圖神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)筆記 -1 | Windows10 CUDA亲轨、PaddlePaddle趋惨、PGL安裝

環(huán)境：Windows10，Anaconda瓶埋，CUDA10.0希柿，PaddlePaddle1.8.5

1诊沪、PaddlePaddle-GPU的依賴項(xiàng)：CUDA安裝

CUDA：CUDA英文全稱是Compute Unified Device Architecture养筒，是顯卡廠商N(yùn)VIDIA推出的運(yùn)算平臺曾撤。 CUDA?是一種由NVIDIA推出的通用并行計(jì)算架構(gòu)，該架構(gòu)使GPU能夠解決復(fù)雜的計(jì)算問題晕粪。按照官方的說法是挤悉，CUDA是一個并行計(jì)算平臺和編程模型，能夠使得使用GPU進(jìn)行通用計(jì)算變得簡單和優(yōu)雅（該解釋來源知乎）巫湘。

在Windows10上安裝深度學(xué)習(xí)框架PaddlePaddle（GPU版装悲，百度出品）前，需要安裝與框架版本相匹配的CUDA驅(qū)動尚氛，使用CMD查看當(dāng)前CUDA版本：

 C:\Users\WangYue>nvcc --version
# 報(bào)錯如下：
'nvcc' 不是內(nèi)部或外部命令诀诊，也不是可運(yùn)行的程序
或批處理文件。

表明本機(jī)尚未安裝CUDA驅(qū)動阅嘶。使用NVIDIA控制面板查看本機(jī)當(dāng)前使用的GPU支持的CUDA最高版本属瓣。順序?yàn)?strong>系統(tǒng)信息——組件——3D設(shè)置，本機(jī)為11.0.228讯柔。

圖1抡蛙，使用NVIDIA控制面板查看本機(jī)使用GPU支持的CUDA最高上限，本機(jī)為11.0.228

然后在NVIDIA官網(wǎng)下載所需版本的CUDA安裝包魂迄。
圖2粗截，選擇對應(yīng)版本的CUDA驅(qū)動，Installer Type選擇exe(local)

雙擊選擇安裝位置捣炬，開始安裝熊昌，以及簽署許可協(xié)議。
圖3湿酸，安裝中

關(guān)鍵的地方在于自定義安裝設(shè)置：
圖4婿屹，務(wù)必選擇自定義

選擇驅(qū)動程序組件的勾選方法如下：
（1）取消Visual Studio Integration；
（2）若當(dāng)前版本（452.11）比待安裝版本（411.31）高稿械，則取消Display Driver选泻。


圖5，選擇驅(qū)動程序組件

選擇安裝位置美莫，按照默認(rèn)路徑即可页眯。


圖6，選擇安裝位置厢呵，按照默認(rèn)路徑

圖7窝撵，安裝完畢

安裝完成后，使用CMD命令查看是否安裝成功襟铭÷捣睿可以看到短曾，已經(jīng)安裝成功了。 
C:\Users\WangYue>nvcc --version
#
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:04_Central_Daylight_Time_2018
Cuda compilation tools, release 10.0, V10.0.130

2赐劣、PaddlePaddle-GPU的依賴項(xiàng)：cudnn7.6.5安裝

cuDNN：是一個專門為深度學(xué)習(xí)計(jì)算設(shè)計(jì)的軟件庫嫉拐，里面提供了很多專門的計(jì)算函數(shù)，如卷積等魁兼。從上圖也可以看到婉徘，還有很多其他的軟件庫和中間件，包括實(shí)現(xiàn)c++ STL的thrust咐汞、實(shí)現(xiàn)gpu版本blas的cublas盖呼、實(shí)現(xiàn)快速傅里葉變換的cuFFT、實(shí)現(xiàn)稀疏矩陣運(yùn)算操作的cuSparse以及實(shí)現(xiàn)深度學(xué)習(xí)網(wǎng)絡(luò)加速的cuDNN等等化撕，具體細(xì)節(jié)可參閱GPU-Accelerated Libraries几晤。
根據(jù)PaddlePaddle安裝指南的提示，cuDNN>7.3都可以植阴，在這里選擇了V7.6.5蟹瘾。（需要注冊NVIDIA賬號才可以繼續(xù)下載）

圖8，選擇cuDNN Library for Windows10

隨后解壓壓縮文件墙贱，修改解壓出的文件夾的名稱热芹，由cuda改為cudnn，并將該文件夾移動到如圖所示路徑惨撇。
圖9伊脓，將改名后的cudnn文件夾移動到如圖所示路徑。

3魁衙、PaddlePaddle-GPU的依賴項(xiàng)：環(huán)境變量設(shè)置

首先私植，依次選擇：我的電腦——屬性——高級系統(tǒng)設(shè)置——系統(tǒng)變量——Path——編輯


圖10诀浪，修改環(huán)境變量

其次总滩，新建環(huán)境變量介汹，新建——瀏覽——CUPTI\libx64路徑導(dǎo)入，同理將cudnn\bin路徑導(dǎo)入纵隔，然后將新添加的路徑上移至頂端翻诉，和已經(jīng)存在的2個CUDA相關(guān)環(huán)境變量并列。完成后關(guān)閉捌刮。


圖11碰煌，創(chuàng)建環(huán)境變量并上移

4、利用Anaconda安裝PaddlePaddle和圖神經(jīng)學(xué)習(xí)庫PGL

首先绅作，利用conda創(chuàng)建3.6版本的python環(huán)境芦圾。

(base) C:\Users\WangYue>conda create -n PGL python=3.6

激活環(huán)境，

(base) C:\Users\WangYue>conda activate PGL

檢查python版本俄认，確認(rèn)為3.6版本个少，并退出python洪乍。

(PGL) C:\Users\WangYue>python
Python 3.6.12 |Anaconda, Inc.| (default, Sep  9 2020, 00:29:25) [MSC v.1916 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> quit()

(PGL) C:\Users\WangYue>

根據(jù)PaddlePaddle官網(wǎng)的提示使用conda安裝GPU版本的框架：

圖12，選擇合適的版本

安裝之前首先添加國內(nèi)鏡像（安裝時報(bào)錯HTTP錯誤通常都是因?yàn)闆]有添加鏡像的原因）：

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/
conda config --set show_channel_urls yes

然后安裝：

(PGL) C:\Users\WangYue>conda install paddlepaddle-gpu==1.8.5 cudatoolkit=10.0 -c paddle

done

檢查是否安裝成功夜焦，提示Your Paddle Fluid works well on MUTIPLE GPU or CPU.Your Paddle Fluid is installed successfully! Let's start deep Learning with Paddle Fluid now.表示已安裝成功PaddlePaddle壳澳，并能夠使用GPU進(jìn)行計(jì)算。

