win10 CPU版，anaconda prompt命令行一句话，pip install --upgrade tensorflow搞定。比caffe好装一万倍。
gpu版没装成，首先这个笔记本没装cuda,另外一个台式装好了cuda8.0和cunn5.1也是报一样的错误，缺少一个setuptool.egg
命令行如下：
1 (D:\Users\song\Anaconda3) C:\SPB_Data>python --version 2 Python 3.6.0 :: Anaconda 4.3.1 (64-bit) 3 4 (D:\Users\song\Anaconda3) C:\SPB_Data>pip -V 5 pip 9.0.1 from D:\Users\song\Anaconda3\lib\site-packages (python 3.6) 6 7 (D:\Users\song\Anaconda3) C:\SPB_Data>pip3 install --upgrade tensorflow-gpu 8 'pip3' 不是内部或外部命令，也不是可运行的程序 9 或批处理文件。 10 11 (D:\Users\song\Anaconda3) C:\SPB_Data>pip install --upgrade tensorflow-gpu 12 Collecting tensorflow-gpu 13 Downloading tensorflow_gpu-1.3.0-cp36-cp36m-win_amd64.whl (60.0MB) 14 100% |████████████████████████████████| 60.0MB 16kB/s 15 Collecting numpy>=1.11.0 (from tensorflow-gpu) 16 Downloading numpy-1.13.3-cp36-none-win_amd64.whl (13.1MB) 17 100% |████████████████████████████████| 13.1MB 73kB/s 18 Collecting protobuf>=3.3.0 (from tensorflow-gpu) 19 Downloading protobuf-3.4.0-py2.py3-none-any.whl (375kB) 20 100% |████████████████████████████████| 378kB 667kB/s 21 Collecting wheel>=0.26 (from tensorflow-gpu) 22 Downloading wheel-0.30.0-py2.py3-none-any.whl (49kB) 23 100% |████████████████████████████████| 51kB 371kB/s 24 Collecting tensorflow-tensorboard<0.2.0,>=0.1.0 (from tensorflow-gpu) 25 Downloading tensorflow_tensorboard-0.1.8-py3-none-any.whl (1.6MB) 26 100% |████████████████████████████████| 1.6MB 413kB/s 27 Collecting six>=1.10.0 (from tensorflow-gpu) 28 Downloading six-1.11.0-py2.py3-none-any.whl 29 Collecting setuptools (from protobuf>=3.3.0->tensorflow-gpu) 30 Downloading setuptools-36.6.0-py2.py3-none-any.whl (481kB) 31 100% |████████████████████████████████| 481kB 734kB/s 32 Collecting bleach==1.5.0 (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow-gpu) 33 Downloading bleach-1.5.0-py2.py3-none-any.whl 34 Collecting werkzeug>=0.11.10 (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow-gpu) 35 Downloading Werkzeug-0.12.2-py2.py3-none-any.whl (312kB) 36 100% |████████████████████████████████| 317kB 1.7MB/s 37 Collecting html5lib==0.9999999 (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow-gpu) 38 Downloading html5lib-0.9999999.tar.gz (889kB) 39 100% |████████████████████████████████| 890kB 502kB/s 40 Collecting markdown>=2.6.8 (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow-gpu) 41 Downloading Markdown-2.6.9.tar.gz (271kB) 42 100% |████████████████████████████████| 276kB 687kB/s 43 Building wheels for collected packages: html5lib, markdown 44 Running setup.py bdist_wheel for html5lib ... done 45 Stored in directory: C:\Users\song\AppData\Local\pip\Cache\wheels\6f\85\6c\56b8e1292c6214c4eb73b9dda50f53e8e977bf65989373c962 46 Running setup.py bdist_wheel for markdown ... done 47 Stored in directory: C:\Users\song\AppData\Local\pip\Cache\wheels\bf\46\10\c93e17ae86ae3b3a919c7b39dad3b5ccf09aeb066419e5c1e5 48 Successfully built html5lib markdown 49 Installing collected packages: numpy, setuptools, six, protobuf, wheel, html5lib, bleach, werkzeug, markdown, tensorflow-tensorboard, tensorflow-gpu 50 Found existing installation: numpy 1.11.3 51 Uninstalling numpy-1.11.3: 52 Successfully uninstalled numpy-1.11.3 53 Found existing installation: setuptools 27.2.0 54 Uninstalling setuptools-27.2.0: 55 Successfully uninstalled setuptools-27.2.0 56 Found existing installation: six 1.10.0 57 DEPRECATION: Uninstalling a distutils installed project (six) has been deprecated and will be removed in a future version. This is due to the fact that uninstalling a distutils project will only partially uninstall the project. 58 Uninstalling six-1.10.0: 59 Successfully uninstalled six-1.10.0 60 Found existing installation: wheel 0.29.0 61 Uninstalling wheel-0.29.0: 62 Successfully uninstalled wheel-0.29.0 63 Found existing installation: Werkzeug 0.11.15 64 Uninstalling Werkzeug-0.11.15: 65 Successfully uninstalled Werkzeug-0.11.15 66 Successfully installed bleach-1.5.0 html5lib-0.9999999 markdown-2.6.9 numpy-1.13.3 protobuf-3.4.0 setuptools-36.6.0 six-1.11.0 tensorflow-gpu-1.3.0 tensorflow-tensorboard-0.1.8 werkzeug-0.12.2 wheel-0.30.0 67 Traceback (most recent call last): 68 File "D:\Users\song\Anaconda3\Scripts\pip-script.py", line 5, in <module> 69 sys.exit(pip.main()) 70 File "D:\Users\song\Anaconda3\lib\site-packages\pip\__init__.py", line 249, in main 71 return command.main(cmd_args) 72 File "D:\Users\song\Anaconda3\lib\site-packages\pip\basecommand.py", line 252, in main 73 pip_version_check(session) 74 File "D:\Users\song\Anaconda3\lib\site-packages\pip\utils\outdated.py", line 102, in pip_version_check 75 installed_version = get_installed_version("pip") 76 File "D:\Users\song\Anaconda3\lib\site-packages\pip\utils\__init__.py", line 838, in get_installed_version 77 working_set = pkg_resources.WorkingSet() 78 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 644, in __init__ 79 self.add_entry(entry) 80 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 700, in add_entry 81 for dist in find_distributions(entry, True): 82 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 1949, in find_eggs_in_zip 83 if metadata.has_metadata('PKG-INFO'): 84 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 1463, in has_metadata 85 return self.egg_info and self._has(self._fn(self.egg_info, name)) 86 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 1823, in _has 87 return zip_path in self.zipinfo or zip_path in self._index() 88 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 1703, in zipinfo 89 return self._zip_manifests.load(self.loader.archive) 90 File "D:\Users\song\Anaconda3\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 1643, in load 91 mtime = os.stat(path).st_mtime 92 FileNotFoundError: [WinError 2] 系统找不到指定的文件。: 'D:\\Users\\song\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg' 93 94 (D:\Users\song\Anaconda3) C:\SPB_Data>cd .. 95 96 (D:\Users\song\Anaconda3) C:\>cd .. 97 98 (D:\Users\song\Anaconda3) C:\>ls 99 'ls' 不是内部或外部命令，也不是可运行的程序 100 或批处理文件。 101 102 (D:\Users\song\Anaconda3) C:\>python --version 103 Python 3.6.0 :: Anaconda 4.3.1 (64-bit) 104 105 (D:\Users\song\Anaconda3) C:\>nvcc -V 106 'nvcc' 不是内部或外部命令，也不是可运行的程序 107 或批处理文件。 108 109 (D:\Users\song\Anaconda3) C:\>pip install --upgrade tensorflow 110 Collecting tensorflow 111 Downloading tensorflow-1.3.0-cp36-cp36m-win_amd64.whl (25.5MB) 112 100% |████████████████████████████████| 25.5MB 29kB/s 113 Requirement already up-to-date: protobuf>=3.3.0 in d:\users\song\anaconda3\lib\site-packages (from tensorflow) 114 Requirement already up-to-date: wheel>=0.26 in d:\users\song\anaconda3\lib\site-packages (from tensorflow) 115 Requirement already up-to-date: tensorflow-tensorboard<0.2.0,>=0.1.0 in d:\users\song\anaconda3\lib\site-packages (from tensorflow) 116 Requirement already up-to-date: six>=1.10.0 in d:\users\song\anaconda3\lib\site-packages (from tensorflow) 117 Requirement already up-to-date: numpy>=1.11.0 in d:\users\song\anaconda3\lib\site-packages (from tensorflow) 118 Requirement already up-to-date: setuptools in d:\users\song\anaconda3\lib\site-packages (from protobuf>=3.3.0->tensorflow) 119 Requirement already up-to-date: markdown>=2.6.8 in d:\users\song\anaconda3\lib\site-packages (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow) 120 Requirement already up-to-date: bleach==1.5.0 in d:\users\song\anaconda3\lib\site-packages (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow) 121 Requirement already up-to-date: html5lib==0.9999999 in d:\users\song\anaconda3\lib\site-packages (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow) 122 Requirement already up-to-date: werkzeug>=0.11.10 in d:\users\song\anaconda3\lib\site-packages (from tensorflow-tensorboard<0.2.0,>=0.1.0->tensorflow) 123 Installing collected packages: tensorflow 124 Successfully installed tensorflow-1.3.0 125 126 (D:\Users\song\Anaconda3) C:\>import tensorflow as tf 127 'import' 不是内部或外部命令，也不是可运行的程序 128 或批处理文件。 129 130 (D:\Users\song\Anaconda3) C:\>python 131 Python 3.6.0 |Anaconda 4.3.1 (64-bit)| (default, Dec 23 2016, 11:57:41) [MSC v.1900 64 bit (AMD64)] on win32 132 Type "help", "copyright", "credits" or "license" for more information. 133 >>> import tensorflow as tf 134 >>> a = tf.random_normal((100,100)) 135 >>> b = tf.random_normal((100,500)) 136 >>> c=tf.matmul(a,b) 137 >>> sess=tf.InteractiveSession() 138 2017-10-29 20:46:03.615036: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. 139 2017-10-29 20:46:03.620666: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations. 