API tools faq
paste
Advertisement
Guest User

خروجی برنامه

a guest
Dec 26th, 2016
113
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 14.76 KB | None | 0 0
raw download clone embed print report
  1. I1227 01:35:41.192610 3821 caffe.cpp:217] Using GPUs 0
  2. I1227 01:35:41.256325 3821 caffe.cpp:222] GPU 0: GeForce GTX 1070
  3. I1227 01:35:41.766284 3821 solver.cpp:48] Initializing solver from parameters:
  4. test_iter: 1000
  5. test_interval: 1000
  6. base_lr: 0.01
  7. display: 20
  8. max_iter: 450000
  9. lr_policy: "step"
  10. gamma: 0.1
  11. momentum: 0.9
  12. weight_decay: 0.0005
  13. stepsize: 100000
  14. snapshot: 10000
  15. snapshot_prefix: "models/bvlc_alexnet/caffe_alexnet_train"
  16. solver_mode: GPU
  17. device_id: 0
  18. net: "models/bvlc_alexnet/train_valmnist.prototxt"
  19. train_state {
  20. level: 0
  21. stage: ""
  22. }
  23. I1227 01:35:41.766728 3821 solver.cpp:91] Creating training net from net file: models/bvlc_alexnet/train_valmnist.prototxt
  24. I1227 01:35:41.768218 3821 net.cpp:322] The NetState phase (0) differed from the phase (1) specified by a rule in layer data
  25. I1227 01:35:41.768262 3821 net.cpp:322] The NetState phase (0) differed from the phase (1) specified by a rule in layer accuracy
  26. I1227 01:35:41.768586 3821 net.cpp:58] Initializing net from parameters:
  27. name: "AlexNet"
  28. state {
  29. phase: TRAIN
  30. level: 0
  31. stage: ""
  32. }
  33. layer {
  34. name: "data"
  35. type: "Data"
  36. top: "data"
  37. top: "label"
  38. include {
  39. phase: TRAIN
  40. }
  41. transform_param {
  42. scale: 0.00390625
  43. }
  44. data_param {
  45. source: "examples/mnist/mnist_train_lmdb"
  46. batch_size: 64
  47. backend: LMDB
  48. }
  49. }
  50. layer {
  51. name: "conv1"
  52. type: "Convolution"
  53. bottom: "data"
  54. top: "conv1"
  55. param {
  56. lr_mult: 1
  57. decay_mult: 1
  58. }
  59. param {
  60. lr_mult: 2
  61. decay_mult: 0
  62. }
  63. convolution_param {
  64. num_output: 96
  65. kernel_size: 11
  66. stride: 4
  67. weight_filler {
  68. type: "gaussian"
  69. std: 0.01
  70. }
  71. bias_filler {
  72. type: "constant"
  73. value: 0
  74. }
  75. }
  76. }
  77. layer {
  78. name: "relu1"
  79. type: "ReLU"
  80. bottom: "conv1"
  81. top: "conv1"
  82. }
  83. layer {
  84. name: "norm1"
  85. type: "LRN"
  86. bottom: "conv1"
  87. top: "norm1"
  88. lrn_param {
  89. local_size: 5
  90. alpha: 0.0001
  91. beta: 0.75
  92. }
  93. }
  94. layer {
  95. name: "pool1"
  96. type: "Pooling"
  97. bottom: "norm1"
  98. top: "pool1"
  99. pooling_param {
  100. pool: MAX
  101. kernel_size: 3
  102. stride: 2
  103. }
  104. }
  105. layer {
  106. name: "conv2"
  107. type: "Convolution"
  108. bottom: "pool1"
  109. top: "conv2"
  110. param {
  111. lr_mult: 1
  112. decay_mult: 1
  113. }