(PGL) C:\Users\WangYue>python
Python 3.6.12 |Anaconda, Inc.| (default, Sep  9 2020, 00:29:25) [MSC v.1916 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import paddle
>>> paddle.fluid.install_check.run_check()
Running Verify Fluid Program ...
W1124 16:46:09.452337 15492 device_context.cc:252] Please NOTE: device: 0, CUDA Capability: 75, Driver API Version: 11.0, Runtime API Version: 10.0
W1124 16:46:12.831832 15492 device_context.cc:260] device: 0, cuDNN Version: 7.6.
Your Paddle Fluid works well on SINGLE GPU or CPU.
W1124 16:46:16.209867 15492 build_strategy.cc:170] fusion_group is not enabled for Windows/MacOS now, and only effective when running with CUDA GPU.
Your Paddle Fluid works well on MUTIPLE GPU or CPU.
Your Paddle Fluid is installed successfully! Let's start deep Learning with Paddle Fluid now
>>>

接下來糊探，安裝PGL钾埂，并下載PGL代碼庫河闰。

# pip安裝PGL
(PGL) C:\Users\WangYue>pip install PGL
# conda安裝git
(PGL) C:\Users\WangYue>conda install git
# 切換到工作目錄
(PGL) C:\Users\WangYue>e:
(PGL) E:>cd pythonproject_win
# git clone PGL代碼庫
(PGL) E:\pythonproject_win>git clone --depth=1 https://github.com/PaddlePaddle/PGL
Cloning into 'PGL'...
remote: Enumerating objects: 480, done.
remote: Counting objects: 100% (480/480), done.
remote: Compressing objects: 100% (416/416), done.

Receiving objects: 100% (480/480), 15.47 MiB | 18.00 KiB/s, done.
Resolving deltas: 100% (88/88), done.