140 >>> sess.run(c) 141 array([[ -2.01546478e+01, -1.21840429e+01, 8.52634966e-01, ..., 142 -1.93460350e+01, -1.17136412e+01, -2.81856956e+01], 143 [ -2.86180496e+00, 1.86777287e+01, 2.39728212e-01, ..., 144 1.65606441e+01, -8.35585117e+00, 1.21092701e+01], 145 [ -6.70668936e+00, -1.92020512e+00, -8.63678837e+00, ..., 146 1.19851971e+01, -1.95774388e+00, -3.46706104e+00], 147 ..., 148 [ -6.20419502e+00, -1.58898029e+01, 1.47155542e+01, ..., 149 -6.35781908e+00, -7.09256840e+00, 1.04180880e+01], 150 [ -1.14867371e-03, -2.47349381e+00, 1.40450490e+00, ..., 151 1.87805653e+00, 7.70393276e+00, -1.11452806e+00], 152 [ -1.81114292e+01, 2.83652916e+01, 2.23067703e+01, ..., 153 4.72095060e+00, 2.01743245e+00, 9.46466255e+00]], dtype=float32) 154 >>> c 155 <tf.Tensor 'MatMul:0' shape=(100, 500) dtype=float32> 156 >>> print(c) 157 Tensor("MatMul:0", shape=(100, 500), dtype=float32) 158 >>> print(c.val) 159 Traceback (most recent call last): 160 File "<stdin>", line 1, in <module> 161 AttributeError: 'Tensor' object has no attribute 'val' 162 >>> print(c.eval()) 163 [[ 7.44645548e+00 7.01777339e-01 -3.29522681e+00 ..., -4.11035490e+00 164 6.88585615e+00 -1.03243275e+01] 165 [ 1.74935007e+00 -8.06512642e+00 -8.94767094e+00 ..., -8.51691341e+00 166 -6.86603403e+00 9.46757889e+00] 167 [ -6.61030436e+00 5.86357307e+00 1.51259956e+01 ..., -9.53737926e+00 168 1.95381641e-02 1.16717541e+00] 169 ..., 170 [ -5.34449625e+00 1.13798809e+00 1.34737101e+01 ..., 6.86746025e+00 171 3.37234330e+00 -9.16017354e-01] 172 [ -3.89829564e+00 1.19947767e+00 9.16424465e+00 ..., 7.61591375e-01 173 -1.70225441e-01 1.02892227e+01] 174 [ 1.97680518e-01 -1.99925423e+01 -9.40755844e+00 ..., 5.44214249e+00 175 1.52138865e+00 2.48984170e+00]] 176 >>> print(a) 177 Tensor("random_normal:0", shape=(100, 100), dtype=float32) 178 >>> sess=tf.InteractiveSession() 179 >>> print(sess.run(a)) 180 [[-1.394485 -1.95048952 0.76553309 ..., -0.43924141 -1.21975422 181 0.60572529] 182 [ 0.34292024 0.86016667 -2.25437665 ..., 1.67957187 1.57846153 183 -1.53106809] 184 [ 0.08453497 0.59995687 -1.37805259 ..., -0.92989731 -0.07856822 185 -1.36062932] 186 ..., 187 [-0.41187105 0.60689414 -0.44695681 ..., 0.51408201 -1.49676847 188 0.95741159] 189 [-1.01903558 -1.24220276 0.12283699 ..., 0.53144586 -0.2782338 190 0.34964591] 191 [ 0.27783027 0.5017578 -1.0619179 ..., 0.4974283 -0.04771407 192 0.48028085]] 193 >>> ls 194 Traceback (most recent call last): 195 File "<stdin>", line 1, in <module> 196 NameError: name 'ls' is not defined 197 >>> exit() 198 199 (D:\Users\song\Anaconda3) C:\>e:\ 200 'e:\' 不是内部或外部命令，也不是可运行的程序 201 或批处理文件。 202 203 (D:\Users\song\Anaconda3) C:\>cd e:\ 204 205 (D:\Users\song\Anaconda3) C:\>python minst.py 206 File "minst.py", line 16 207 SyntaxError: Non-UTF-8 code starting with '\xb0' in file minst.py on line 16, but no encoding declared; see http://python.org/dev/peps/pep-0263/ for details 208 209 (D:\Users\song\Anaconda3) C:\>python minst.py 210 File "minst.py", line 16 211 SyntaxError: Non-UTF-8 code starting with '\xb0' in file minst.py on line 16, but no encoding declared; see http://python.org/dev/peps/pep-0263/ for details 212 213 (D:\Users\song\Anaconda3) C:\>python minst.py 214 File "minst.py", line 16 215 SyntaxError: Non-UTF-8 code starting with '\xb0' in file minst.py on line 16, but no encoding declared; see http://python.org/dev/peps/pep-0263/ for details 216 217 (D:\Users\song\Anaconda3) C:\>python 218 Python 3.6.0 |Anaconda 4.3.1 (64-bit)| (default, Dec 23 2016, 11:57:41) [MSC v.1900 64 bit (AMD64)] on win32 219 Type "help", "copyright", "credits" or "license" for more information. 220 >>> import tensorflow as tf 221 >>> flags = tf.app.flags 222 >>> FLAGS = flags.FLAGS 223 >>> flags.DEFINE_string('data_dir', '/tmp/data/', 'Directory for storing data') 224 >>> 225 >>> mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True) 226 Traceback (most recent call last): 227 File "<stdin>", line 1, in <module> 228 NameError: name 'input_data' is not defined 229 >>> from __future__ import absolute_import 230 >>> from __future__ import division 231 >>> from __future__ import print_function 232 >>> from tensorflow.examples.tutorials.mnist import input_data 233 >>> 234 >>> mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True) 235 Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes. 236 Extracting /tmp/data/train-images-idx3-ubyte.gz 237 Traceback (most recent call last): 238 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 1318, in do_open 239 encode_chunked=req.has_header('Transfer-encoding')) 240 File "D:\Users\song\Anaconda3\lib\http\client.py", line 1239, in request 241 self._send_request(method, url, body, headers, encode_chunked) 242 File "D:\Users\song\Anaconda3\lib\http\client.py", line 1285, in _send_request 243 self.endheaders(body, encode_chunked=encode_chunked) 244 File "D:\Users\song\Anaconda3\lib\http\client.py", line 1234, in endheaders 245 self._send_output(message_body, encode_chunked=encode_chunked) 246 File "D:\Users\song\Anaconda3\lib\http\client.py", line 1026, in _send_output 247 self.send(msg) 248 File "D:\Users\song\Anaconda3\lib\http\client.py", line 964, in send 249 self.connect() 250 File "D:\Users\song\Anaconda3\lib\http\client.py", line 1400, in connect 251 server_hostname=server_hostname) 252 File "D:\Users\song\Anaconda3\lib\ssl.py", line 401, in wrap_socket 253 _context=self, _session=session) 254 File "D:\Users\song\Anaconda3\lib\ssl.py", line 808, in __init__ 255 self.do_handshake() 256 File "D:\Users\song\Anaconda3\lib\ssl.py", line 1061, in do_handshake 257 self._sslobj.do_handshake() 258 File "D:\Users\song\Anaconda3\lib\ssl.py", line 683, in do_handshake 259 self._sslobj.do_handshake() 260 ssl.SSLEOFError: EOF occurred in violation of protocol (_ssl.c:749) 261 262 During handling of the above exception, another exception occurred: 263 264 Traceback (most recent call last): 265 File "<stdin>", line 1, in <module> 266 File "D:\Users\song\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py", line 240, in read_data_sets 267 SOURCE_URL + TRAIN_LABELS) 268 File "D:\Users\song\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\base.py", line 208, in maybe_download 269 temp_file_name, _ = urlretrieve_with_retry(source_url) 270 File "D:\Users\song\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\base.py", line 165, in wrapped_fn 271 return fn(*args, **kwargs) 272 File "D:\Users\song\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\base.py", line 190, in urlretrieve_with_retry 273 return urllib.request.urlretrieve(url, filename) 274 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 248, in urlretrieve 275 with contextlib.closing(urlopen(url, data)) as fp: 276 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 223, in urlopen 277 return opener.open(url, data, timeout) 278 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 526, in open 279 response = self._open(req, data) 280 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 544, in _open 281 '_open', req) 282 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 504, in _call_chain 283 result = func(*args) 284 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 1361, in https_open 285 context=self._context, check_hostname=self._check_hostname) 286 File "D:\Users\song\Anaconda3\lib\urllib\request.py", line 1320, in do_open 287 raise URLError(err) 288 urllib.error.URLError: <urlopen error EOF occurred in violation of protocol (_ssl.c:749)> 289 >>> import requests 290 >>> >>> from requests.adapters import HTTPAdapter 291 File "<stdin>", line 1 292 >>> from requests.adapters import HTTPAdapter 293 ^ 294 SyntaxError: invalid syntax 295 >>> >>> from requests.packages.urllib3.poolmanager import PoolManager 296 File "<stdin>", line 1 297 >>> from requests.packages.urllib3.poolmanager import PoolManager 298 ^ 299 SyntaxError: invalid syntax 300 >>> >>> import ssl 301 File "<stdin>", line 1 302 >>> import ssl 303 ^ 304 SyntaxError: invalid syntax 305 >>> >>> 306 File "<stdin>", line 1 307 >>> 308 ^ 309 SyntaxError: invalid syntax 310 >>> >>> class MyAdapter(HTTPAdapter): 311 File "<stdin>", line 1 312 >>> class MyAdapter(HTTPAdapter): 313 ^ 314 SyntaxError: invalid syntax 315 >>> ... def init_poolmanager(self, connections, maxsize, block=False): 316 File "<stdin>", line 1 317 ... def init_poolmanager(self, connections, maxsize, block=False): 318 ^ 319 SyntaxError: invalid syntax 320 >>> ... self.poolmanager = PoolManager(num_pools=connections, 321 File "<stdin>", line 1 322 ... self.poolmanager = PoolManager(num_pools=connections, 323 ^ 324 SyntaxError: invalid syntax 325 >>> ... maxsize=maxsize, 326 File "<stdin>", line 1 327 ... maxsize=maxsize, 328 ^ 329 SyntaxError: invalid syntax 330 >>> ... block=block, 331 File "<stdin>", line 1 332 ... block=block, 333 ^ 334 SyntaxError: invalid syntax 335 >>> ... ssl_version=ssl.PROTOCOL_TLSv1) 336 File "<stdin>", line 1 337 ... ssl_version=ssl.PROTOCOL_TLSv1) 338 ^ 339 SyntaxError: invalid syntax 340 >>> ... 