  114. param {
  115. lr_mult: 2
  116. decay_mult: 0
  117. }
  118. convolution_param {
  119. num_output: 256
  120. pad: 2
  121. kernel_size: 5
  122. group: 2
  123. weight_filler {
  124. type: "gaussian"
  125. std: 0.01
  126. }
  127. bias_filler {
  128. type: "constant"
  129. value: 0.1
  130. }
  131. }
  132. }
  133. layer {
  134. name: "relu2"
  135. type: "ReLU"
  136. bottom: "conv2"
  137. top: "conv2"
  138. }
  139. layer {
  140. name: "norm2"
  141. type: "LRN"
  142. bottom: "conv2"
  143. top: "norm2"
  144. lrn_param {
  145. local_size: 5
  146. alpha: 0.0001
  147. beta: 0.75
  148. }
  149. }
  150. layer {
  151. name: "pool2"
  152. type: "Pooling"
  153. bottom: "norm2"
  154. top: "pool2"
  155. pooling_param {
  156. pool: MAX
  157. kernel_size: 3
  158. stride: 2
  159. }
  160. }
  161. layer {
  162. name: "conv3"
  163. type: "Convolution"
  164. bottom: "pool2"
  165. top: "conv3"
  166. param {
  167. lr_mult: 1
  168. decay_mult: 1
  169. }
  170. param {
  171. lr_mult: 2
  172. decay_mult: 0
  173. }
  174. convolution_param {
  175. num_output: 384
  176. pad: 1
  177. kernel_size: 3
  178. weight_filler {
  179. type: "gaussian"
  180. std: 0.01
  181. }
  182. bias_filler {
  183. type: "constant"
  184. value: 0
  185. }
  186. }
  187. }
  188. layer {
  189. name: "relu3"
  190. type: "ReLU"
  191. bottom: "conv3"
  192. top: "conv3"
  193. }
  194. layer {
  195. name: "conv4"
  196. type: "Convolution"
  197. bottom: "conv3"
  198. top: "conv4"
  199. param {
  200. lr_mult: 1
  201. decay_mult: 1
  202. }
  203. param {
  204. lr_mult: 2
  205. decay_mult: 0
  206. }
  207. convolution_param {
  208. num_output: 384
  209. pad: 1
  210. kernel_size: 3
  211. group: 2
  212. weight_filler {
  213. type: "gaussian"
  214. std: 0.01
  215. }
  216. bias_filler {
  217. type: "constant"
  218. value: 0.1
  219. }
  220. }
  221. }
  222. layer {
  223. name: "relu4"
  224. type: "ReLU"
  225. bottom: "conv4"
  226. top: "conv4"
  227. }
  228. layer {
  229. name: "conv5"
  230. type: "Convolution"
  231. bottom: "conv4"
  232. top: "conv5"
  233. param {
  234. lr_mult: 1
  235. decay_mult: 1
  236. }
  237. param {
  238. lr_mult: 2
  239. decay_mult: 0
  240. }
  241. convolution_param {
  242. num_output: 256
  243. pad: 1
  244. kernel_size: 3
  245. group: 2
  246. weight_filler {
  247. type: "gaussian"
  248. std: 0.01
  249. }
  250. bias_filler {
  251. type: "constant"
  252. value: 0.1
  253. }
  254. }
  255. }
  256. layer {
  257. name: "relu5"
  258. type: "ReLU"
  259. bottom: "conv5"
  260. top: "conv5"
  261. }
  262. layer {
  263. name: "pool5"
  264. type: "Pooling"
  265. bottom: "conv5"
  266. top: "pool5"
  267. pooling_param {
  268. pool: MAX
  269. kernel_size: 3
  270. stride: 2
  271. }
  272. }
  273. layer {
  274. name: "fc6"