測試PGL

(PGL) E:\pythonproject_win\PGL\examples\gcn>python train.py

[INFO] 2020-11-24 17:38:14,396 [    train.py:  152]:    Namespace(dataset='cora', use_cuda=False)
D:\Anaconda3\envs\PGL\lib\site-packages\numpy\core\fromnumeric.py:3373: RuntimeWarning: Mean of empty slice.
  out=out, **kwargs)
D:\Anaconda3\envs\PGL\lib\site-packages\numpy\core\_methods.py:170: RuntimeWarning: invalid value encountered in double_scalars
  ret = ret.dtype.type(ret / rcount)
[INFO] 2020-11-24 17:38:15,892 [    train.py:  135]:    Epoch 0 (nan sec) Train Loss: 1.946376 Train Acc: 0.121429 Val Loss: 1.936659 Val Acc: 0.343333
[INFO] 2020-11-24 17:38:15,925 [    train.py:  135]:    Epoch 1 (nan sec) Train Loss: 1.935814 Train Acc: 0.321429 Val Loss: 1.926904 Val Acc: 0.373333
[INFO] 2020-11-24 17:38:15,960 [    train.py:  135]:    Epoch 2 (nan sec) Train Loss: 1.924818 Train Acc: 0.392857 Val Loss: 1.916334 Val Acc: 0.380000
[INFO] 2020-11-24 17:38:15,990 [    train.py:  135]:    Epoch 3 (0.01900 sec) Train Loss: 1.909246 Train Acc: 0.392857 Val Loss: 1.905591 Val Acc: 0.450000
[INFO] 2020-11-24 17:38:16,021 [    train.py:  135]:    Epoch 4 (0.01900 sec) Train Loss: 1.894153 Train Acc: 0.407143 Val Loss: 1.894562 Val Acc: 0.463333
[INFO] 2020-11-24 17:38:16,052 [    train.py:  135]:    Epoch 5 (0.01900 sec) Train Loss: 1.883368 Train Acc: 0.414286 Val Loss: 1.883252 Val Acc: 0.463333
[INFO] 2020-11-24 17:38:16,082 [    train.py:  135]:    Epoch 6 (0.01901 sec) Train Loss: 1.871770 Train Acc: 0.392857 Val Loss: 1.871455 Val Acc: 0.463333
[INFO] 2020-11-24 17:38:16,115 [    train.py:  135]:    Epoch 7 (0.01920 sec) Train Loss: 1.853012 Train Acc: 0.435714 Val Loss: 1.859422 Val Acc: 0.466667
[INFO] 2020-11-24 17:38:16,146 [    train.py:  135]:    Epoch 8 (0.01917 sec) Train Loss: 1.837925 Train Acc: 0.450000 Val Loss: 1.847324 Val Acc: 0.466667
[INFO] 2020-11-24 17:38:16,177 [    train.py:  135]:    Epoch 9 (0.01900 sec) Train Loss: 1.824604 Train Acc: 0.435714 Val Loss: 1.835141 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,208 [    train.py:  135]:    Epoch 10 (0.01900 sec) Train Loss: 1.797683 Train Acc: 0.464286 Val Loss: 1.822889 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,239 [    train.py:  135]:    Epoch 11 (0.01900 sec) Train Loss: 1.790788 Train Acc: 0.428571 Val Loss: 1.810861 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,269 [    train.py:  135]:    Epoch 12 (0.01900 sec) Train Loss: 1.779723 Train Acc: 0.435714 Val Loss: 1.799263 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,300 [    train.py:  135]:    Epoch 13 (0.01909 sec) Train Loss: 1.765455 Train Acc: 0.414286 Val Loss: 1.788079 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,330 [    train.py:  135]:    Epoch 14 (0.01909 sec) Train Loss: 1.738075 Train Acc: 0.421429 Val Loss: 1.777288 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,361 [    train.py:  135]:    Epoch 15 (0.01908 sec) Train Loss: 1.722855 Train Acc: 0.407143 Val Loss: 1.766843 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,393 [    train.py:  135]:    Epoch 16 (0.01907 sec) Train Loss: 1.728457 Train Acc: 0.385714 Val Loss: 1.756886 Val Acc: 0.470000
[INFO] 2020-11-24 17:38:16,423 [    train.py:  135]:    Epoch 17 (0.01907 sec) Train Loss: 1.701181 Train Acc: 0.428571 Val Loss: 1.747185 Val Acc: 0.473333
[INFO] 2020-11-24 17:38:16,453 [    train.py:  135]:    Epoch 18 (0.01906 sec) Train Loss: 1.691437 Train Acc: 0.442857 Val Loss: 1.737742 Val Acc: 0.466667
[INFO] 2020-11-24 17:38:16,484 [    train.py:  135]:    Epoch 19 (0.01906 sec) Train Loss: 1.678157 Train Acc: 0.478571 Val Loss: 1.728544 Val Acc: 0.456667
[INFO] 2020-11-24 17:38:16,515 [    train.py:  135]:    Epoch 20 (0.01911 sec) Train Loss: 1.654645 Train Acc: 0.435714 Val Loss: 1.719246 Val Acc: 0.450000
[INFO] 2020-11-24 17:38:16,546 [    train.py:  135]:    Epoch 21 (0.01916 sec) Train Loss: 1.649073 Train Acc: 0.428571 Val Loss: 1.709656 Val Acc: 0.430000
[INFO] 2020-11-24 17:38:16,578 [    train.py:  135]:    Epoch 22 (0.01925 sec) Train Loss: 1.642157 Train Acc: 0.407143 Val Loss: 1.700160 Val Acc: 0.430000
[INFO] 2020-11-24 17:38:16,608 [    train.py:  135]:    Epoch 23 (0.01919 sec) Train Loss: 1.624353 Train Acc: 0.450000 Val Loss: 1.690708 Val Acc: 0.430000
[INFO] 2020-11-24 17:38:16,638 [    train.py:  135]:    Epoch 24 (0.01918 sec) Train Loss: 1.616144 Train Acc: 0.450000 Val Loss: 1.681005 Val Acc: 0.426667
[INFO] 2020-11-24 17:38:16,669 [    train.py:  135]:    Epoch 25 (0.01918 sec) Train Loss: 1.610140 Train Acc: 0.421429 Val Loss: 1.671384 Val Acc: 0.430000
[INFO] 2020-11-24 17:38:16,699 [    train.py:  135]:    Epoch 26 (0.01917 sec) Train Loss: 1.587404 Train Acc: 0.457143 Val Loss: 1.661528 Val Acc: 0.430000
[INFO] 2020-11-24 17:38:16,729 [    train.py:  135]:    Epoch 27 (0.01916 sec) Train Loss: 1.567697 Train Acc: 0.457143 Val Loss: 1.651543 Val Acc: 0.433333
[INFO] 2020-11-24 17:38:16,760 [    train.py:  135]:    Epoch 28 (0.01914 sec) Train Loss: 1.572376 Train Acc: 0.435714 Val Loss: 1.641517 Val Acc: 0.446667
[INFO] 2020-11-24 17:38:16,796 [    train.py:  135]:    Epoch 29 (0.01932 sec) Train Loss: 1.539159 Train Acc: 0.464286 Val Loss: 1.631305 Val Acc: 0.460000
[INFO] 2020-11-24 17:38:16,827 [    train.py:  135]:    Epoch 30 (0.01934 sec) Train Loss: 1.537863 Train Acc: 0.450000 Val Loss: 1.621206 Val Acc: 0.466667
[INFO] 2020-11-24 17:38:16,857 [    train.py:  135]:    Epoch 31 (0.01933 sec) Train Loss: 1.513063 Train Acc: 0.471429 Val Loss: 1.611248 Val Acc: 0.470000
[INFO] 2020-11-24 17:38:16,890 [    train.py:  135]:    Epoch 32 (0.01938 sec) Train Loss: 1.538276 Train Acc: 0.471429 Val Loss: 1.601295 Val Acc: 0.470000
[INFO] 2020-11-24 17:38:16,920 [    train.py:  135]:    Epoch 33 (0.01937 sec) Train Loss: 1.483976 Train Acc: 0.507143 Val Loss: 1.591422 Val Acc: 0.470000
[INFO] 2020-11-24 17:38:16,952 [    train.py:  135]:    Epoch 34 (0.01936 sec) Train Loss: 1.484524 Train Acc: 0.485714 Val Loss: 1.581631 Val Acc: 0.470000
[INFO] 2020-11-24 17:38:16,982 [    train.py:  135]:    Epoch 35 (0.01935 sec) Train Loss: 1.412567 Train Acc: 0.514286 Val Loss: 1.571641 Val Acc: 0.480000
[INFO] 2020-11-24 17:38:17,013 [    train.py:  135]:    Epoch 36 (0.01934 sec) Train Loss: 1.456412 Train Acc: 0.500000 Val Loss: 1.561643 Val Acc: 0.486667
[INFO] 2020-11-24 17:38:17,045 [    train.py:  135]:    Epoch 37 (0.01933 sec) Train Loss: 1.422783 Train Acc: 0.578571 Val Loss: 1.551188 Val Acc: 0.503333
[INFO] 2020-11-24 17:38:17,077 [    train.py:  135]:    Epoch 38 (0.01938 sec) Train Loss: 1.401480 Train Acc: 0.550000 Val Loss: 1.540481 Val Acc: 0.520000