341 Ellipsis 342 >>> >>> s = requests.Session() 343 File "<stdin>", line 1 344 >>> s = requests.Session() 345 ^ 346 SyntaxError: invalid syntax 347 >>> >>> s.mount('https://', MyAdapter()) 348 File "<stdin>", line 1 349 >>> s.mount('https://', MyAdapter()) 350 ^ 351 SyntaxError: invalid syntax 352 >>> >>> s.get('https://www.supercash.cz') 353 File "<stdin>", line 1 354 >>> s.get('https://www.supercash.cz') 355 ^ 356 SyntaxError: invalid syntax 357 >>> <Response [200]> 358 File "<stdin>", line 1 359 <Response [200]> 360 ^ 361 SyntaxError: invalid syntax 362 >>> mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True) 363 Extracting /tmp/data/train-images-idx3-ubyte.gz 364 Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes. 365 Extracting /tmp/data/train-labels-idx1-ubyte.gz 366 Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes. 367 Extracting /tmp/data/t10k-images-idx3-ubyte.gz 368 Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes. 369 Extracting /tmp/data/t10k-labels-idx1-ubyte.gz 370 >>> x = tf.placeholder(tf.float32, [None, 784]) # 占位符 371 >>> y = tf.placeholder(tf.float32, [None, 10]) 372 >>> W = tf.Variable(tf.zeros([784, 10])) 373 >>> b = tf.Variable(tf.zeros([10])) 374 >>> a = tf.nn.softmax(tf.matmul(x, W) + b) 375 >>> cross_entropy = tf.reduce_mean(-tf.reduce_sum(y * tf.log(a), reduction_indices=[1])) # 损失函数为交叉熵 376 >>> optimizer = tf.train.GradientDescentOptimizer(0.5) # 梯度下降法，学习速率为0.5 377 >>> train = optimizer.minimize(cross_entropy) # 训练目标：最小化损失函数 378 >>> 379 >>> # Test trained model 380 ... correct_prediction = tf.equal(tf.argmax(a, 1), tf.argmax(y, 1)) 381 >>> accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 382 >>> correct_prediction = tf.equal(tf.argmax(a, 1), tf.argmax(y, 1)) 383 >>> accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 384 >>> sess = tf.InteractiveSession() # 建立交互式会话 385 2017-10-29 21:28:03.960497: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. 386 2017-10-29 21:28:03.968465: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations. 387 >>> tf.initialize_all_variables().run() 388 WARNING:tensorflow:From D:\Users\song\Anaconda3\lib\site-packages\tensorflow\python\util\tf_should_use.py:175: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02. 389 Instructions for updating: 390 Use `tf.global_variables_initializer` instead. 391 >>> for i in range(1000): 392 ... batch_xs, batch_ys = mnist.train.next_batch(100) 393 ... train.run({x: batch_xs, y: batch_ys}) 394 ... print(sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})) 395 File "<stdin>", line 4 396 print(sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})) 397 ^ 398 SyntaxError: invalid syntax 399 >>> tf.initialize_all_variables().run() 400 WARNING:tensorflow:From D:\Users\song\Anaconda3\lib\site-packages\tensorflow\python\util\tf_should_use.py:175: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02. 401 Instructions for updating: 402 Use `tf.global_variables_initializer` instead. 403 >>> tf.global_variables_initializer().run() 404 >>> for i in range(1000): 405 ... batch_xs, batch_ys = mnist.train.next_batch(100) 406 ... train.run({x: batch_xs, y: batch_ys}) 407 ... 408 >>> print(sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})) 409 0.9154 410 >>>
----------2018.02.10 另外一台ubuntu服务器，tensorflow已装好，python能import--------------
python -c 'import tensorflow as tf; print(tf.__version__)'
或：
>>> tf.__version__
>>> tf.__path__
使用TensorFlow-Slim App:
github上models/research/slim目录下的README有详细说明。
python download_and_convert_data.py --dataset_name=flowers --dataset_dir="/home/.../data/"
等一会儿就下载好了，ls /home/.../data可看到：
新建creatingTFSlimDataset.py写入：
1 import tensorflow as tf 2 from datasets import flowers 3 4 slim = tf.contrib.slim 5 6 # Selects the 'validation' dataset. 7 dataset = flowers.get_split('validation', "/home/.../data/") 8 9 # Creates a TF-Slim DataProvider which reads the dataset in the background 10 # during both training and testing. 11 provider = slim.dataset_data_provider.DatasetDataProvider(dataset) 12 [image, label] = provider.get(['image', 'label'])
在slim目录下python creatingTFSlimDataset.py
----------2018.02.11 macbook pro--------------
mac os安装参考官网和教程，每次打开命令行，进入tf目录执行
source bin/activate
进入；执行 deactivate退出tensorflow环境。
----------2018.02.11 用自己的数据集训练cnn----------
代码完全是来自这里，写一个python脚本，把作者的代码贴进去，文件前后分别加上：
import os
import numpy as np
import tensorflow as tf
if __name__ == '__main__':
run_training()
这里要么把run_trainning()里的inputData、model等删掉，要么拆成几个.py分别import。
在run_training()里指向自己的数据，作者代码支持2分类，建两个目录，名字分别为0，1，下边直接放图像数据，不能放其他东西。
目录下python xx.py运行，总是报莫名其妙的错误，如下：
2018-02-11 16:14:27.688087: W tensorflow/core/framework/op_kernel.cc:1188] Unimplemented: Cast float to string is not supported
2018-02-11 16:14:27.691410: W tensorflow/core/framework/op_kernel.cc:1188] Unimplemented: Cast float to string is not supported
2018-02-11 16:14:27.700514: W tensorflow/core/framework/op_kernel.cc:1188] Unimplemented: Cast float to string is not supported
2018-02-11 16:14:27.700547: E tensorflow/core/common_runtime/executor.cc:651] Executor failed to create kernel. Unimplemented: Cast float to string is not supported
[[Node: Cast = Cast[DstT=DT_STRING, SrcT=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Cast/x)]]
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected image (JPEG, PNG, or GIF), got unknown format starting with '\000\000\000\001Bud1\000\000(\000\000\000\010\000'
参考这里解决，主要是mac os每个目录下会生成一个.DS_Store隐藏文件，并且每个目录都有，然后get_files里的for in os.listdir(filename+train_class)会把这个不是目录的文件也读进来，用命令：
ls -d .* //显示目录下的隐藏文件
rm .DS_Store //删除
暴力删除所有DS_Store，就可以运行了：
1 (tf) ...$ python selfDataTest.py 2 2018-02-11 16:29:32.737708: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.2 AVX AVX2 FMA 3 0 4 loss:0.693223297596 accuracy:0.5 5 1 6 loss:0.693074345589 accuracy:0.5 7 2 8 loss:0.697106897831 accuracy:0.25 9 3 10 loss:0.693120956421 accuracy:0.5 11 4 12 loss:0.693217039108 accuracy:0.5 13 5 14 loss:0.693105101585 accuracy:0.5 15 6 16 loss:0.696964502335 accuracy:0.25 17 7 18 loss:0.689658999443 accuracy:0.75 19 8 20 loss:0.689396262169 accuracy:0.75 21 9 22 loss:0.689066112041 accuracy:0.75 23 10 24 loss:0.688840508461 accuracy:0.75 25 11 26 loss:0.693139314651 accuracy:0.5 27 12 28 loss:0.683785676956 accuracy:1.0 29 13 30 loss:0.703975439072 accuracy:0.0 31 14 32 loss:0.68853032589 accuracy:0.75 33 15 34 loss:0.698201835155 accuracy:0.25 35 16 36 loss:0.68848156929 accuracy:0.75 37 17 38 loss:0.698279738426 accuracy:0.25 39 18 40 loss:0.693163573742 accuracy:0.5 41 19 42 loss:0.6931681633 accuracy:0.5 43 20 44 loss:0.683992028236 accuracy:1.0 45 21 46 loss:0.693161666393 accuracy:0.5 47 22 48 loss:0.698703587055 accuracy:0.25 49 23 50 loss:0.693104684353 accuracy:0.5 51 24 52 loss:0.68318516016 accuracy:1.0 53 25 54 loss:0.699333965778 accuracy:0.25 55 26 56 loss:0.693171679974 accuracy:0.5 57 27 58 loss:0.687688589096 accuracy:0.75 59 28 60 loss:0.699294626713 accuracy:0.25 61 29 62 loss:0.698648869991 accuracy:0.25 63 30 64 loss:0.697887659073 accuracy:0.25 65 31 66 loss:0.697125077248 accuracy:0.25 67 32 68 loss:0.693179786205 accuracy:0.5 69 33 70 loss:0.690038383007 accuracy:0.75 71 34 72 loss:0.693158328533 accuracy:0.5 73 35 74 loss:0.693139135838 accuracy:0.5 75 36 76 loss:0.693126440048 accuracy:0.5 77 37 78 loss:0.6970089674 accuracy:0.25 79 38 80 loss:0.693112254143 accuracy:0.5 81 39 82 loss:0.696039140224 accuracy:0.25 83 40 84 loss:0.691227436066 accuracy:0.75 85 41 86 loss:0.6871124506 accuracy:1.0 87 42 88 loss:0.698171555996 accuracy:0.25 89 43 90 loss:0.693155050278 accuracy:0.5 91 44 92 loss:0.693078219891 accuracy:0.5 93 45 94 loss:0.700998663902 accuracy:0.0 95 46 96 loss:0.69156730175 accuracy:0.75 97 47 98 loss:0.693068742752 accuracy:0.5 99 48 100 loss:0.69571262598 accuracy:0.25 101 49 102 loss:0.694398403168 accuracy:0.25 103 50 104 loss:0.692993998528 accuracy:0.75 105 51 106 loss:0.69304227829 accuracy:0.75 107 52 108 loss:0.691499948502 accuracy:0.75 109 53 110 loss:0.699331462383 accuracy:0.0 111 54 112 loss:0.693157672882 accuracy:0.25 113 55 114 loss:0.693060457706 accuracy:0.5 115 56 116 loss:0.694615125656 accuracy:0.25 117 57 118 loss:0.693363189697 accuracy:0.25 119 58 120 loss:0.693014979362 accuracy:0.5 121 59 122 loss:0.694661080837 accuracy:0.25 123 60 124 loss:0.693545818329 accuracy:0.25 125 61 126 loss:0.693045854568 accuracy:0.5 127 62 128 loss:0.693035364151 accuracy:0.5 129 63 130 loss:0.694476723671 accuracy:0.25 131 64 132 loss:0.692974746227 accuracy:0.5 133 65 134 loss:0.692882657051 accuracy:0.5 135 66 136 loss:0.693762481213 accuracy:0.25 137 67 138 loss:0.690908133984 accuracy:0.75 139 68 140 loss:0.702915489674 accuracy:0.0 141 69 142 loss:0.692815005779 accuracy:0.5 143 70 144 loss:0.694090306759 accuracy:0.25 145 71 146 loss:0.690848052502 accuracy:0.75 147 72 148 loss:0.698566675186 accuracy:0.25 149 73 150 loss:0.689132213593 accuracy:1.0 151 74 152 loss:0.675133347511 accuracy:1.0 153 75 