這篇文章主要介紹了關於pytorch visdom 處理簡單分類問題,有著一定的參考價值,現在分享給大家,有需要的朋友可以參考一下
環境
系統: win 10
顯示卡:gtx965m
cpu :i7-6700HQ
python 3.61
pytorch 0.3
import torch from torch.autograd import Variable import torch.nn.functional as F import numpy as np import visdom import time from torch import nn,optim#資料準備 ##
use_gpu = True ones = np.ones((500,2)) x1 = torch.normal(6*torch.from_numpy(ones),2) y1 = torch.zeros(500) x2 = torch.normal(6*torch.from_numpy(ones*[-1,1]),2) y2 = y1 +1 x3 = torch.normal(-6*torch.from_numpy(ones),2) y3 = y1 +2 x4 = torch.normal(6*torch.from_numpy(ones*[1,-1]),2) y4 = y1 +3 x = torch.cat((x1, x2, x3 ,x4), 0).float() y = torch.cat((y1, y2, y3, y4), ).long()視覺化如下看一下:
visdom視覺化準備
##先建立需要觀察的windows
viz = visdom.Visdom() colors = np.random.randint(0,255,(4,3)) #颜色随机 #线图用来观察loss 和 accuracy line = viz.line(X=np.arange(1,10,1), Y=np.arange(1,10,1)) #散点图用来观察分类变化 scatter = viz.scatter( X=x, Y=y+1, opts=dict( markercolor = colors, marksize = 5, legend=["0","1","2","3"]),) #text 窗口用来显示loss 、accuracy 、时间 text = viz.text("FOR TEST") #散点图做对比 viz.scatter( X=x, Y=y+1, opts=dict( markercolor = colors, marksize = 5, legend=["0","1","2","3"] ), )#效果如下:
##邏輯迴歸處理
輸入2,輸出4
#logstic = nn.Sequential( nn.Linear(2,4) )
gpu還是cpu選擇:
if use_gpu: gpu_status = torch.cuda.is_available() if gpu_status: logstic = logstic.cuda() # net = net.cuda() print("###############使用gpu##############") else : print("###############使用cpu##############") else: gpu_status = False print("###############使用cpu##############")
優化器與loss函數:
#
loss_f = nn.CrossEntropyLoss() optimizer_l = optim.SGD(logstic.parameters(), lr=0.001)
訓練2000次:
#
start_time = time.time() time_point, loss_point, accuracy_point = [], [], [] for t in range(2000): if gpu_status: train_x = Variable(x).cuda() train_y = Variable(y).cuda() else: train_x = Variable(x) train_y = Variable(y) # out = net(train_x) out_l = logstic(train_x) loss = loss_f(out_l,train_y) optimizer_l.zero_grad() loss.backward() optimizer_l.step()
訓練過成觀察及視覺化:
#if t % 10 == 0: prediction = torch.max(F.softmax(out_l, 1), 1)[1] pred_y = prediction.data accuracy = sum(pred_y ==train_y.data)/float(2000.0) loss_point.append(loss.data[0]) accuracy_point.append(accuracy) time_point.append(time.time()-start_time) print("[{}/{}] | accuracy : {:.3f} | loss : {:.3f} | time : {:.2f} ".format(t + 1, 2000, accuracy, loss.data[0], time.time() - start_time)) viz.line(X=np.column_stack((np.array(time_point),np.array(time_point))), Y=np.column_stack((np.array(loss_point),np.array(accuracy_point))), win=line, opts=dict(legend=["loss", "accuracy"])) #这里的数据如果用gpu跑会出错,要把数据换成cpu的数据 .cpu()即可 viz.scatter(X=train_x.cpu().data, Y=pred_y.cpu()+1, win=scatter,name="add", opts=dict(markercolor=colors,legend=["0", "1", "2", "3"])) viz.text("<h3 align='center' style='color:blue'>accuracy : {}</h3><br><h3 align='center' style='color:pink'>" "loss : {:.4f}</h3><br><h3 align ='center' style='color:green'>time : {:.1f}</h3>" .format(accuracy,loss.data[0],time.time()-start_time),win =text)
#我的理解就是gpu在處理圖片識別大量矩陣運算等方面運算能力遠高於cpu,在處理一些輸入和輸出都很少的,還是cpu更具優勢。
###新增神經層:############net = nn.Sequential( nn.Linear(2, 10), nn.ReLU(), #激活函数 nn.Linear(10, 4) )#########新增一層10單元神經層,看看效果是否會有所提升: #########使用cpu:######### ##########使用gpu:##############比較觀察,似乎沒有什麼差別,看來處理簡單分類問題(輸入,輸出少)的問題,神經層和gpu不會對機器學習加持。 ######相關推薦:############PyTorch上搭建簡單神經網路實作迴歸與分類的範例###############詳解PyTorch批次訓練及最佳化器比較#################################
以上是pytorch + visdom 處理簡單分類問題的詳細內容。更多資訊請關注PHP中文網其他相關文章!