[INFO] 2020-11-24 17:38:17,107 [    train.py:  135]:    Epoch 39 (0.01937 sec) Train Loss: 1.381318 Train Acc: 0.571429 Val Loss: 1.529427 Val Acc: 0.533333
[INFO] 2020-11-24 17:38:17,137 [    train.py:  135]:    Epoch 40 (0.01936 sec) Train Loss: 1.385848 Train Acc: 0.585714 Val Loss: 1.518172 Val Acc: 0.536667
[INFO] 2020-11-24 17:38:17,169 [    train.py:  135]:    Epoch 41 (0.01935 sec) Train Loss: 1.373476 Train Acc: 0.614286 Val Loss: 1.506592 Val Acc: 0.540000
[INFO] 2020-11-24 17:38:17,199 [    train.py:  135]:    Epoch 42 (0.01934 sec) Train Loss: 1.327903 Train Acc: 0.600000 Val Loss: 1.494827 Val Acc: 0.540000
[INFO] 2020-11-24 17:38:17,231 [    train.py:  135]:    Epoch 43 (0.01936 sec) Train Loss: 1.330398 Train Acc: 0.578571 Val Loss: 1.482955 Val Acc: 0.540000
[INFO] 2020-11-24 17:38:17,262 [    train.py:  135]:    Epoch 44 (0.01937 sec) Train Loss: 1.320188 Train Acc: 0.614286 Val Loss: 1.471008 Val Acc: 0.546667
[INFO] 2020-11-24 17:38:17,293 [    train.py:  135]:    Epoch 45 (0.01936 sec) Train Loss: 1.292543 Train Acc: 0.664286 Val Loss: 1.458795 Val Acc: 0.553333
[INFO] 2020-11-24 17:38:17,324 [    train.py:  135]:    Epoch 46 (0.01935 sec) Train Loss: 1.280111 Train Acc: 0.635714 Val Loss: 1.446541 Val Acc: 0.563333
[INFO] 2020-11-24 17:38:17,354 [    train.py:  135]:    Epoch 47 (0.01935 sec) Train Loss: 1.268894 Train Acc: 0.664286 Val Loss: 1.433995 Val Acc: 0.570000
[INFO] 2020-11-24 17:38:17,386 [    train.py:  135]:    Epoch 48 (0.01934 sec) Train Loss: 1.264615 Train Acc: 0.657143 Val Loss: 1.421343 Val Acc: 0.580000
[INFO] 2020-11-24 17:38:17,417 [    train.py:  135]:    Epoch 49 (0.01935 sec) Train Loss: 1.235874 Train Acc: 0.664286 Val Loss: 1.408745 Val Acc: 0.600000
[INFO] 2020-11-24 17:38:17,448 [    train.py:  135]:    Epoch 50 (0.01934 sec) Train Loss: 1.212078 Train Acc: 0.678571 Val Loss: 1.396486 Val Acc: 0.606667
[INFO] 2020-11-24 17:38:17,479 [    train.py:  135]:    Epoch 51 (0.01936 sec) Train Loss: 1.184450 Train Acc: 0.728571 Val Loss: 1.384343 Val Acc: 0.616667
[INFO] 2020-11-24 17:38:17,511 [    train.py:  135]:    Epoch 52 (0.01935 sec) Train Loss: 1.195419 Train Acc: 0.707143 Val Loss: 1.372334 Val Acc: 0.626667
[INFO] 2020-11-24 17:38:17,545 [    train.py:  135]:    Epoch 53 (0.01940 sec) Train Loss: 1.192992 Train Acc: 0.685714 Val Loss: 1.360279 Val Acc: 0.646667
[INFO] 2020-11-24 17:38:17,576 [    train.py:  135]:    Epoch 54 (0.01939 sec) Train Loss: 1.201842 Train Acc: 0.728571 Val Loss: 1.348460 Val Acc: 0.650000
[INFO] 2020-11-24 17:38:17,608 [    train.py:  135]:    Epoch 55 (0.01941 sec) Train Loss: 1.139250 Train Acc: 0.750000 Val Loss: 1.336654 Val Acc: 0.653333
[INFO] 2020-11-24 17:38:17,640 [    train.py:  135]:    Epoch 56 (0.01944 sec) Train Loss: 1.113972 Train Acc: 0.757143 Val Loss: 1.325034 Val Acc: 0.660000
[INFO] 2020-11-24 17:38:17,673 [    train.py:  135]:    Epoch 57 (0.01946 sec) Train Loss: 1.094335 Train Acc: 0.800000 Val Loss: 1.313636 Val Acc: 0.666667
[INFO] 2020-11-24 17:38:17,703 [    train.py:  135]:    Epoch 58 (0.01946 sec) Train Loss: 1.106194 Train Acc: 0.750000 Val Loss: 1.302360 Val Acc: 0.676667
[INFO] 2020-11-24 17:38:17,734 [    train.py:  135]:    Epoch 59 (0.01945 sec) Train Loss: 1.081495 Train Acc: 0.785714 Val Loss: 1.291049 Val Acc: 0.680000
[INFO] 2020-11-24 17:38:17,764 [    train.py:  135]:    Epoch 60 (0.01944 sec) Train Loss: 1.118300 Train Acc: 0.750000 Val Loss: 1.279665 Val Acc: 0.683333
[INFO] 2020-11-24 17:38:17,800 [    train.py:  135]:    Epoch 61 (0.01952 sec) Train Loss: 1.057867 Train Acc: 0.792857 Val Loss: 1.268428 Val Acc: 0.693333
[INFO] 2020-11-24 17:38:17,831 [    train.py:  135]:    Epoch 62 (0.01952 sec) Train Loss: 1.017038 Train Acc: 0.764286 Val Loss: 1.257187 Val Acc: 0.696667
[INFO] 2020-11-24 17:38:17,864 [    train.py:  135]:    Epoch 63 (0.01955 sec) Train Loss: 1.005523 Train Acc: 0.800000 Val Loss: 1.246129 Val Acc: 0.710000
[INFO] 2020-11-24 17:38:17,895 [    train.py:  135]:    Epoch 64 (0.01954 sec) Train Loss: 1.049122 Train Acc: 0.728571 Val Loss: 1.235504 Val Acc: 0.713333
[INFO] 2020-11-24 17:38:17,925 [    train.py:  135]:    Epoch 65 (0.01953 sec) Train Loss: 1.030980 Train Acc: 0.750000 Val Loss: 1.224965 Val Acc: 0.720000
[INFO] 2020-11-24 17:38:17,956 [    train.py:  135]:    Epoch 66 (0.01952 sec) Train Loss: 0.969386 Train Acc: 0.800000 Val Loss: 1.214571 Val Acc: 0.730000
[INFO] 2020-11-24 17:38:17,987 [    train.py:  135]:    Epoch 67 (0.01952 sec) Train Loss: 0.939819 Train Acc: 0.778571 Val Loss: 1.204163 Val Acc: 0.733333
[INFO] 2020-11-24 17:38:18,020 [    train.py:  135]:    Epoch 68 (0.01951 sec) Train Loss: 0.942907 Train Acc: 0.814286 Val Loss: 1.193557 Val Acc: 0.736667
[INFO] 2020-11-24 17:38:18,050 [    train.py:  135]:    Epoch 69 (0.01949 sec) Train Loss: 0.951270 Train Acc: 0.842857 Val Loss: 1.182744 Val Acc: 0.740000
[INFO] 2020-11-24 17:38:18,081 [    train.py:  135]:    Epoch 70 (0.01948 sec) Train Loss: 0.931611 Train Acc: 0.785714 Val Loss: 1.172386 Val Acc: 0.743333
[INFO] 2020-11-24 17:38:18,111 [    train.py:  135]:    Epoch 71 (0.01947 sec) Train Loss: 0.917022 Train Acc: 0.814286 Val Loss: 1.162505 Val Acc: 0.746667
[INFO] 2020-11-24 17:38:18,142 [    train.py:  135]:    Epoch 72 (0.01945 sec) Train Loss: 0.927033 Train Acc: 0.828571 Val Loss: 1.152792 Val Acc: 0.746667
[INFO] 2020-11-24 17:38:18,174 [    train.py:  135]:    Epoch 73 (0.01944 sec) Train Loss: 0.892688 Train Acc: 0.835714 Val Loss: 1.143111 Val Acc: 0.750000
[INFO] 2020-11-24 17:38:18,204 [    train.py:  135]:    Epoch 74 (0.01944 sec) Train Loss: 0.931898 Train Acc: 0.821429 Val Loss: 1.133670 Val Acc: 0.750000
[INFO] 2020-11-24 17:38:18,234 [    train.py:  135]:    Epoch 75 (0.01943 sec) Train Loss: 0.914224 Train Acc: 0.828571 Val Loss: 1.124703 Val Acc: 0.753333
[INFO] 2020-11-24 17:38:18,265 [    train.py:  135]:    Epoch 76 (0.01943 sec) Train Loss: 0.876583 Train Acc: 0.857143 Val Loss: 1.116272 Val Acc: 0.753333
[INFO] 2020-11-24 17:38:18,296 [    train.py:  135]:    Epoch 77 (0.01942 sec) Train Loss: 0.835312 Train Acc: 0.828571 Val Loss: 1.107984 Val Acc: 0.753333
[INFO] 2020-11-24 17:38:18,326 [    train.py:  135]:    Epoch 78 (0.01941 sec) Train Loss: 0.860001 Train Acc: 0.828571 Val Loss: 1.099642 Val Acc: 0.753333
[INFO] 2020-11-24 17:38:18,357 [    train.py:  135]:    Epoch 79 (0.01941 sec) Train Loss: 0.811797 Train Acc: 0.857143 Val Loss: 1.091735 Val Acc: 0.746667