154 loss:0.693369984627 accuracy:0.5 155 76 156 loss:0.709350824356 accuracy:0.25 157 77 158 loss:0.693330347538 accuracy:0.5 159 78 160 loss:0.704541862011 accuracy:0.25 161 79 162 loss:0.706527590752 accuracy:0.0 163 80 164 loss:0.692816853523 accuracy:0.5 165 81 166 loss:0.694923400879 accuracy:0.25 167 82 168 loss:0.689839780331 accuracy:0.75 169 83 170 loss:0.70052075386 accuracy:0.25 171 84 172 loss:0.692834496498 accuracy:0.5 173 85 174 loss:0.692559659481 accuracy:0.5 175 86 176 loss:0.695177018642 accuracy:0.25 177 87 178 loss:0.697179615498 accuracy:0.25 179 88 180 loss:0.697944283485 accuracy:0.0 181 89 182 loss:0.682408571243 accuracy:0.75 183 90 184 loss:0.676290035248 accuracy:0.75 185 91 186 loss:0.646753549576 accuracy:1.0 187 92 188 loss:0.657571673393 accuracy:0.75 189 93 190 loss:0.74190735817 accuracy:0.25 191 94 192 loss:0.729316711426 accuracy:0.25 193 95 194 loss:0.668318748474 accuracy:0.75 195 96 196 loss:0.726832032204 accuracy:0.25 197 97 198 loss:0.692601561546 accuracy:0.5 199 98 200 loss:0.692799925804 accuracy:0.5 201 99 202 loss:0.671272993088 accuracy:0.75 203 100 204 loss:0.663210988045 accuracy:0.75 205 101 206 loss:0.69605076313 accuracy:0.5 207 102 208 loss:0.733357787132 accuracy:0.25 209 103 210 loss:0.717833042145 accuracy:0.25 211 104 212 loss:0.691287755966 accuracy:0.5 213 105 214 loss:0.691427409649 accuracy:0.5 215 106 216 loss:0.704467654228 accuracy:0.25 217 107 218 loss:0.689470171928 accuracy:1.0 219 108 220 loss:0.704850375652 accuracy:0.25 221 109 222 loss:0.68930375576 accuracy:1.0 223 110 224 loss:0.690158724785 accuracy:1.0 225 111 226 loss:0.678738832474 accuracy:0.75 227 112 228 loss:0.690320134163 accuracy:0.5 229 113 230 loss:0.685899198055 accuracy:0.5 231 114 232 loss:0.666072010994 accuracy:0.75 233 115 234 loss:0.69532930851 accuracy:0.5 235 116 236 loss:0.67963975668 accuracy:0.5 237 117 238 loss:0.664266467094 accuracy:0.5 239 118 240 loss:0.637705147266 accuracy:1.0 241 119 242 loss:0.639262676239 accuracy:0.75 243 120 244 loss:0.549074888229 accuracy:0.75 245 121 246 loss:0.950685620308 accuracy:0.0 247 122 248 loss:0.649527430534 accuracy:0.75 249 123 250 loss:0.687687039375 accuracy:0.75 251 124 252 loss:0.236011490226 accuracy:1.0 253 125 254 loss:0.360839009285 accuracy:0.75 255 126 256 loss:0.160097658634 accuracy:1.0 257 127 258 loss:0.0284716840833 accuracy:1.0 259 128 260 loss:1.20477676392 accuracy:0.75 261 129 262 loss:0.785823404789 accuracy:0.25 263 130 264 loss:0.596278190613 accuracy:0.75 265 131 266 loss:0.474103331566 accuracy:0.75 267 132 268 loss:0.170581206679 accuracy:1.0 269 133 270 loss:1.17357873917 accuracy:0.5 271 134 272 loss:0.369093000889 accuracy:1.0 273 135 274 loss:0.396817922592 accuracy:0.75 275 136 276 loss:0.53536605835 accuracy:0.75 277 137 278 loss:0.276045441628 accuracy:0.75 279 138 280 loss:0.36287856102 accuracy:0.75 281 139 282 loss:0.196955054998 accuracy:1.0 283 140 284 loss:0.0153374457732 accuracy:1.0 285 141 286 loss:0.0416378080845 accuracy:1.0 287 142 288 loss:1.89024567604 accuracy:0.5 289 143 290 loss:0.512691378593 accuracy:1.0 291 144 292 loss:0.0846931710839 accuracy:1.0 293 145 294 loss:0.330246806145 accuracy:0.75 295 146 296 loss:0.349481493235 accuracy:0.75 297 147 298 loss:0.847968816757 accuracy:0.5 299 148 300 loss:0.320005506277 accuracy:0.75 301 149 302 loss:0.846890568733 accuracy:0.25 303 150 304 loss:0.236197531223 accuracy:1.0 305 151 306 loss:0.0872330516577 accuracy:1.0 307 152 308 loss:0.0432429946959 accuracy:1.0 309 153 310 loss:0.0282921157777 accuracy:1.0 311 154 312 loss:1.17421019077 accuracy:0.75 313 155 314 loss:0.526151418686 accuracy:0.75 315 156 316 loss:0.417270839214 accuracy:0.75 317 157 318 loss:0.537223100662 accuracy:0.75 319 158 320 loss:0.247993305326 accuracy:1.0 321 159 322 loss:0.278814792633 accuracy:1.0 323 160 324 loss:0.0463420078158 accuracy:1.0 325 161 326 loss:0.0170685201883 accuracy:1.0 327 162 328 loss:0.223224148154 accuracy:0.75 329 163 330 loss:0.0268691331148 accuracy:1.0 331 164 332 loss:2.04596710205 accuracy:0.5 333 165 334 loss:0.349981129169 accuracy:1.0 335 166 336 loss:0.812381505966 accuracy:0.5 337 167 338 loss:0.132523924112 accuracy:1.0 339 168 340 loss:0.493652850389 accuracy:0.75 341 169 342 loss:0.328869134188 accuracy:0.75 343 170 344 loss:0.105988666415 accuracy:1.0 345 171 346 loss:0.0751493424177 accuracy:1.0 347 172 348 loss:0.0750939249992 accuracy:1.0 349 173 350 loss:0.304137170315 accuracy:0.75 351 174 352 loss:0.273175984621 accuracy:0.75 353 175 354 loss:0.543058216572 accuracy:0.75 355 176 356 loss:1.90773689747 accuracy:0.5 357 177 358 loss:0.438852667809 accuracy:0.75 359 178 360 loss:0.442263126373 accuracy:0.75 361 179 362 loss:0.429260343313 accuracy:0.75 363 180 364 loss:0.245088890195 accuracy:1.0 365 181 366 loss:0.159963816404 accuracy:1.0 367 182 368 loss:0.039998114109 accuracy:1.0 369 183 370 loss:0.105835229158 accuracy:1.0 371 184 372 loss:0.00809328071773 accuracy:1.0 373 185 374 loss:0.0673048049212 accuracy:1.0 375 186 376 loss:1.13752818108 accuracy:0.75 377 187 378 loss:0.490282326937 accuracy:0.75 379 188 380 loss:1.42135226727 accuracy:0.75 381 189 382 loss:0.288748651743 accuracy:1.0 383 190 384 loss:0.0984246730804 accuracy:1.0 385 191 386 loss:0.123517766595 accuracy:1.0 387 192 388 loss:0.0920013636351 accuracy:1.0 389 193 390 loss:1.44978451729 accuracy:0.75 391 194 392 loss:0.305551946163 accuracy:1.0 393 195 394 loss:0.443002015352 accuracy:0.75 395 196 396 loss:0.106428675354 accuracy:1.0 397 197 398 loss:0.356863230467 accuracy:0.75 399 198 400 loss:0.0275120735168 accuracy:1.0 401 199 402 loss:1.12723910809 accuracy:0.75 403 200 404 loss:0.08886256814 accuracy:1.0 405 201 406 loss:0.0773176699877 accuracy:1.0 407 202 408 loss:0.17778685689 accuracy:1.0 409 203 410 loss:0.263333916664 accuracy:0.75 411 204 412 loss:0.100112996995 accuracy:1.0 413 205 414 loss:0.0208118930459 accuracy:1.0 415 206 416 loss:0.0241779796779 accuracy:1.0 417 207 418 loss:0.00176866375841 accuracy:1.0 419 208 420 loss:1.03581428528 accuracy:0.75 421 209 422 loss:0.101269900799 accuracy:1.0 423 210 424 loss:0.522728979588 accuracy:0.75 425 211 426 loss:0.0190876871347 accuracy:1.0 427 212 428 loss:0.851385474205 accuracy:0.75 429 213 430 loss:0.627064526081 accuracy:0.5 431 214 432 loss:0.178076297045 accuracy:1.0 433 215 434 loss:0.272920429707 accuracy:1.0 435 216 436 loss:0.722631931305 accuracy:0.75 437 217 438 loss:0.405046164989 accuracy:0.75 439 218 440 loss:0.434506893158 accuracy:0.75 441 219 442 loss:0.205615088344 accuracy:1.0 443 220 444 loss:0.102596238256 accuracy:1.0 445 221 446 loss:0.89775633812 accuracy:0.5 447 222 448 loss:0.0162407811731 accuracy:1.0 449 223 450 loss:0.257048845291 accuracy:0.75 451 224 452 loss:0.53179782629 accuracy:0.75 453 225 454 loss:0.414461612701 accuracy:0.75 455 226 456 loss:0.274204641581 accuracy:0.75 457 227 458 loss:0.751442372799 accuracy:0.75 459 228 460 loss:0.100349068642 accuracy:1.0 461 229 462 loss:0.491792619228 accuracy:0.5 463 230 464 loss:0.470929801464 accuracy:1.0 465 231 466 loss:0.684968233109 accuracy:0.5 467 232 468 loss:0.505018293858 accuracy:0.75 469 233 470 loss:0.23813906312 accuracy:1.0 471 234 472 loss:1.05322659016 accuracy:0.5 473 235 474 loss:0.291554331779 accuracy:1.0 475 236 476 loss:0.384746789932 accuracy:1.0 477 237 478 loss:0.37275955081 accuracy:0.75 479 238 480 loss:0.0688233971596 accuracy:1.0 481 239 482 loss:0.718187510967 accuracy:0.75 483 240 484 loss:0.609194219112 accuracy:0.75 485 241 486 loss:0.225485235453 accuracy:1.0 487 242 488 loss:0.283724486828 accuracy:0.75 489 243 490 loss:0.563280165195 accuracy:0.75 491 244 492 loss:0.0566305555403 accuracy:1.0 493 245 494 loss:0.0681798830628 accuracy:1.0 495 246 496 loss:0.198830872774 accuracy:1.0 497 247 498 loss:0.743586599827 accuracy:0.75 499 248 500 loss:0.108701385558 accuracy:1.0 501 249 502 loss:0.232169955969 accuracy:1.0 503 250 504 loss:0.0204469505697 accuracy:1.0 505 251 506 loss:0.0746807381511 accuracy:1.0 507 252 508 loss:1.67662298679 accuracy:0.5 509 253 510 loss:0.0344735346735 accuracy:1.0 511 254 512 loss:0.329333722591 accuracy:0.75 513 255 514 loss:0.0228136144578 accuracy:1.0 515 256 516 loss:0.558523058891 accuracy:0.75 517 257 518 loss:0.801098883152 accuracy:0.75 519 258 520 loss:0.294895410538 accuracy:1.0 521 259 522 loss:0.073697000742 accuracy:1.0 523 260 524 loss:0.0375180691481 accuracy:1.0 525 261 526 loss:0.246171832085 accuracy:0.75 527 262 528 loss:0.774982333183 accuracy:0.5 529 263 530 loss:0.305063486099 accuracy:1.0 531 264 532 loss:0.463157624006 accuracy:0.5 533 265 534 loss:0.642466902733 accuracy:0.25 535 266 536 loss:0.110810160637 accuracy:1.0 537 267 538 loss:0.055772036314 accuracy:1.0 539 268 540 loss:0.111803464592 accuracy:1.0 541 269 542 loss:0.0542620681226 