  275. type: "InnerProduct"
  276. bottom: "pool5"
  277. top: "fc6"
  278. param {
  279. lr_mult: 1
  280. decay_mult: 1
  281. }
  282. param {
  283. lr_mult: 2
  284. decay_mult: 0
  285. }
  286. inner_product_param {
  287. num_output: 4096
  288. weight_filler {
  289. type: "gaussian"
  290. std: 0.005
  291. }
  292. bias_filler {
  293. type: "constant"
  294. value: 0.1
  295. }
  296. }
  297. }
  298. layer {
  299. name: "relu6"
  300. type: "ReLU"
  301. bottom: "fc6"
  302. top: "fc6"
  303. }
  304. layer {
  305. name: "drop6"
  306. type: "Dropout"
  307. bottom: "fc6"
  308. top: "fc6"
  309. dropout_param {
  310. dropout_ratio: 0.5
  311. }
  312. }
  313. layer {
  314. name: "fc7"
  315. type: "InnerProduct"
  316. bottom: "fc6"
  317. top: "fc7"
  318. param {
  319. lr_mult: 1
  320. decay_mult: 1
  321. }
  322. param {
  323. lr_mult: 2
  324. decay_mult: 0
  325. }
  326. inner_product_param {
  327. num_output: 4096
  328. weight_filler {
  329. type: "gaussian"
  330. std: 0.005
  331. }
  332. bias_filler {
  333. type: "constant"
  334. value: 0.1
  335. }
  336. }
  337. }
  338. layer {
  339. name: "relu7"
  340. type: "ReLU"
  341. bottom: "fc7"
  342. top: "fc7"
  343. }
  344. layer {
  345. name: "drop7"
  346. type: "Dropout"
  347. bottom: "fc7"
  348. top: "fc7"
  349. dropout_param {
  350. dropout_ratio: 0.5
  351. }
  352. }
  353. layer {
  354. name: "fc8"
  355. type: "InnerProduct"
  356. bottom: "fc7"
  357. top: "fc8"
  358. param {
  359. lr_mult: 1
  360. decay_mult: 1
  361. }
  362. param {
  363. lr_mult: 2
  364. decay_mult: 0
  365. }
  366. inner_product_param {
  367. num_output: 1000
  368. weight_filler {
  369. type: "gaussian"
  370. std: 0.01
  371. }
  372. bias_filler {
  373. type: "constant"
  374. value: 0
  375. }
  376. }
  377. }
  378. layer {
  379. name: "loss"
  380. type: "SoftmaxWithLoss"
  381. bottom: "fc8"
  382. bottom: "label"
  383. top: "loss"
  384. }
  385. I1227 01:35:41.769074 3821 layer_factory.hpp:77] Creating layer data
  386. I1227 01:35:41.770401 3821 net.cpp:100] Creating Layer data
  387. I1227 01:35:41.770426 3821 net.cpp:408] data -> data
  388. I1227 01:35:41.770462 3821 net.cpp:408] data -> label
  389. I1227 01:35:41.772739 3830 db_lmdb.cpp:35] Opened lmdb examples/mnist/mnist_train_lmdb
  390. I1227 01:35:41.854802 3821 data_layer.cpp:41] output data size: 64,1,28,28
  391. I1227 01:35:41.856761 3821 net.cpp:150] Setting up data
  392. I1227 01:35:41.856784 3821 net.cpp:157] Top shape: 64 1 28 28 (50176)
  393. I1227 01:35:41.856791 3821 net.cpp:157] Top shape: 64 (64)
  394. I1227 01:35:41.856796 3821 net.cpp:165] Memory required for data: 200960
  395. I1227 01:35:41.856808 3821 layer_factory.hpp:77] Creating layer conv1
  396. I1227 01:35:41.856842 3821 net.cpp:100] Creating Layer conv1