[INFO] 2020-11-24 17:38:18,388 [    train.py:  135]:    Epoch 80 (0.01940 sec) Train Loss: 0.827785 Train Acc: 0.807143 Val Loss: 1.083777 Val Acc: 0.743333
[INFO] 2020-11-24 17:38:18,418 [    train.py:  135]:    Epoch 81 (0.01939 sec) Train Loss: 0.823327 Train Acc: 0.842857 Val Loss: 1.075461 Val Acc: 0.746667
[INFO] 2020-11-24 17:38:18,448 [    train.py:  135]:    Epoch 82 (0.01938 sec) Train Loss: 0.807287 Train Acc: 0.864286 Val Loss: 1.067636 Val Acc: 0.746667
[INFO] 2020-11-24 17:38:18,479 [    train.py:  135]:    Epoch 83 (0.01938 sec) Train Loss: 0.749915 Train Acc: 0.871429 Val Loss: 1.059620 Val Acc: 0.753333
[INFO] 2020-11-24 17:38:18,512 [    train.py:  135]:    Epoch 84 (0.01941 sec) Train Loss: 0.788638 Train Acc: 0.864286 Val Loss: 1.051789 Val Acc: 0.753333
[INFO] 2020-11-24 17:38:18,543 [    train.py:  135]:    Epoch 85 (0.01940 sec) Train Loss: 0.777396 Train Acc: 0.842857 Val Loss: 1.044784 Val Acc: 0.756667
[INFO] 2020-11-24 17:38:18,574 [    train.py:  135]:    Epoch 86 (0.01941 sec) Train Loss: 0.806583 Train Acc: 0.842857 Val Loss: 1.037960 Val Acc: 0.756667
[INFO] 2020-11-24 17:38:18,605 [    train.py:  135]:    Epoch 87 (0.01941 sec) Train Loss: 0.792139 Train Acc: 0.857143 Val Loss: 1.031266 Val Acc: 0.760000
[INFO] 2020-11-24 17:38:18,636 [    train.py:  135]:    Epoch 88 (0.01941 sec) Train Loss: 0.774478 Train Acc: 0.864286 Val Loss: 1.024997 Val Acc: 0.766667
[INFO] 2020-11-24 17:38:18,669 [    train.py:  135]:    Epoch 89 (0.01943 sec) Train Loss: 0.758760 Train Acc: 0.864286 Val Loss: 1.018678 Val Acc: 0.766667
[INFO] 2020-11-24 17:38:18,700 [    train.py:  135]:    Epoch 90 (0.01943 sec) Train Loss: 0.718107 Train Acc: 0.885714 Val Loss: 1.012541 Val Acc: 0.766667
[INFO] 2020-11-24 17:38:18,731 [    train.py:  135]:    Epoch 91 (0.01942 sec) Train Loss: 0.755768 Train Acc: 0.850000 Val Loss: 1.006553 Val Acc: 0.763333
[INFO] 2020-11-24 17:38:18,761 [    train.py:  135]:    Epoch 92 (0.01942 sec) Train Loss: 0.671023 Train Acc: 0.871429 Val Loss: 1.000243 Val Acc: 0.766667
[INFO] 2020-11-24 17:38:18,799 [    train.py:  135]:    Epoch 93 (0.01949 sec) Train Loss: 0.736484 Train Acc: 0.871429 Val Loss: 0.993748 Val Acc: 0.770000
[INFO] 2020-11-24 17:38:18,829 [    train.py:  135]:    Epoch 94 (0.01949 sec) Train Loss: 0.684531 Train Acc: 0.900000 Val Loss: 0.987403 Val Acc: 0.773333
[INFO] 2020-11-24 17:38:18,860 [    train.py:  135]:    Epoch 95 (0.01948 sec) Train Loss: 0.704644 Train Acc: 0.878571 Val Loss: 0.980671 Val Acc: 0.776667
[INFO] 2020-11-24 17:38:18,890 [    train.py:  135]:    Epoch 96 (0.01947 sec) Train Loss: 0.700402 Train Acc: 0.842857 Val Loss: 0.974380 Val Acc: 0.776667
[INFO] 2020-11-24 17:38:18,921 [    train.py:  135]:    Epoch 97 (0.01948 sec) Train Loss: 0.701402 Train Acc: 0.892857 Val Loss: 0.967968 Val Acc: 0.776667
[INFO] 2020-11-24 17:38:18,952 [    train.py:  135]:    Epoch 98 (0.01949 sec) Train Loss: 0.688109 Train Acc: 0.892857 Val Loss: 0.961627 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:18,985 [    train.py:  135]:    Epoch 99 (0.01948 sec) Train Loss: 0.698456 Train Acc: 0.878571 Val Loss: 0.955670 Val Acc: 0.783333
[INFO] 2020-11-24 17:38:19,015 [    train.py:  135]:    Epoch 100 (0.01948 sec) Train Loss: 0.715043 Train Acc: 0.892857 Val Loss: 0.949948 Val Acc: 0.783333
[INFO] 2020-11-24 17:38:19,046 [    train.py:  135]:    Epoch 101 (0.01947 sec) Train Loss: 0.680752 Train Acc: 0.900000 Val Loss: 0.945099 Val Acc: 0.783333
[INFO] 2020-11-24 17:38:19,076 [    train.py:  135]:    Epoch 102 (0.01947 sec) Train Loss: 0.699681 Train Acc: 0.864286 Val Loss: 0.940839 Val Acc: 0.780000
[INFO] 2020-11-24 17:38:19,106 [    train.py:  135]:    Epoch 103 (0.01945 sec) Train Loss: 0.713673 Train Acc: 0.871429 Val Loss: 0.937625 Val Acc: 0.783333
[INFO] 2020-11-24 17:38:19,136 [    train.py:  135]:    Epoch 104 (0.01945 sec) Train Loss: 0.683508 Train Acc: 0.871429 Val Loss: 0.935034 Val Acc: 0.780000
[INFO] 2020-11-24 17:38:19,166 [    train.py:  135]:    Epoch 105 (0.01943 sec) Train Loss: 0.617904 Train Acc: 0.900000 Val Loss: 0.932254 Val Acc: 0.783333
[INFO] 2020-11-24 17:38:19,196 [    train.py:  135]:    Epoch 106 (0.01943 sec) Train Loss: 0.691874 Train Acc: 0.871429 Val Loss: 0.929585 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,227 [    train.py:  135]:    Epoch 107 (0.01943 sec) Train Loss: 0.600925 Train Acc: 0.935714 Val Loss: 0.926206 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,257 [    train.py:  135]:    Epoch 108 (0.01941 sec) Train Loss: 0.626542 Train Acc: 0.871429 Val Loss: 0.921885 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,287 [    train.py:  135]:    Epoch 109 (0.01941 sec) Train Loss: 0.623590 Train Acc: 0.900000 Val Loss: 0.916823 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,318 [    train.py:  135]:    Epoch 110 (0.01940 sec) Train Loss: 0.628510 Train Acc: 0.892857 Val Loss: 0.911530 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,348 [    train.py:  135]:    Epoch 111 (0.01940 sec) Train Loss: 0.623448 Train Acc: 0.885714 Val Loss: 0.906081 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,379 [    train.py:  135]:    Epoch 112 (0.01940 sec) Train Loss: 0.666084 Train Acc: 0.878571 Val Loss: 0.900852 Val Acc: 0.783333
[INFO] 2020-11-24 17:38:19,410 [    train.py:  135]:    Epoch 113 (0.01939 sec) Train Loss: 0.583377 Train Acc: 0.928571 Val Loss: 0.896402 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,443 [    train.py:  135]:    Epoch 114 (0.01941 sec) Train Loss: 0.671777 Train Acc: 0.878571 Val Loss: 0.892135 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,478 [    train.py:  135]:    Epoch 115 (0.01944 sec) Train Loss: 0.617062 Train Acc: 0.892857 Val Loss: 0.888102 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,508 [    train.py:  135]:    Epoch 116 (0.01944 sec) Train Loss: 0.632892 Train Acc: 0.871429 Val Loss: 0.884869 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,539 [    train.py:  135]:    Epoch 117 (0.01943 sec) Train Loss: 0.621602 Train Acc: 0.885714 Val Loss: 0.881907 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,574 [    train.py:  135]:    Epoch 118 (0.01945 sec) Train Loss: 0.601480 Train Acc: 0.885714 Val Loss: 0.879309 Val Acc: 0.790000
[INFO] 2020-11-24 17:38:19,604 [    train.py:  135]:    Epoch 119 (0.01945 sec) Train Loss: 0.608852 Train Acc: 0.928571 Val Loss: 0.876792 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:19,636 [    train.py:  135]:    Epoch 120 (0.01945 sec) Train Loss: 0.582225 Train Acc: 0.892857 Val Loss: 0.874423 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,666 [    train.py:  135]:    Epoch 121 (0.01944 sec) Train Loss: 0.576704 Train Acc: 0.907143 Val Loss: 0.871257 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,698 [    train.py:  135]:    Epoch 122 (0.01944 sec) Train Loss: 0.593480 Train Acc: 0.892857 Val Loss: 0.868069 Val Acc: 0.790000