accuracy:1.0 543 270 544 loss:0.867859005928 accuracy:0.75 545 271 546 loss:0.282488763332 accuracy:1.0 547 272 548 loss:0.102671615779 accuracy:1.0 549 273 550 loss:0.251693636179 accuracy:0.75 551 274 552 loss:0.765829801559 accuracy:0.75 553 275 554 loss:0.194914981723 accuracy:1.0 555 276 556 loss:0.102006778121 accuracy:1.0 557 277 558 loss:0.0539451315999 accuracy:1.0 559 278 560 loss:0.0130981495604 accuracy:1.0 561 279 562 loss:2.14160680771 accuracy:0.5 563 280 564 loss:0.176309481263 accuracy:1.0 565 281 566 loss:0.155295550823 accuracy:1.0 567 282 568 loss:0.0576198920608 accuracy:1.0 569 283 570 loss:0.267267256975 accuracy:1.0 571 284 572 loss:0.170527070761 accuracy:1.0 573 285 574 loss:0.793471336365 accuracy:0.75 575 286 576 loss:0.054802633822 accuracy:1.0 577 287 578 loss:0.0160926636308 accuracy:1.0 579 288 580 loss:0.113910079002 accuracy:1.0 581 289 582 loss:0.0136507945135 accuracy:1.0 583 290 584 loss:0.319148600101 accuracy:0.75 585 291 586 loss:0.000944297935348 accuracy:1.0 587 292 588 loss:0.000640460464638 accuracy:1.0 589 293 590 loss:0.00669733900577 accuracy:1.0 591 294 592 loss:0.00175015779678 accuracy:1.0 593 295 594 loss:0.0475143417716 accuracy:1.0 595 296 596 loss:0.00636913161725 accuracy:1.0 597 297 598 loss:0.00344254914671 accuracy:1.0 599 298 600 loss:0.629906773567 accuracy:0.75 601 299 602 loss:0.00485158292577 accuracy:1.0 603 300 604 loss:0.117860376835 accuracy:1.0 605 301 606 loss:2.2443985939 accuracy:0.75 607 302 608 loss:0.00151524401736 accuracy:1.0 609 303 610 loss:0.668887317181 accuracy:0.75 611 304 612 loss:0.341220498085 accuracy:0.75 613 305 614 loss:0.243527442217 accuracy:0.75 615 306 616 loss:0.109274975955 accuracy:1.0 617 307 618 loss:0.127818629146 accuracy:1.0 619 308 620 loss:0.0721819028258 accuracy:1.0 621 309 622 loss:0.0184937343001 accuracy:1.0 623 310 624 loss:0.820344865322 accuracy:0.5 625 311 626 loss:0.0684595555067 accuracy:1.0 627 312 628 loss:0.364878892899 accuracy:0.75 629 313 630 loss:0.119165182114 accuracy:1.0 631 314 632 loss:0.917512893677 accuracy:0.5 633 315 634 loss:0.208229511976 accuracy:0.75 635 316 636 loss:0.0379144325852 accuracy:1.0 637 317 638 loss:0.291262000799 accuracy:0.75 639 318 640 loss:1.70546030998 accuracy:0.5 641 319 642 loss:0.0183182619512 accuracy:1.0 643 320 644 loss:0.382932752371 accuracy:0.75 645 321 646 loss:0.163620784879 accuracy:1.0 647 322 648 loss:0.319008469582 accuracy:0.75 649 323 650 loss:0.088489279151 accuracy:1.0 651 324 652 loss:0.715149879456 accuracy:0.5 653 325 654 loss:0.0675266161561 accuracy:1.0 655 326 656 loss:0.916550815105 accuracy:0.5 657 327 658 loss:0.448634713888 accuracy:1.0 659 328 660 loss:0.271819204092 accuracy:0.75 661 329 662 loss:0.0831155627966 accuracy:1.0 663 330 664 loss:0.171018838882 accuracy:1.0 665 331 666 loss:0.0210947152227 accuracy:1.0 667 332 668 loss:0.331143260002 accuracy:0.75 669 333 670 loss:0.50136744976 accuracy:0.75 671 334 672 loss:0.156625300646 accuracy:1.0 673 335 674 loss:0.0159201174974 accuracy:1.0 675 336 676 loss:0.171763345599 accuracy:1.0 677 337 678 loss:0.317091315985 accuracy:0.75 679 338 680 loss:0.00742457062006 accuracy:1.0 681 339 682 loss:0.147552683949 accuracy:1.0 683 340 684 loss:0.265565574169 accuracy:0.75 685 341 686 loss:0.0794127807021 accuracy:1.0 687 342 688 loss:0.90516358614 accuracy:0.75 689 343 690 loss:0.0485695488751 accuracy:1.0 691 344 692 loss:0.929676651955 accuracy:0.75 693 345 694 loss:0.0915883779526 accuracy:1.0 695 346 696 loss:0.0149378413334 accuracy:1.0 697 347 698 loss:0.0227350518107 accuracy:1.0 699 348 700 loss:0.188080132008 accuracy:1.0 701 349 702 loss:0.0991646498442 accuracy:1.0 703 350 704 loss:0.0718017593026 accuracy:1.0 705 351 706 loss:1.19274258614 accuracy:0.5 707 352 708 loss:0.965473353863 accuracy:0.5 709 353 710 loss:0.259137153625 accuracy:0.75 711 354 712 loss:0.0660394281149 accuracy:1.0 713 355 714 loss:0.0636159256101 accuracy:1.0 715 356 716 loss:0.473960787058 accuracy:0.75 717 357 718 loss:0.0584978982806 accuracy:1.0 719 358 720 loss:0.225148662925 accuracy:1.0 721 359 722 loss:0.551927268505 accuracy:0.75 723 360 724 loss:0.129055544734 accuracy:1.0 725 361 726 loss:0.135725021362 accuracy:1.0 727 362 728 loss:0.05837514624 accuracy:1.0 729 363 730 loss:0.050028629601 accuracy:1.0 731 364 732 loss:0.0220219194889 accuracy:1.0 733 365 734 loss:0.563142418861 accuracy:0.75 735 366 736 loss:0.213800609112 accuracy:1.0 737 367 738 loss:0.0281376540661 accuracy:1.0 739 368 740 loss:1.20224881172 accuracy:0.75 741 369 742 loss:0.528139770031 accuracy:0.75 743 370 744 loss:0.124928534031 accuracy:1.0 745 371 746 loss:0.26053994894 accuracy:0.75 747 372 748 loss:0.200136646628 accuracy:0.75 749 373 750 loss:0.106237880886 accuracy:1.0 751 374 752 loss:0.317531168461 accuracy:1.0 753 375 754 loss:0.246357157826 accuracy:0.75 755 376 756 loss:0.161189392209 accuracy:1.0 757 377 758 loss:0.0400363244116 accuracy:1.0 759 378 760 loss:0.000115944123536 accuracy:1.0 761 379 762 loss:0.0736970975995 accuracy:1.0 763 380 764 loss:2.95828056335 accuracy:0.5 765 381 766 loss:0.0402479618788 accuracy:1.0 767 382 768 loss:0.27467161417 accuracy:1.0 769 383 770 loss:0.0441851988435 accuracy:1.0 771 384 772 loss:0.0222014114261 accuracy:1.0 773 385 774 loss:0.0845765322447 accuracy:1.0 775 386 776 loss:0.21609556675 accuracy:0.75 777 387 778 loss:0.305368185043 accuracy:0.75 779 388 780 loss:0.457645982504 accuracy:0.75 781 389 782 loss:0.479472994804 accuracy:0.75 783 390 784 loss:0.163302078843 accuracy:1.0 785 391 786 loss:0.436002552509 accuracy:0.75 787 392 788 loss:0.128151774406 accuracy:1.0 789 393 790 loss:0.258456408978 accuracy:0.75 791 394 792 loss:0.22227601707 accuracy:0.75 793 395 794 loss:0.0503372251987 accuracy:1.0 795 396 796 loss:0.02476574108 accuracy:1.0 797 397 798 loss:0.000495057029184 accuracy:1.0 799 398 800 loss:0.419431209564 accuracy:0.75 801 399 802 loss:0.279945731163 accuracy:1.0 803 400 804 loss:0.000864843954332 accuracy:1.0 805 401 806 loss:0.0879789367318 accuracy:1.0 807 402 808 loss:0.00543585978448 accuracy:1.0 809 403 810 loss:0.0035734588746 accuracy:1.0 811 404 812 loss:0.00278418860398 accuracy:1.0 813 405 814 loss:0.800966143608 accuracy:0.75 815 406 816 loss:0.0348575152457 accuracy:1.0 817 407 818 loss:0.217690259218 accuracy:0.75 819 408 820 loss:0.00130753079429 accuracy:1.0 821 409 822 loss:0.00162001827266 accuracy:1.0 823 410 824 loss:0.546540558338 accuracy:0.75 825 411 826 loss:0.443211138248 accuracy:0.75 827 412 828 loss:0.0923056006432 accuracy:1.0 829 413 830 loss:0.282079219818 accuracy:0.75 831 414 832 loss:0.304762452841 accuracy:0.75 833 415 834 loss:0.292380183935 accuracy:0.75 835 416 836 loss:0.028173699975 accuracy:1.0 837 417 838 loss:0.0553055480123 accuracy:1.0 839 418 840 loss:0.388806015253 accuracy:0.75 841 419 842 loss:0.256281733513 accuracy:0.75 843 420 844 loss:0.00459419749677 accuracy:1.0 845 421 846 loss:0.108316868544 accuracy:1.0 847 422 848 loss:0.00306999869645 accuracy:1.0 849 423 850 loss:0.185824766755 accuracy:0.75 851 424 852 loss:0.0356827452779 accuracy:1.0 853 425 854 loss:0.0110305007547 accuracy:1.0 855 426 856 loss:0.000118359719636 accuracy:1.0 857 427 858 loss:0.0264259390533 accuracy:1.0 859 428 860 loss:2.09415435791 accuracy:0.5 861 429 862 loss:0.405786812305 accuracy:0.5 863 430 864 loss:0.170478060842 accuracy:1.0 865 431 866 loss:0.153327018023 accuracy:1.0 867 432 868 loss:0.0670616924763 accuracy:1.0 869 433 870 loss:0.100017897785 accuracy:1.0 871 434 872 loss:0.803987801075 accuracy:0.75 873 435 874 loss:0.242291912436 accuracy:0.75 875 436 876 loss:0.887839794159 accuracy:0.75 877 437 878 loss:0.126330152154 accuracy:1.0 879 438 880 loss:0.495402723551 accuracy:0.5 881 439 882 loss:0.0176431145519 accuracy:1.0 883 440 884 loss:0.254504919052 accuracy:1.0 885 441 886 loss:0.0066742207855 accuracy:1.0 887 442 888 loss:0.103796347976 accuracy:1.0 889 443 890 loss:0.0256795622408 accuracy:1.0 891 444 892 loss:0.412333756685 accuracy:0.75 893 445 894 loss:0.0198563206941 accuracy:1.0 895 446 896 loss:0.0271796099842 accuracy:1.0 897 447 898 loss:0.00262259342708 accuracy:1.0 899 448 900 loss:0.679375708103 accuracy:0.75 901 449 902 loss:0.436676889658 accuracy:0.75 903 450 904 loss:0.133831515908 accuracy:1.0 905 451 906 loss:0.121498912573 accuracy:1.0 907 452 908 loss:0.033711925149 accuracy:1.0 909 453 910 loss:0.102268278599 accuracy:1.0 911 454 912 loss:0.00103223056067 accuracy:1.0 913 455 914 loss:0.128242060542 accuracy:1.0 915 456 916 loss:0.00504214642569 accuracy:1.0 917 457 918 loss:0.00237890915014 accuracy:1.0 919 458 920 loss:1.08625376225 accuracy:0.25 921 459 922 loss:0.030952764675 accuracy:1.0 923 460 924 loss:0.173320218921 accuracy:1.0 925 461 926 loss:0.121969670057 accuracy:1.0 927 462 928 loss:0.0947612226009 