  397. I1227 01:35:41.856850 3821 net.cpp:434] conv1 <- data
  398. I1227 01:35:41.856869 3821 net.cpp:408] conv1 -> conv1
  399. I1227 01:35:41.858649 3821 net.cpp:150] Setting up conv1
  400. I1227 01:35:41.858671 3821 net.cpp:157] Top shape: 64 96 5 5 (153600)
  401. I1227 01:35:41.858676 3821 net.cpp:165] Memory required for data: 815360
  402. I1227 01:35:41.858700 3821 layer_factory.hpp:77] Creating layer relu1
  403. I1227 01:35:41.858716 3821 net.cpp:100] Creating Layer relu1
  404. I1227 01:35:41.858721 3821 net.cpp:434] relu1 <- conv1
  405. I1227 01:35:41.858731 3821 net.cpp:395] relu1 -> conv1 (in-place)
  406. I1227 01:35:41.858742 3821 net.cpp:150] Setting up relu1
  407. I1227 01:35:41.858752 3821 net.cpp:157] Top shape: 64 96 5 5 (153600)
  408. I1227 01:35:41.858757 3821 net.cpp:165] Memory required for data: 1429760
  409. I1227 01:35:41.858763 3821 layer_factory.hpp:77] Creating layer norm1
  410. I1227 01:35:41.858772 3821 net.cpp:100] Creating Layer norm1
  411. I1227 01:35:41.858783 3821 net.cpp:434] norm1 <- conv1
  412. I1227 01:35:41.858791 3821 net.cpp:408] norm1 -> norm1
  413. I1227 01:35:41.858846 3821 net.cpp:150] Setting up norm1
  414. I1227 01:35:41.858860 3821 net.cpp:157] Top shape: 64 96 5 5 (153600)
  415. I1227 01:35:41.858866 3821 net.cpp:165] Memory required for data: 2044160
  416. I1227 01:35:41.858872 3821 layer_factory.hpp:77] Creating layer pool1
  417. I1227 01:35:41.858882 3821 net.cpp:100] Creating Layer pool1
  418. I1227 01:35:41.858888 3821 net.cpp:434] pool1 <- norm1
  419. I1227 01:35:41.858897 3821 net.cpp:408] pool1 -> pool1
  420. I1227 01:35:41.858959 3821 net.cpp:150] Setting up pool1
  421. I1227 01:35:41.858969 3821 net.cpp:157] Top shape: 64 96 2 2 (24576)
  422. I1227 01:35:41.858999 3821 net.cpp:165] Memory required for data: 2142464
  423. I1227 01:35:41.859007 3821 layer_factory.hpp:77] Creating layer conv2
  424. I1227 01:35:41.859025 3821 net.cpp:100] Creating Layer conv2
  425. I1227 01:35:41.859030 3821 net.cpp:434] conv2 <- pool1
  426. I1227 01:35:41.859041 3821 net.cpp:408] conv2 -> conv2
  427. I1227 01:35:41.864717 3821 net.cpp:150] Setting up conv2
  428. I1227 01:35:41.864732 3821 net.cpp:157] Top shape: 64 256 2 2 (65536)
  429. I1227 01:35:41.864738 3821 net.cpp:165] Memory required for data: 2404608
  430. I1227 01:35:41.864751 3821 layer_factory.hpp:77] Creating layer relu2
  431. I1227 01:35:41.864761 3821 net.cpp:100] Creating Layer relu2
  432. I1227 01:35:41.864766 3821 net.cpp:434] relu2 <- conv2
  433. I1227 01:35:41.864773 3821 net.cpp:395] relu2 -> conv2 (in-place)
  434. I1227 01:35:41.864783 3821 net.cpp:150] Setting up relu2
  435. I1227 01:35:41.864789 3821 net.cpp:157] Top shape: 64 256 2 2 (65536)
  436. I1227 01:35:41.864794 3821 net.cpp:165] Memory required for data: 2666752