[INFO] 2020-11-24 17:38:19,728 [    train.py:  135]:    Epoch 123 (0.01944 sec) Train Loss: 0.572575 Train Acc: 0.907143 Val Loss: 0.864672 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:19,759 [    train.py:  135]:    Epoch 124 (0.01943 sec) Train Loss: 0.556454 Train Acc: 0.928571 Val Loss: 0.861215 Val Acc: 0.790000
[INFO] 2020-11-24 17:38:19,794 [    train.py:  135]:    Epoch 125 (0.01947 sec) Train Loss: 0.583361 Train Acc: 0.892857 Val Loss: 0.856351 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:19,825 [    train.py:  135]:    Epoch 126 (0.01947 sec) Train Loss: 0.575858 Train Acc: 0.892857 Val Loss: 0.851848 Val Acc: 0.790000
[INFO] 2020-11-24 17:38:19,855 [    train.py:  135]:    Epoch 127 (0.01946 sec) Train Loss: 0.586449 Train Acc: 0.907143 Val Loss: 0.848449 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,886 [    train.py:  135]:    Epoch 128 (0.01946 sec) Train Loss: 0.569864 Train Acc: 0.907143 Val Loss: 0.845945 Val Acc: 0.786667
[INFO] 2020-11-24 17:38:19,917 [    train.py:  135]:    Epoch 129 (0.01945 sec) Train Loss: 0.549760 Train Acc: 0.914286 Val Loss: 0.844092 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:19,949 [    train.py:  135]:    Epoch 130 (0.01947 sec) Train Loss: 0.525366 Train Acc: 0.914286 Val Loss: 0.842285 Val Acc: 0.796667
[INFO] 2020-11-24 17:38:19,980 [    train.py:  135]:    Epoch 131 (0.01946 sec) Train Loss: 0.570853 Train Acc: 0.907143 Val Loss: 0.841248 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,010 [    train.py:  135]:    Epoch 132 (0.01946 sec) Train Loss: 0.545706 Train Acc: 0.885714 Val Loss: 0.840566 Val Acc: 0.796667
[INFO] 2020-11-24 17:38:20,040 [    train.py:  135]:    Epoch 133 (0.01945 sec) Train Loss: 0.522932 Train Acc: 0.942857 Val Loss: 0.839006 Val Acc: 0.796667
[INFO] 2020-11-24 17:38:20,081 [    train.py:  135]:    Epoch 134 (0.01950 sec) Train Loss: 0.549455 Train Acc: 0.935714 Val Loss: 0.836572 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,111 [    train.py:  135]:    Epoch 135 (0.01949 sec) Train Loss: 0.540828 Train Acc: 0.914286 Val Loss: 0.833662 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,142 [    train.py:  135]:    Epoch 136 (0.01949 sec) Train Loss: 0.532241 Train Acc: 0.914286 Val Loss: 0.829949 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:20,174 [    train.py:  135]:    Epoch 137 (0.01949 sec) Train Loss: 0.513366 Train Acc: 0.935714 Val Loss: 0.825624 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:20,205 [    train.py:  135]:    Epoch 138 (0.01949 sec) Train Loss: 0.523155 Train Acc: 0.928571 Val Loss: 0.821903 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:20,236 [    train.py:  135]:    Epoch 139 (0.01949 sec) Train Loss: 0.507928 Train Acc: 0.921429 Val Loss: 0.818555 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,267 [    train.py:  135]:    Epoch 140 (0.01948 sec) Train Loss: 0.529753 Train Acc: 0.907143 Val Loss: 0.816106 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:20,297 [    train.py:  135]:    Epoch 141 (0.01948 sec) Train Loss: 0.581101 Train Acc: 0.864286 Val Loss: 0.814416 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:20,329 [    train.py:  135]:    Epoch 142 (0.01948 sec) Train Loss: 0.529025 Train Acc: 0.942857 Val Loss: 0.813017 Val Acc: 0.796667
[INFO] 2020-11-24 17:38:20,359 [    train.py:  135]:    Epoch 143 (0.01947 sec) Train Loss: 0.547050 Train Acc: 0.914286 Val Loss: 0.811976 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,390 [    train.py:  135]:    Epoch 144 (0.01947 sec) Train Loss: 0.477046 Train Acc: 0.957143 Val Loss: 0.810994 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:20,422 [    train.py:  135]:    Epoch 145 (0.01947 sec) Train Loss: 0.523743 Train Acc: 0.900000 Val Loss: 0.809442 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,453 [    train.py:  135]:    Epoch 146 (0.01946 sec) Train Loss: 0.511287 Train Acc: 0.900000 Val Loss: 0.808221 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:20,484 [    train.py:  135]:    Epoch 147 (0.01946 sec) Train Loss: 0.492253 Train Acc: 0.942857 Val Loss: 0.806867 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:20,514 [    train.py:  135]:    Epoch 148 (0.01946 sec) Train Loss: 0.480283 Train Acc: 0.935714 Val Loss: 0.804443 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:20,545 [    train.py:  135]:    Epoch 149 (0.01945 sec) Train Loss: 0.453111 Train Acc: 0.971429 Val Loss: 0.802412 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,576 [    train.py:  135]:    Epoch 150 (0.01946 sec) Train Loss: 0.490314 Train Acc: 0.928571 Val Loss: 0.800740 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:20,607 [    train.py:  135]:    Epoch 151 (0.01946 sec) Train Loss: 0.475686 Train Acc: 0.928571 Val Loss: 0.798504 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:20,637 [    train.py:  135]:    Epoch 152 (0.01946 sec) Train Loss: 0.495609 Train Acc: 0.914286 Val Loss: 0.795318 Val Acc: 0.793333
[INFO] 2020-11-24 17:38:20,668 [    train.py:  135]:    Epoch 153 (0.01945 sec) Train Loss: 0.516428 Train Acc: 0.921429 Val Loss: 0.792276 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,698 [    train.py:  135]:    Epoch 154 (0.01945 sec) Train Loss: 0.502076 Train Acc: 0.950000 Val Loss: 0.788550 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,728 [    train.py:  135]:    Epoch 155 (0.01944 sec) Train Loss: 0.462659 Train Acc: 0.942857 Val Loss: 0.785604 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,759 [    train.py:  135]:    Epoch 156 (0.01944 sec) Train Loss: 0.499720 Train Acc: 0.914286 Val Loss: 0.784087 Val Acc: 0.800000