accuracy:1.0 929 463 930 loss:0.205078348517 accuracy:0.75 931 464 932 loss:0.00106444279663 accuracy:1.0 933 465 934 loss:0.34515401721 accuracy:0.75 935 466 936 loss:0.15998339653 accuracy:1.0 937 467 938 loss:0.00492420978844 accuracy:1.0 939 468 940 loss:0.0870720297098 accuracy:1.0 941 469 942 loss:2.09969067574 accuracy:0.5 943 470 944 loss:0.194903433323 accuracy:1.0 945 471 946 loss:0.242374703288 accuracy:1.0 947 472 948 loss:0.00174707639962 accuracy:1.0 949 473 950 loss:0.0663149431348 accuracy:1.0 951 474 952 loss:0.0415232479572 accuracy:1.0 953 475 954 loss:0.745410084724 accuracy:0.75 955 476 956 loss:0.72058993578 accuracy:0.75 957 477 958 loss:0.074091270566 accuracy:1.0 959 478 960 loss:0.0825443267822 accuracy:1.0 961 479 962 loss:0.0513244643807 accuracy:1.0 963 480 964 loss:0.0320774801075 accuracy:1.0 965 481 966 loss:0.0128127280623 accuracy:1.0 967 482 968 loss:0.0371737554669 accuracy:1.0 969 483 970 loss:0.276018559933 accuracy:0.75 971 484 972 loss:0.0172993671149 accuracy:1.0 973 485 974 loss:0.0301472023129 accuracy:1.0 975 486 976 loss:0.00649361917749 accuracy:1.0 977 487 978 loss:0.000473263178719 accuracy:1.0 979 488 980 loss:0.000434344052337 accuracy:1.0 981 489 982 loss:0.0177765209228 accuracy:1.0 983 490 984 loss:0.100023776293 accuracy:1.0 985 491 986 loss:0.00998072884977 accuracy:1.0 987 492 988 loss:0.178784310818 accuracy:0.75 989 493 990 loss:0.000287099683192 accuracy:1.0 991 494 992 loss:2.17384004593 accuracy:0.75 993 495 994 loss:0.125859886408 accuracy:1.0 995 496 996 loss:0.0469430424273 accuracy:1.0 997 497 998 loss:0.0470446236432 accuracy:1.0 999 498 1000 loss:0.00149866973516 accuracy:1.0 1001 499 1002 loss:1.76050198078 accuracy:0.5 1003 500 1004 loss:0.223427206278 accuracy:1.0 1005 501 1006 loss:0.252842336893 accuracy:0.75 1007 502 1008 loss:0.688393950462 accuracy:0.75 1009 503 1010 loss:0.0202198959887 accuracy:1.0 1011 504 1012 loss:0.00671406136826 accuracy:1.0 1013 505 1014 loss:0.248940289021 accuracy:1.0 1015 506 1016 loss:0.274929821491 accuracy:0.75 1017 507 1018 loss:0.12192375958 accuracy:1.0 1019 508 1020 loss:0.529097795486 accuracy:0.75 1021 509 1022 loss:0.0117030935362 accuracy:1.0 1023 510 1024 loss:0.0703663975 accuracy:1.0 1025 511 1026 loss:0.00478047179058 accuracy:1.0 1027 512 1028 loss:0.0121546797454 accuracy:1.0 1029 513 1030 loss:0.208536297083 accuracy:1.0 1031 514 1032 loss:0.00334931351244 accuracy:1.0 1033 515 1034 loss:0.79892295599 accuracy:0.75 1035 516 1036 loss:1.14639115334 accuracy:0.75 1037 517 1038 loss:0.0293184090406 accuracy:1.0 1039 518 1040 loss:0.0145129384473 accuracy:1.0 1041 519 1042 loss:0.51245445013 accuracy:0.5 1043 520 1044 loss:0.163923382759 accuracy:1.0 1045 521 1046 loss:0.00152231776156 accuracy:1.0 1047 522 1048 loss:0.00467296224087 accuracy:1.0 1049 523 1050 loss:0.335566133261 accuracy:0.75 1051 524 1052 loss:0.565649867058 accuracy:0.75 1053 525 1054 loss:0.0779503583908 accuracy:1.0 1055 526 1056 loss:0.0503666475415 accuracy:1.0 1057 527 1058 loss:0.0936669185758 accuracy:1.0 1059 528 1060 loss:0.0114694610238 accuracy:1.0 1061 529 1062 loss:0.0113796535879 accuracy:1.0 1063 530 1064 loss:0.00210900465026 accuracy:1.0 1065 531 1066 loss:0.0697501897812 accuracy:1.0 1067 532 1068 loss:0.0413017123938 accuracy:1.0 1069 533 1070 loss:0.000223232258577 accuracy:1.0 1071 534 1072 loss:0.00237680179998 accuracy:1.0 1073 535 1074 loss:0.0935806557536 accuracy:1.0 1075 536 1076 loss:0.105601318181 accuracy:1.0 1077 537 1078 loss:2.22019316425e-05 accuracy:1.0 1079 538 1080 loss:0.604238510132 accuracy:0.75 1081 539 1082 loss:0.0422407202423 accuracy:1.0 1083 540 1084 loss:0.0232363473624 accuracy:1.0 1085 541 1086 loss:0.0315810516477 accuracy:1.0 1087 542 1088 loss:3.51061898982e-05 accuracy:1.0 1089 543 1090 loss:0.0173356998712 accuracy:1.0 1091 544 1092 loss:0.00834203884006 accuracy:1.0 1093 545 1094 loss:0.000342688814271 accuracy:1.0 1095 546 1096 loss:7.11309767212e-05 accuracy:1.0 1097 547 1098 loss:0.00906061194837 accuracy:1.0 1099 548 1100 loss:1.66892471043e-06 accuracy:1.0 1101 549 1102 loss:0.00172243604902 accuracy:1.0 1103 550 1104 loss:0.034824796021 accuracy:1.0 1105 551 1106 loss:1.22189294416e-06 accuracy:1.0 1107 552 1108 loss:0.00228166719899 accuracy:1.0 1109 553 1110 loss:1.75538408756 accuracy:0.75 1111 554 1112 loss:0.160510271788 accuracy:1.0 1113 555 1114 loss:0.00583411566913 accuracy:1.0 1115 556 1116 loss:0.0328364670277 accuracy:1.0 1117 557 1118 loss:0.865779876709 accuracy:0.75 1119 558 1120 loss:0.643167614937 accuracy:0.5 1121 559 1122 loss:2.28500294685 accuracy:0.0 1123 560 1124 loss:0.0093042999506 accuracy:1.0 1125 561 1126 loss:0.735183119774 accuracy:0.75 1127 562 1128 loss:0.0769147053361 accuracy:1.0 1129 563 1130 loss:0.0310892332345 accuracy:1.0 1131 564 1132 loss:0.0728826448321 accuracy:1.0 1133 565 1134 loss:0.178516685963 accuracy:1.0 1135 566 1136 loss:0.0103313624859 accuracy:1.0 1137 567 1138 loss:0.118710055947 accuracy:1.0 1139 568 1140 loss:0.074576176703 accuracy:1.0 1141 569 1142 loss:0.240194231272 accuracy:0.75 1143 570 1144 loss:0.0038958825171 accuracy:1.0 1145 571 1146 loss:0.000401474506361 accuracy:1.0 1147 572 1148 loss:0.0813326686621 accuracy:1.0 1149 573 1150 loss:0.0319667756557 accuracy:1.0 1151 574 1152 loss:0.0254385173321 accuracy:1.0 1153 575 1154 loss:0.00608881236985 accuracy:1.0 1155 576 1156 loss:0.0615266412497 accuracy:1.0 1157 577 1158 loss:0.00878894422203 accuracy:1.0 1159 578 1160 loss:0.00919084344059 accuracy:1.0 1161 579 1162 loss:0.0137438997626 accuracy:1.0 1163 580 1164 loss:5.85580492043e-05 accuracy:1.0 1165 581 1166 loss:0.950065612793 accuracy:0.75 1167 582 1168 loss:0.517662346363 accuracy:0.75 1169 583 1170 loss:0.0079373139888 accuracy:1.0 1171 584 1172 loss:0.199831828475 accuracy:0.75 1173 585 1174 loss:0.0586840547621 accuracy:1.0 1175 586 1176 loss:0.0635885223746 accuracy:1.0 1177 587 1178 loss:0.00248917890713 accuracy:1.0 1179 588 1180 loss:0.0176570080221 accuracy:1.0 1181 589 1182 loss:0.00802893098444 accuracy:1.0 1183 590 1184 loss:0.00644389400259 accuracy:1.0 1185 591 1186 loss:0.000337625970133 accuracy:1.0 1187 592 1188 loss:0.000656736374367 accuracy:1.0 1189 593 1190 loss:0.0069315279834 accuracy:1.0 1191 594 1192 loss:0.000192244129721 accuracy:1.0 1193 595 1194 loss:0.153810724616 accuracy:1.0 1195 596 1196 loss:0.509512066841 accuracy:0.75 1197 597 1198 loss:2.8454875946 accuracy:0.5 1199 598 1200 loss:0.121696084738 accuracy:1.0 1201 599 1202 loss:0.13493694365 accuracy:1.0 1203 600 1204 loss:0.0113169485703 accuracy:1.0 1205 601 1206 loss:0.143897026777 accuracy:1.0 1207 602 1208 loss:0.0995514839888 accuracy:1.0 1209 603 1210 loss:0.00416302261874 accuracy:1.0 1211 604 1212 loss:0.0498762577772 accuracy:1.0 1213 605 1214 loss:0.000733904773369 accuracy:1.0 1215 606 1216 loss:0.00432188156992 accuracy:1.0 1217 607 1218 loss:0.247714474797 accuracy:0.75 1219 608 1220 loss:0.0603492446244 accuracy:1.0 1221 609 1222 loss:0.00636652298272 accuracy:1.0 1223 610 1224 loss:3.8743002051e-07 accuracy:1.0 1225 611 1226 loss:0.000434571033111 accuracy:1.0 1227 612 1228 loss:0.000185367985978 accuracy:1.0 1229 613 1230 loss:1.27765703201 accuracy:0.5 1231 614 1232 loss:0.0464809089899 accuracy:1.0 1233 615 1234 loss:0.0682013481855 accuracy:1.0 1235 616 1236 loss:0.166923344135 accuracy:1.0 1237 617 1238 loss:0.00747666787356 accuracy:1.0 1239 618 1240 loss:0.000737957539968 accuracy:1.0 1241 619 1242 loss:0.147793710232 accuracy:1.0 1243 620 1244 loss:0.00622826628387 accuracy:1.0 1245 621 1246 loss:0.0026685774792 accuracy:1.0 1247 622 1248 loss:0.0266832802445 accuracy:1.0 1249 623 1250 loss:0.00111918640323 accuracy:1.0 1251 624 1252 loss:0.166999429464 accuracy:1.0 1253 625 1254 loss:0.00493326690048 accuracy:1.0 1255 626 1256 loss:0.148973792791 accuracy:1.0 1257 627 1258 loss:0.0164778511971 accuracy:1.0 1259 628 1260 loss:0.0263445004821 accuracy:1.0 1261 629 1262 loss:0.000971373054199 accuracy:1.0 1263 630 1264 loss:0.137379467487 accuracy:1.0 1265 631 1266 loss:0.000336995668476 accuracy:1.0 1267 632 1268 loss:0.000118585114251 accuracy:1.0 1269 633 1270 loss:0.194744035602 accuracy:0.75 1271 634 1272 loss:0.622318923473 accuracy:0.75 1273 635 1274 loss:0.0158670805395 accuracy:1.0 1275 636 1276 loss:0.00111870421097 accuracy:1.0 1277 637 1278 loss:0.00360449962318 accuracy:1.0 1279 638 1280 loss:0.123612225056 accuracy:1.0 1281 639 1282 loss:0.915646851063 accuracy:0.75 1283 640 1284 loss:0.00414372095838 accuracy:1.0 1285 641 1286 loss:0.00148615182843 accuracy:1.0 1287 642 1288 loss:0.139044344425 accuracy:1.0 1289 643 1290 loss:0.000594415760133 accuracy:1.0 1291 644 1292 loss:0.0548767484725 accuracy:1.0 1293 645 1294 loss:0.131095871329 accuracy:1.0 1295 646 1296 loss:0.0180732347071 accuracy:1.0 1297 647 1298 loss:0.0192443877459 