  437. I1227 01:35:41.864799 3821 layer_factory.hpp:77] Creating layer norm2
  438. I1227 01:35:41.864804 3821 net.cpp:100] Creating Layer norm2
  439. I1227 01:35:41.864809 3821 net.cpp:434] norm2 <- conv2
  440. I1227 01:35:41.864817 3821 net.cpp:408] norm2 -> norm2
  441. I1227 01:35:41.864857 3821 net.cpp:150] Setting up norm2
  442. I1227 01:35:41.864864 3821 net.cpp:157] Top shape: 64 256 2 2 (65536)
  443. I1227 01:35:41.864869 3821 net.cpp:165] Memory required for data: 2928896
  444. I1227 01:35:41.864874 3821 layer_factory.hpp:77] Creating layer pool2
  445. I1227 01:35:41.864883 3821 net.cpp:100] Creating Layer pool2
  446. I1227 01:35:41.864888 3821 net.cpp:434] pool2 <- norm2
  447. I1227 01:35:41.864895 3821 net.cpp:408] pool2 -> pool2
  448. I1227 01:35:41.864935 3821 net.cpp:150] Setting up pool2
  449. I1227 01:35:41.864943 3821 net.cpp:157] Top shape: 64 256 1 1 (16384)
  450. I1227 01:35:41.864948 3821 net.cpp:165] Memory required for data: 2994432
  451. I1227 01:35:41.864953 3821 layer_factory.hpp:77] Creating layer conv3
  452. I1227 01:35:41.864964 3821 net.cpp:100] Creating Layer conv3
  453. I1227 01:35:41.864969 3821 net.cpp:434] conv3 <- pool2
  454. I1227 01:35:41.864975 3821 net.cpp:408] conv3 -> conv3
  455. I1227 01:35:41.876174 3821 net.cpp:150] Setting up conv3
  456. I1227 01:35:41.876195 3821 net.cpp:157] Top shape: 64 384 1 1 (24576)
  457. I1227 01:35:41.876199 3821 net.cpp:165] Memory required for data: 3092736
  458. I1227 01:35:41.876211 3821 layer_factory.hpp:77] Creating layer relu3
  459. I1227 01:35:41.876220 3821 net.cpp:100] Creating Layer relu3
  460. I1227 01:35:41.876224 3821 net.cpp:434] relu3 <- conv3
  461. I1227 01:35:41.876230 3821 net.cpp:395] relu3 -> conv3 (in-place)
  462. I1227 01:35:41.876240 3821 net.cpp:150] Setting up relu3
  463. I1227 01:35:41.876245 3821 net.cpp:157] Top shape: 64 384 1 1 (24576)
  464. I1227 01:35:41.876250 3821 net.cpp:165] Memory required for data: 3191040
  465. I1227 01:35:41.876253 3821 layer_factory.hpp:77] Creating layer conv4
  466. I1227 01:35:41.876262 3821 net.cpp:100] Creating Layer conv4
  467. I1227 01:35:41.876267 3821 net.cpp:434] conv4 <- conv3
  468. I1227 01:35:41.876273 3821 net.cpp:408] conv4 -> conv4
  469. I1227 01:35:41.882702 3821 net.cpp:150] Setting up conv4
  470. I1227 01:35:41.882714 3821 net.cpp:157] Top shape: 64 384 1 1 (24576)
  471. I1227 01:35:41.882716 3821 net.cpp:165] Memory required for data: 3289344
  472. I1227 01:35:41.882722 3821 layer_factory.hpp:77] Creating layer relu4
  473. I1227 01:35:41.882728 3821 net.cpp:100] Creating Layer relu4
  474. I1227 01:35:41.882731 3821 net.cpp:434] relu4 <- conv4
  475. I1227 01:35:41.882736 3821 net.cpp:395] relu4 -> conv4 (in-place)
  476. I1227 01:35:41.882742 3821 net.cpp:150] Setting up relu4
  477. I1227 01:35:41.882745 3821 net.cpp:157] Top shape: 64 384 1 1 (24576)