[INFO] 2020-11-24 17:38:20,795 [    train.py:  135]:    Epoch 157 (0.01947 sec) Train Loss: 0.501638 Train Acc: 0.950000 Val Loss: 0.783460 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:20,827 [    train.py:  135]:    Epoch 158 (0.01947 sec) Train Loss: 0.474494 Train Acc: 0.942857 Val Loss: 0.783603 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:20,858 [    train.py:  135]:    Epoch 159 (0.01946 sec) Train Loss: 0.463639 Train Acc: 0.921429 Val Loss: 0.784178 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:20,889 [    train.py:  135]:    Epoch 160 (0.01946 sec) Train Loss: 0.506787 Train Acc: 0.921429 Val Loss: 0.783240 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:20,923 [    train.py:  135]:    Epoch 161 (0.01948 sec) Train Loss: 0.470841 Train Acc: 0.907143 Val Loss: 0.781275 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:20,954 [    train.py:  135]:    Epoch 162 (0.01947 sec) Train Loss: 0.472303 Train Acc: 0.935714 Val Loss: 0.780728 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:20,985 [    train.py:  135]:    Epoch 163 (0.01947 sec) Train Loss: 0.470098 Train Acc: 0.928571 Val Loss: 0.780580 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,015 [    train.py:  135]:    Epoch 164 (0.01946 sec) Train Loss: 0.446667 Train Acc: 0.935714 Val Loss: 0.779541 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,045 [    train.py:  135]:    Epoch 165 (0.01946 sec) Train Loss: 0.452989 Train Acc: 0.935714 Val Loss: 0.777650 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,076 [    train.py:  135]:    Epoch 166 (0.01946 sec) Train Loss: 0.427969 Train Acc: 0.928571 Val Loss: 0.775191 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,107 [    train.py:  135]:    Epoch 167 (0.01945 sec) Train Loss: 0.475839 Train Acc: 0.928571 Val Loss: 0.772008 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,139 [    train.py:  135]:    Epoch 168 (0.01946 sec) Train Loss: 0.491018 Train Acc: 0.921429 Val Loss: 0.769636 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:21,171 [    train.py:  135]:    Epoch 169 (0.01946 sec) Train Loss: 0.490486 Train Acc: 0.928571 Val Loss: 0.768028 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,201 [    train.py:  135]:    Epoch 170 (0.01946 sec) Train Loss: 0.450003 Train Acc: 0.907143 Val Loss: 0.766701 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,232 [    train.py:  135]:    Epoch 171 (0.01945 sec) Train Loss: 0.465099 Train Acc: 0.957143 Val Loss: 0.765610 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,265 [    train.py:  135]:    Epoch 172 (0.01946 sec) Train Loss: 0.425242 Train Acc: 0.935714 Val Loss: 0.764214 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,295 [    train.py:  135]:    Epoch 173 (0.01946 sec) Train Loss: 0.425517 Train Acc: 0.942857 Val Loss: 0.762162 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,327 [    train.py:  135]:    Epoch 174 (0.01946 sec) Train Loss: 0.440138 Train Acc: 0.942857 Val Loss: 0.760464 Val Acc: 0.806667
[INFO] 2020-11-24 17:38:21,357 [    train.py:  135]:    Epoch 175 (0.01946 sec) Train Loss: 0.451479 Train Acc: 0.942857 Val Loss: 0.760121 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:21,391 [    train.py:  135]:    Epoch 176 (0.01946 sec) Train Loss: 0.456870 Train Acc: 0.900000 Val Loss: 0.759870 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:21,423 [    train.py:  135]:    Epoch 177 (0.01946 sec) Train Loss: 0.466615 Train Acc: 0.928571 Val Loss: 0.760071 Val Acc: 0.803333
[INFO] 2020-11-24 17:38:21,455 [    train.py:  135]:    Epoch 178 (0.01947 sec) Train Loss: 0.421555 Train Acc: 0.942857 Val Loss: 0.761534 Val Acc: 0.810000
[INFO] 2020-11-24 17:38:21,487 [    train.py:  135]:    Epoch 179 (0.01947 sec) Train Loss: 0.435196 Train Acc: 0.928571 Val Loss: 0.762187 Val Acc: 0.810000
[INFO] 2020-11-24 17:38:21,518 [    train.py:  135]:    Epoch 180 (0.01946 sec) Train Loss: 0.475000 Train Acc: 0.942857 Val Loss: 0.761095 Val Acc: 0.810000
[INFO] 2020-11-24 17:38:21,548 [    train.py:  135]:    Epoch 181 (0.01946 sec) Train Loss: 0.442108 Train Acc: 0.914286 Val Loss: 0.759001 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,578 [    train.py:  135]:    Epoch 182 (0.01946 sec) Train Loss: 0.444315 Train Acc: 0.928571 Val Loss: 0.756658 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,609 [    train.py:  135]:    Epoch 183 (0.01946 sec) Train Loss: 0.456490 Train Acc: 0.921429 Val Loss: 0.753842 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,639 [    train.py:  135]:    Epoch 184 (0.01946 sec) Train Loss: 0.445454 Train Acc: 0.921429 Val Loss: 0.752500 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,670 [    train.py:  135]:    Epoch 185 (0.01946 sec) Train Loss: 0.474711 Train Acc: 0.907143 Val Loss: 0.751830 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,700 [    train.py:  135]:    Epoch 186 (0.01945 sec) Train Loss: 0.435747 Train Acc: 0.935714 Val Loss: 0.751131 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,730 [    train.py:  135]:    Epoch 187 (0.01945 sec) Train Loss: 0.454062 Train Acc: 0.914286 Val Loss: 0.750023 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,762 [    train.py:  135]:    Epoch 188 (0.01945 sec) Train Loss: 0.398557 Train Acc: 0.928571 Val Loss: 0.748987 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,797 [    train.py:  135]:    Epoch 189 (0.01947 sec) Train Loss: 0.435511 Train Acc: 0.935714 Val Loss: 0.746897 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,829 [    train.py:  135]:    Epoch 190 (0.01946 sec) Train Loss: 0.432686 Train Acc: 0.950000 Val Loss: 0.745300 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:21,860 [    train.py:  135]:    Epoch 191 (0.01946 sec) Train Loss: 0.404004 Train Acc: 0.971429 Val Loss: 0.743253 Val Acc: 0.810000
[INFO] 2020-11-24 17:38:21,892 [    train.py:  135]:    Epoch 192 (0.01947 sec) Train Loss: 0.433725 Train Acc: 0.935714 Val Loss: 0.742340 Val Acc: 0.810000
[INFO] 2020-11-24 17:38:21,923 [    train.py:  135]:    Epoch 193 (0.01946 sec) Train Loss: 0.429871 Train Acc: 0.935714 Val Loss: 0.741186 Val Acc: 0.813333
[INFO] 2020-11-24 17:38:21,954 [    train.py:  135]:    Epoch 194 (0.01946 sec) Train Loss: 0.397349 Train Acc: 0.957143 Val Loss: 0.740313 Val Acc: 0.820000
[INFO] 2020-11-24 17:38:21,985 [    train.py:  135]:    Epoch 195 (0.01946 sec) Train Loss: 0.423486 Train Acc: 0.921429 Val Loss: 0.739777 Val Acc: 0.820000
[INFO] 2020-11-24 17:38:22,016 [    train.py:  135]:    Epoch 196 (0.01946 sec) Train Loss: 0.453004 Train Acc: 0.935714 Val Loss: 0.738899 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:22,046 [    train.py:  135]:    Epoch 197 (0.01945 sec) Train Loss: 0.427575 Train Acc: 0.950000 Val Loss: 0.738128 Val Acc: 0.820000
[INFO] 2020-11-24 17:38:22,076 [    train.py:  135]:    Epoch 198 (0.01945 sec) Train Loss: 0.438130 Train Acc: 0.935714 Val Loss: 0.736901 Val Acc: 0.820000
[INFO] 2020-11-24 17:38:22,107 [    train.py:  135]:    Epoch 199 (0.01945 sec) Train Loss: 0.390269 Train Acc: 0.935714 Val Loss: 0.736106 Val Acc: 0.816667
[INFO] 2020-11-24 17:38:22,119 [    train.py:  143]:    Accuracy: 0.809000