accuracy:1.0 1299 648 1300 loss:0.002840944333 accuracy:1.0 1301 649 1302 loss:0.0817834958434 accuracy:1.0 1303 650 1304 loss:7.39887691452e-05 accuracy:1.0 1305 651 1306 loss:0.000455870700534 accuracy:1.0 1307 652 1308 loss:0.00230005686171 accuracy:1.0 1309 653 1310 loss:0.000108704443846 accuracy:1.0 1311 654 1312 loss:0.0797890126705 accuracy:1.0 1313 655 1314 loss:0.00503324298188 accuracy:1.0 1315 656 1316 loss:0.0720994323492 accuracy:1.0 1317 657 1318 loss:2.68220759381e-07 accuracy:1.0 1319 658 1320 loss:0.00216671684757 accuracy:1.0 1321 659 1322 loss:0.000182132818736 accuracy:1.0 1323 660 1324 loss:0.0201711002737 accuracy:1.0 1325 661 1326 loss:0.000373564369511 accuracy:1.0 1327 662 1328 loss:0.210333183408 accuracy:0.75 1329 663 1330 loss:0.434348583221 accuracy:0.75 1331 664 1332 loss:0.00160946941469 accuracy:1.0 1333 665 1334 loss:0.00168058788404 accuracy:1.0 1335 666 1336 loss:0.0156195694581 accuracy:1.0 1337 667 1338 loss:0.0179282538593 accuracy:1.0 1339 668 1340 loss:0.619975090027 accuracy:0.75 1341 669 1342 loss:0.0250529292971 accuracy:1.0 1343 670 1344 loss:1.1728490591 accuracy:0.75 1345 671 1346 loss:0.000638192694169 accuracy:1.0 1347 672 1348 loss:0.00298879598267 accuracy:1.0 1349 673 1350 loss:0.000486818666104 accuracy:1.0 1351 674 1352 loss:7.75988737587e-05 accuracy:1.0 1353 675 1354 loss:0.0147338835523 accuracy:1.0 1355 676 1356 loss:0.0939862802625 accuracy:1.0 1357 677 1358 loss:0.356457710266 accuracy:0.75 1359 678 1360 loss:0.0 accuracy:1.0 1361 679 1362 loss:0.00246878503822 accuracy:1.0 1363 680 1364 loss:0.00888949073851 accuracy:1.0 1365 681 1366 loss:0.170242756605 accuracy:1.0 1367 682 1368 loss:0.0192358512431 accuracy:1.0 1369 683 1370 loss:0.228889971972 accuracy:1.0 1371 684 1372 loss:0.0224611312151 accuracy:1.0 1373 685 1374 loss:0.645591199398 accuracy:0.75 1375 686 1376 loss:0.0435347706079 accuracy:1.0 1377 687 1378 loss:0.016888409853 accuracy:1.0 1379 688 1380 loss:0.000532899983227 accuracy:1.0 1381 689 1382 loss:0.0515907779336 accuracy:1.0 1383 690 1384 loss:0.0468752644956 accuracy:1.0 1385 691 1386 loss:7.48243910493e-05 accuracy:1.0 1387 692 1388 loss:0.000171366787981 accuracy:1.0 1389 693 1390 loss:0.134263500571 accuracy:1.0 1391 694 1392 loss:0.0109058497474 accuracy:1.0 1393 695 1394 loss:0.0117134619504 accuracy:1.0 1395 696 1396 loss:0.000636452401523 accuracy:1.0 1397 697 1398 loss:0.074299864471 accuracy:1.0 1399 698 1400 loss:0.0229991711676 accuracy:1.0 1401 699 1402 loss:1.19209028071e-06 accuracy:1.0 1403 700 1404 loss:5.01820904901e-05 accuracy:1.0 1405 701 1406 loss:0.000727334117983 accuracy:1.0 1407 702 1408 loss:6.25842085356e-06 accuracy:1.0 1409 703 1410 loss:0.00155220844317 accuracy:1.0 1411 704 1412 loss:2.98023206113e-08 accuracy:1.0 1413 705 1414 loss:0.0246029030532 accuracy:1.0 1415 706 1416 loss:0.00987655483186 accuracy:1.0 1417 707 1418 loss:0.00130767049268 accuracy:1.0 1419 708 1420 loss:8.22408910608e-05 accuracy:1.0 1421 709 1422 loss:1.19209261129e-07 accuracy:1.0 1423 710 1424 loss:8.04661510756e-07 accuracy:1.0 1425 711 1426 loss:0.00843916833401 accuracy:1.0 1427 712 1428 loss:0.710033893585 accuracy:0.75 1429 713 1430 loss:3.87427189708e-06 accuracy:1.0 1431 714 1432 loss:0.00279647787102 accuracy:1.0 1433 715 1434 loss:1.66902518272 accuracy:0.75 1435 716 1436 loss:4.8334699386e-05 accuracy:1.0 1437 717 1438 loss:0.000108164756966 accuracy:1.0 1439 718 1440 loss:0.000460023642518 accuracy:1.0 1441 719 1442 loss:0.014947255142 accuracy:1.0 1443 720 1444 loss:0.00103411846794 accuracy:1.0 1445 721 1446 loss:0.00142774963751 accuracy:1.0 1447 722 1448 loss:0.00128786324058 accuracy:1.0 1449 723 1450 loss:0.000406698818551 accuracy:1.0 1451 724 1452 loss:0.0186016894877 accuracy:1.0 1453 725 1454 loss:3.92168876715e-05 accuracy:1.0 1455 726 1456 loss:0.00641623232514 accuracy:1.0 1457 727 1458 loss:0.000120202676044 accuracy:1.0 1459 728 1460 loss:5.96040854361e-06 accuracy:1.0 1461 729 1462 loss:0.0003364807053 accuracy:1.0 1463 730 1464 loss:7.39286333555e-05 accuracy:1.0 1465 731 1466 loss:0.0154847707599 accuracy:1.0 1467 732 1468 loss:0.000457124668173 accuracy:1.0 1469 733 1470 loss:3.1618270441e-05 accuracy:1.0 1471 734 1472 loss:0.910873115063 accuracy:0.75 1473 735 1474 loss:0.0267107822001 accuracy:1.0 1475 736 1476 loss:0.39768460393 accuracy:0.75 1477 737 1478 loss:0.0669838786125 accuracy:1.0 1479 738 1480 loss:0.00644081551582 accuracy:1.0 1481 739 1482 loss:0.034500323236 accuracy:1.0 1483 740 1484 loss:0.00022785415058 accuracy:1.0 1485 741 1486 loss:0.0 accuracy:1.0 1487 742 1488 loss:0.000210024169064 accuracy:1.0 1489 743 1490 loss:0.00147695967462 accuracy:1.0 1491 744 1492 loss:0.0725145637989 accuracy:1.0 1493 745 1494 loss:0.029834413901 accuracy:1.0 1495 746 1496 loss:0.0220102537423 accuracy:1.0 1497 747 1498 loss:7.51805127948e-05 accuracy:1.0 1499 748 1500 loss:0.243395596743 accuracy:1.0 1501 749 1502 loss:0.0 accuracy:1.0 1503 750 1504 loss:0.000294363766443 accuracy:1.0 1505 751 1506 loss:0.000681870267726 accuracy:1.0 1507 752 1508 loss:0.0001109384757 accuracy:1.0 1509 753 1510 loss:0.00326775875874 accuracy:1.0 1511 754 1512 loss:0.000125748862047 accuracy:1.0 1513 755 1514 loss:0.0223309192806 accuracy:1.0 1515 756 1516 loss:2.08616171449e-07 accuracy:1.0 1517 757 1518 loss:0.00221180100925 accuracy:1.0 1519 758 1520 loss:0.000174014785443 accuracy:1.0 1521 759 1522 loss:1.72069203854 accuracy:0.5 1523 760 1524 loss:0.0 accuracy:1.0 1525 761 1526 loss:2.15550684929 accuracy:0.75 1527 762 1528 loss:0.518400728703 accuracy:0.75 1529 763 1530 loss:0.105010151863 accuracy:1.0 1531 764 1532 loss:0.00476733082905 accuracy:1.0 1533 765 1534 loss:0.618326127529 accuracy:0.75 1535 766 1536 loss:0.0568829216063 accuracy:1.0 1537 767 1538 loss:0.00282724341378 accuracy:1.0 1539 768 1540 loss:0.00655440147966 accuracy:1.0 1541 769 1542 loss:0.0208293218166 accuracy:1.0 1543 770 1544 loss:0.0136799290776 accuracy:1.0 1545 771 1546 loss:0.069712460041 accuracy:1.0 1547 772 1548 loss:0.000210100814002 accuracy:1.0 1549 773 1550 loss:0.00459663849324 accuracy:1.0 1551 774 1552 loss:0.000156323905685 accuracy:1.0 1553 775 1554 loss:0.00276682106778 accuracy:1.0 1555 776 1556 loss:0.000317671743687 accuracy:1.0 1557 777 1558 loss:0.00603116257116 accuracy:1.0 1559 778 1560 loss:0.000105627936136 accuracy:1.0 1561 779 1562 loss:0.0012082036119 accuracy:1.0 1563 780 1564 loss:0.00771681312472 accuracy:1.0 1565 781 1566 loss:0.000266665418167 accuracy:1.0 1567 782 1568 loss:0.000127759703901 accuracy:1.0 1569 783 1570 loss:0.0755270496011 accuracy:1.0 1571 784 1572 loss:0.16779884696 accuracy:1.0 1573 785 1574 loss:0.00140535703395 accuracy:1.0 1575 786 1576 loss:0.00015215415624 accuracy:1.0 1577 787 1578 loss:0.000368304987205 accuracy:1.0 1579 788 1580 loss:0.00157043302897 accuracy:1.0 1581 789 1582 loss:2.41397765421e-06 accuracy:1.0 1583 790 1584 loss:2.59279295278e-06 accuracy:1.0 1585 791 1586 loss:6.28824091109e-06 accuracy:1.0 1587 792 1588 loss:0.0221433527768 accuracy:1.0 1589 793 1590 loss:2.08616171449e-07 accuracy:1.0 1591 794 1592 loss:1.57948488777e-05 accuracy:1.0 1593 795 1594 loss:0.143929585814 accuracy:1.0 1595 796 1596 loss:1.9745169878 accuracy:0.75 1597 797 1598 loss:0.000270577816991 accuracy:1.0 1599 798 1600 loss:5.12140083313 accuracy:0.5 1601 799 1602 loss:0.00173324288335 accuracy:1.0 1603 800 1604 loss:1.19792962074 accuracy:0.75 1605 801 1606 loss:2.02655382964e-06 accuracy:1.0 1607 802 1608 loss:0.00112404092215 accuracy:1.0 1609 803 1610 loss:0.00845727138221 accuracy:1.0 1611 804 1612 loss:0.28252235055 accuracy:0.75 1613 805 1614 loss:0.0106558371335 accuracy:1.0 1615 806 1616 loss:0.014702941291 accuracy:1.0 1617 807 1618 loss:0.00130192749202 accuracy:1.0 1619 808 1620 loss:0.000347329594661 accuracy:1.0 1621 809 1622 loss:0.00703197019175 accuracy:1.0 1623 810 1624 loss:0.0106599340215 accuracy:1.0 1625 811 1626 loss:0.00392346037552 accuracy:1.0 1627 812 1628 loss:0.0465068034828 accuracy:1.0 1629 813 1630 loss:8.81706946529e-05 accuracy:1.0 1631 814 1632 loss:0.0458577163517 accuracy:1.0 1633 815 1634 loss:0.0467248111963 accuracy:1.0 1635 816 1636 loss:0.00091094506206 accuracy:1.0 1637 817 1638 loss:3.09035203827e-05 accuracy:1.0 1639 818 1640 loss:0.00139724835753 accuracy:1.0 1641 819 1642 loss:0.000333012023475 accuracy:1.0 1643 820 1644 loss:0.00710536446422 accuracy:1.0 1645 821 1646 loss:0.00560972420499 accuracy:1.0 1647 822 1648 loss:0.000250497396337 accuracy:1.0 1649 823 1650 loss:0.00380676612258 accuracy:1.0 1651 824 1652 loss:0.000113908354251 accuracy:1.0 1653 825 1654 loss:0.0343874841928 accuracy:1.0 1655 826 1656 loss:0.00282790628262 accuracy:1.0 1657 827 1658 loss:6.72862443025e-05 accuracy:1.0 1659 828 1660 loss:0.00147931976244 accuracy:1.0 1661 829 1662 loss:2.86683352897e-05 