  478. I1227 01:35:41.882748 3821 net.cpp:165] Memory required for data: 3387648
  479. I1227 01:35:41.882752 3821 layer_factory.hpp:77] Creating layer conv5
  480. I1227 01:35:41.882758 3821 net.cpp:100] Creating Layer conv5
  481. I1227 01:35:41.882761 3821 net.cpp:434] conv5 <- conv4
  482. I1227 01:35:41.882766 3821 net.cpp:408] conv5 -> conv5
  483. I1227 01:35:41.886646 3821 net.cpp:150] Setting up conv5
  484. I1227 01:35:41.886656 3821 net.cpp:157] Top shape: 64 256 1 1 (16384)
  485. I1227 01:35:41.886677 3821 net.cpp:165] Memory required for data: 3453184
  486. I1227 01:35:41.886687 3821 layer_factory.hpp:77] Creating layer relu5
  487. I1227 01:35:41.886694 3821 net.cpp:100] Creating Layer relu5
  488. I1227 01:35:41.886698 3821 net.cpp:434] relu5 <- conv5
  489. I1227 01:35:41.886703 3821 net.cpp:395] relu5 -> conv5 (in-place)
  490. I1227 01:35:41.886708 3821 net.cpp:150] Setting up relu5
  491. I1227 01:35:41.886713 3821 net.cpp:157] Top shape: 64 256 1 1 (16384)
  492. I1227 01:35:41.886714 3821 net.cpp:165] Memory required for data: 3518720
  493. I1227 01:35:41.886718 3821 layer_factory.hpp:77] Creating layer pool5
  494. I1227 01:35:41.886721 3821 net.cpp:100] Creating Layer pool5
  495. I1227 01:35:41.886724 3821 net.cpp:434] pool5 <- conv5
  496. I1227 01:35:41.886729 3821 net.cpp:408] pool5 -> pool5
  497. I1227 01:35:41.886754 3821 net.cpp:150] Setting up pool5
  498. I1227 01:35:41.886759 3821 net.cpp:157] Top shape: 64 256 0 0 (0)
  499. I1227 01:35:41.886761 3821 net.cpp:165] Memory required for data: 3518720
  500. I1227 01:35:41.886765 3821 layer_factory.hpp:77] Creating layer fc6
  501. I1227 01:35:41.886772 3821 net.cpp:100] Creating Layer fc6
  502. I1227 01:35:41.886775 3821 net.cpp:434] fc6 <- pool5
  503. I1227 01:35:41.886780 3821 net.cpp:408] fc6 -> fc6
  504. F1227 01:35:41.886826 3821 blob.cpp:115] Check failed: data_
  505. *** Check failure stack trace: ***
  506. @ 0x7f366ba695cd google::LogMessage::Fail()
  507. @ 0x7f366ba6b433 google::LogMessage::SendToLog()
  508. @ 0x7f366ba6915b google::LogMessage::Flush()
  509. @ 0x7f366ba6be1e google::LogMessageFatal::~LogMessageFatal()
  510. @ 0x7f366c217d3b caffe::Blob<>::mutable_cpu_data()
  511. @ 0x7f366c0f633a caffe::GaussianFiller<>::Fill()
  512. @ 0x7f366c0f6e27 caffe::InnerProductLayer<>::LayerSetUp()
  513. @ 0x7f366c0c17e2 caffe::Net<>::Init()
  514. @ 0x7f366c0c3071 caffe::Net<>::Net()
  515. @ 0x7f366c0d44aa caffe::Solver<>::InitTrainNet()
  516. @ 0x7f366c0d5817 caffe::Solver<>::Init()
  517. @ 0x7f366c0d5bba caffe::Solver<>::Solver()
  518. @ 0x7f366c20bc83 caffe::Creator_SGDSolver<>()
  519. @ 0x40afb9 train()
  520. @ 0x4077c8 main
  521. @ 0x7f366a200830 __libc_start_main
  522. @ 0x408099 _start
  523. @ (nil) (unknown)
  524. Aborted (core dumped)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!