至此科平，CUDA、cuDNN姜性、PaddlePaddle-GPU瞪慧、PGL全部安裝完畢。

最后編輯于 ：
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請聯(lián)系作者
  • 人面猴
    序言：七十年代末部念，一起剝皮案震驚了整個濱河市弃酌，隨后出現(xiàn)的幾起案子，更是在濱河造成了極大的恐慌儡炼，老刑警劉巖妓湘，帶你破解...
    沈念sama閱讀 206,013評論 6贊 481
  • 死咒
    序言：濱河連續(xù)發(fā)生了三起死亡事件，死亡現(xiàn)場離奇詭異乌询，居然都是意外死亡榜贴，警方通過查閱死者的電腦和手機(jī)，發(fā)現(xiàn)死者居然都...
    沈念sama閱讀 88,205評論 2贊 382
  • 救了他兩次的神仙讓他今天三更去死
    文/潘曉璐 我一進(jìn)店門妹田，熙熙樓的掌柜王于貴愁眉苦臉地迎上來唬党，“玉大人，你說我怎么就攤上這事鬼佣∈还埃” “怎么了？”我有些...
    開封第一講書人閱讀 152,370評論 0贊 342
  • 道士緝兇錄：失蹤的賣姜人
    文/不壞的土叔 我叫張陵晶衷，是天一觀的道長蓝纲。 經(jīng)常有香客問我，道長晌纫，這世上最難降的妖魔是什么税迷？ 我笑而不...
    開封第一講書人閱讀 55,168評論 1贊 278
  • ?港島之戀（遺憾婚禮）
    正文 為了忘掉前任，我火速辦了婚禮缸匪，結(jié)果婚禮上翁狐，老公的妹妹穿的比我還像新娘。我一直安慰自己凌蔬，他們只是感情好露懒，可當(dāng)我...
    茶點(diǎn)故事閱讀 64,153評論 5贊 371
  • 惡毒庶女頂嫁案：這布局不是一般人想出來的
    文/花漫 我一把揭開白布闯冷。 她就那樣靜靜地躺著，像睡著了一般懈词。 火紅的嫁衣襯著肌膚如雪蛇耀。 梳的紋絲不亂的頭發(fā)上，一...
    開封第一講書人閱讀 48,954評論 1贊 283
  • 城市分裂傳說
    那天坎弯，我揣著相機(jī)與錄音纺涤，去河邊找鬼。 笑死抠忘，一個胖子當(dāng)著我的面吹牛撩炊，可吹牛的內(nèi)容都是我干的。 我是一名探鬼主播崎脉，決...
    沈念sama閱讀 38,271評論 3贊 399
  • 雙鴛鴦連環(huán)套：你想象不到人心有多黑
    文/蒼蘭香墨 我猛地睜開眼拧咳，長吁一口氣：“原來是場噩夢啊……” “哼！你這毒婦竟也來了囚灼？” 一聲冷哼從身側(cè)響起骆膝，我...
    開封第一講書人閱讀 36,916評論 0贊 259
  • 萬榮殺人案實(shí)錄
    序言：老撾萬榮一對情侶失蹤，失蹤者是張志新（化名）和其女友劉穎灶体，沒想到半個月后阅签，有當(dāng)?shù)厝嗽跇淞掷锇l(fā)現(xiàn)了一具尸體，經(jīng)...
    沈念sama閱讀 43,382評論 1贊 300
  • ?護(hù)林員之死
    正文 獨(dú)居荒郊野嶺守林人離奇死亡蝎抽，尸身上長有42處帶血的膿包…… 初始之章·張勛 以下內(nèi)容為張勛視角 年9月15日...
    茶點(diǎn)故事閱讀 35,877評論 2贊 323
  • ?白月光啟示錄
    正文 我和宋清朗相戀三年政钟，在試婚紗的時候發(fā)現(xiàn)自己被綠了。 大學(xué)時的朋友給我發(fā)了我未婚夫和他白月光在一起吃飯的照片织中。...
    茶點(diǎn)故事閱讀 37,989評論 1贊 333
  • 活死人
    序言：一個原本活蹦亂跳的男人離奇死亡锥涕，死狀恐怖，靈堂內(nèi)的尸體忽然破棺而出狭吼，到底是詐尸還是另有隱情层坠，我是刑警寧澤，帶...
    沈念sama閱讀 33,624評論 4贊 322
  • ?日本核電站爆炸內(nèi)幕
    正文 年R本政府宣布刁笙，位于F島的核電站破花，受9級特大地震影響，放射性物質(zhì)發(fā)生泄漏疲吸。R本人自食惡果不足惜座每，卻給世界環(huán)境...
    茶點(diǎn)故事閱讀 39,209評論 3贊 307
  • 男人毒藥：我在死后第九天來索命
    文/蒙蒙 一、第九天 我趴在偏房一處隱蔽的房頂上張望摘悴。 院中可真熱鬧峭梳，春花似錦、人聲如沸。這莊子的主人今日做“春日...
    開封第一講書人閱讀 30,199評論 0贊 19
  • 一樁弒父案捂寿，背后竟有這般陰謀
    文/蒼蘭香墨 我抬頭看了看天上的太陽。三九已至孵运，卻和暖如春秦陋，著一層夾襖步出監(jiān)牢的瞬間，已是汗流浹背治笨。 一陣腳步聲響...
    開封第一講書人閱讀 31,418評論 1贊 260
  • 情欲美人皮
    我被黑心中介騙來泰國打工驳概， 沒想到剛下飛機(jī)就差點(diǎn)兒被人妖公主榨干…… 1. 我叫王不留，地道東北人旷赖。 一個月前我還...
    沈念sama閱讀 45,401評論 2贊 352
  • 代替公主和親
    正文 我出身青樓顺又，卻偏偏與公主長得像，于是被迫代替她去往敵國和親杠愧。 傳聞我的和親對象是個殘疾皇子待榔，可洞房花燭夜當(dāng)晚...
    茶點(diǎn)故事閱讀 42,700評論 2贊 345