1000 == 0): print("誤差： "+str(overallError)) print("預測： "+str(d)) print("實際： "+str(c)) out = 0 for index,x in enumerate(reversed(d)): out += x*pow(2,index) print(str(a_int) + " + " + str(b_int) + " = " + str(out)) print("------------"); 116 次閱讀|0 個評論

更多...

標籤: 二進制

相關帖子

相關日誌

警告：您的Adblck已啟用