accuracy:1.0 1663 830 1664 loss:0.0245764218271 accuracy:1.0 1665 831 1666 loss:4.20210108132e-06 accuracy:1.0 1667 832 1668 loss:7.25034042262e-05 accuracy:1.0 1669 833 1670 loss:3.16184814437e-05 accuracy:1.0 1671 834 1672 loss:1.79704529728e-05 accuracy:1.0 1673 835 1674 loss:0.000492809806019 accuracy:1.0 1675 836 1676 loss:0.01179948356 accuracy:1.0 1677 837 1678 loss:0.0204155929387 accuracy:1.0 1679 838 1680 loss:0.0225518066436 accuracy:1.0 1681 839 1682 loss:0.000979462754913 accuracy:1.0 1683 840 1684 loss:0.0264807604253 accuracy:1.0 1685 841 1686 loss:0.000642011058517 accuracy:1.0 1687 842 1688 loss:9.98367613647e-06 accuracy:1.0 1689 843 1690 loss:0.000578560575377 accuracy:1.0 1691 844 1692 loss:0.00985639821738 accuracy:1.0 1693 845 1694 loss:0.000689651060384 accuracy:1.0 1695 846 1696 loss:0.264054358006 accuracy:0.75 1697 847 1698 loss:0.00211702845991 accuracy:1.0 1699 848 1700 loss:0.0 accuracy:1.0 1701 849 1702 loss:0.00793411303312 accuracy:1.0 1703 850 1704 loss:0.0133068496361 accuracy:1.0 1705 851 1706 loss:0.00019709445769 accuracy:1.0 1707 852 1708 loss:0.000726983242203 accuracy:1.0 1709 853 1710 loss:4.52993208455e-06 accuracy:1.0 1711 854 1712 loss:0.000351926224539 accuracy:1.0 1713 855 1714 loss:2.68220759381e-07 accuracy:1.0 1715 856 1716 loss:2.38418522258e-07 accuracy:1.0 1717 857 1718 loss:0.000103779944766 accuracy:1.0 1719 858 1720 loss:0.00327592715621 accuracy:1.0 1721 859 1722 loss:0.000106491184852 accuracy:1.0 1723 860 1724 loss:5.18235428899e-05 accuracy:1.0 1725 861 1726 loss:2.75658640021e-05 accuracy:1.0 1727 862 1728 loss:6.54671530356e-05 accuracy:1.0 1729 863 1730 loss:0.0223422013223 accuracy:1.0 1731 864 1732 loss:0.000272205128567 accuracy:1.0 1733 865 1734 loss:2.03243580472e-05 accuracy:1.0 1735 866 1736 loss:2.66121260211e-05 accuracy:1.0 1737 867 1738 loss:1.37090319186e-06 accuracy:1.0 1739 868 1740 loss:0.0945804268122 accuracy:1.0 1741 869 1742 loss:3.57627612857e-07 accuracy:1.0 1743 870 1744 loss:0.0 accuracy:1.0 1745 871 1746 loss:4.93477746204e-05 accuracy:1.0 1747 872 1748 loss:4.08288497056e-06 accuracy:1.0 1749 873 1750 loss:0.0 accuracy:1.0 1751 874 1752 loss:0.000123173100292 accuracy:1.0 1753 875 1754 loss:0.000122963945614 accuracy:1.0 1755 876 1756 loss:1.90734135685e-06 accuracy:1.0 1757 877 1758 loss:0.0 accuracy:1.0 1759 878 1760 loss:2.5754442215 accuracy:0.75 1761 879 1762 loss:7.56566732889e-05 accuracy:1.0 1763 880 1764 loss:0.0012678487692 accuracy:1.0 1765 881 1766 loss:0.000307852867991 accuracy:1.0 1767 882 1768 loss:1.25169458443e-06 accuracy:1.0 1769 883 1770 loss:0.00642994698137 accuracy:1.0 1771 884 1772 loss:0.000592304742895 accuracy:1.0 1773 885 1774 loss:0.000150688283611 accuracy:1.0 1775 886 1776 loss:0.00178344349843 accuracy:1.0 1777 887 1778 loss:0.259098112583 accuracy:0.75 1779 888 1780 loss:0.000131561449962 accuracy:1.0 1781 889 1782 loss:3.65051782865e-05 accuracy:1.0 1783 890 1784 loss:0.00213865935802 accuracy:1.0 1785 891 1786 loss:6.25848144864e-07 accuracy:1.0 1787 892 1788 loss:4.12733934354e-05 accuracy:1.0 1789 893 1790 loss:5.81375788897e-05 accuracy:1.0 1791 894 1792 loss:0.000273287500022 accuracy:1.0 1793 895 1794 loss:0.000152824548422 accuracy:1.0 1795 896 1796 loss:8.31473425933e-06 accuracy:1.0 1797 897 1798 loss:2.2857580916e-05 accuracy:1.0 1799 898 1800 loss:7.83792074799e-06 accuracy:1.0 1801 899 1802 loss:0.0115786949173 accuracy:1.0 1803 900 1804 loss:9.68728563748e-05 accuracy:1.0 1805 901 1806 loss:1.13248688649e-06 accuracy:1.0 1807 902 1808 loss:0.0496145673096 accuracy:1.0 1809 903 1810 loss:1.11756226033e-05 accuracy:1.0 1811 904 1812 loss:0.000203325893381 accuracy:1.0 1813 905 1814 loss:4.82794484924e-06 accuracy:1.0 1815 906 1816 loss:1.26060649563e-05 accuracy:1.0 1817 907 1818 loss:0.000413879693951 accuracy:1.0 1819 908 1820 loss:6.35007745586e-05 accuracy:1.0 1821 909 1822 loss:2.98023206113e-08 accuracy:1.0 1823 910 1824 loss:0.00323041388765 accuracy:1.0 1825 911 1826 loss:9.79712203844e-05 accuracy:1.0 1827 912 1828 loss:1.62848079205 accuracy:0.75 1829 913 1830 loss:0.0242614541203 accuracy:1.0 1831 914 1832 loss:0.0270170196891 accuracy:1.0 1833 915 1834 loss:0.298094958067 accuracy:0.75 1835 916 1836 loss:0.000197779576411 accuracy:1.0 1837 917 1838 loss:0.0 accuracy:1.0 1839 918 1840 loss:1.09183096886 accuracy:0.75 1841 919 1842 loss:0.059089269489 accuracy:1.0 1843 920 1844 loss:0.540388822556 accuracy:0.75 1845 921 1846 loss:0.00234878063202 accuracy:1.0 1847 922 1848 loss:0.00449673319235 accuracy:1.0 1849 923 1850 loss:0.00438120402396 accuracy:1.0 1851 924 1852 loss:0.000105101295048 accuracy:1.0 1853 925 1854 loss:0.00597113603726 accuracy:1.0 1855 926 1856 loss:0.000764504424296 accuracy:1.0 1857 927 1858 loss:0.000180775154149 accuracy:1.0 1859 928 1860 loss:0.000158698647283 accuracy:1.0 1861 929 1862 loss:3.12923202728e-06 accuracy:1.0 1863 930 1864 loss:0.0212600249797 accuracy:1.0 1865 931 1866 loss:0.00659835385159 accuracy:1.0 1867 932 1868 loss:0.181482896209 accuracy:0.75 1869 933 1870 loss:0.00233455142006 accuracy:1.0 1871 934 1872 loss:0.77560710907 accuracy:0.75 1873 935 1874 loss:2.85493988486e-05 accuracy:1.0 1875 936 1876 loss:1.73443495441e-05 accuracy:1.0 1877 937 1878 loss:1.39770290843e-05 accuracy:1.0 1879 938 1880 loss:0.0147224320099 accuracy:1.0 1881 939 1882 loss:0.0225931722671 accuracy:1.0 1883 940 1884 loss:0.000159510731464 accuracy:1.0 1885 941 1886 loss:0.0267392788082 accuracy:1.0 1887 942 1888 loss:1.6301364667e-05 accuracy:1.0 1889 943 1890 loss:0.00837118458003 accuracy:1.0 1891 944 1892 loss:1.40070710586e-06 accuracy:1.0 1893 945 1894 loss:1.78813877483e-07 accuracy:1.0 1895 946 1896 loss:1.35598693305e-05 accuracy:1.0 1897 947 1898 loss:3.6832956539e-05 accuracy:1.0 1899 948 1900 loss:2.1457603907e-06 accuracy:1.0 1901 949 1902 loss:6.25848201707e-07 accuracy:1.0 1903 950 1904 loss:6.67563244861e-06 accuracy:1.0 1905 951 1906 loss:0.000172200932866 accuracy:1.0 1907 952 1908 loss:2.45559112955e-05 accuracy:1.0 1909 953 1910 loss:0.28211170435 accuracy:0.75 1911 954 1912 loss:3.78486629415e-06 accuracy:1.0 1913 955 1914 loss:0.0 accuracy:1.0 1915 956 1916 loss:3.99325363105e-05 accuracy:1.0 1917 957 1918 loss:0.000164037759532 accuracy:1.0 1919 958 1920 loss:5.56377053726e-05 accuracy:1.0 1921 959 1922 loss:1.34110086947e-06 accuracy:1.0 1923 960 1924 loss:0.00719599006698 accuracy:1.0 1925 961 1926 loss:5.1224942581e-05 accuracy:1.0 1927 962 1928 loss:0.108724892139 accuracy:1.0 1929 963 1930 loss:0.216220155358 accuracy:0.75 1931 964 1932 loss:2.98023206113e-08 accuracy:1.0 1933 965 1934 loss:1.32020913952e-05 accuracy:1.0 1935 966 1936 loss:0.000549052318092 accuracy:1.0 1937 967 1938 loss:1.04307912352e-06 accuracy:1.0 1939 968 1940 loss:0.00227680965327 accuracy:1.0 1941 969 1942 loss:3.91273861169e-05 accuracy:1.0 1943 970 1944 loss:1.72852867308e-06 accuracy:1.0 1945 971 1946 loss:5.95975398028e-05 accuracy:1.0 1947 972 1948 loss:2.98023206113e-08 accuracy:1.0 1949 973 1950 loss:1.12845361233 accuracy:0.75 1951 974 1952 loss:0.00344220059924 accuracy:1.0 1953 975 1954 loss:1.78813891694e-07 accuracy:1.0 1955 976 1956 loss:0.00555469095707 accuracy:1.0 1957 977 1958 loss:0.0254180897027 accuracy:1.0 1959 978 1960 loss:0.00575304357335 accuracy:1.0 1961 979 1962 loss:8.87657224666e-05 accuracy:1.0 1963 980 1964 loss:0.333685457706 accuracy:0.75 1965 981 1966 loss:1.5411645174 accuracy:0.75 1967 982 1968 loss:0.00339213898405 accuracy:1.0 1969 983 1970 loss:0.00120935903396 accuracy:1.0 1971 984 1972 loss:0.000193331274204 accuracy:1.0 1973 985 1974 loss:0.00145972822793 accuracy:1.0 1975 986 1976 loss:0.0121605098248 accuracy:1.0 1977 987 1978 loss:0.000133721638122 accuracy:1.0 1979 988 1980 loss:5.54321013624e-06 accuracy:1.0 1981 989 1982 loss:0.0561847537756 accuracy:1.0 1983 990 1984 loss:2.12487684621e-05 accuracy:1.0 1985 991 1986 loss:0.00121289375238 accuracy:1.0 1987 992 1988 loss:7.45056922824e-07 accuracy:1.0 1989 993 1990 loss:0.000156591951963 accuracy:1.0 1991 994 1992 loss:0.00030597744626 accuracy:1.0 1993 995 1994 loss:0.00287289102562 accuracy:1.0 1995 996 1996 loss:0.00114007492084 accuracy:1.0 1997 997 1998 loss:0.000725160876755 accuracy:1.0 1999 998 2000 loss:1.57951808433e-06 accuracy:1.0 2001 999 2002 loss:0.00928597245365 accuracy:1.0
----------2018.02.19 在给定inception v4模型下继续训练---------------
实验记录：
error 1:
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [5] rhs shape= [1001]
官方给的是1000分类的ImagNet, 自己的数据需要重新训练
error 2:
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [5] rhs shape= [1001]
因为用cpu跑，修改train_image_classfier.py里的tf.app.Flags.DEFINE_boolean('clone_on_cpu',False,'use CPUs to deploy clones.')，False改成True.
可视化：
调用tensorboard以后显示TensorBoard 1.5.1 at http://localhost:6006 (Press CTRL+C to quit)，在浏览器打开http://localhost:6006即可