API tools faq
paste
Advertisement
shayegh

log file

shayegh
Apr 12th, 2018
140
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 54.67 KB | None | 0 0
raw download clone embed print report
  1. ./caffe train --solver C:/Users/mahtab/Desktop/finetune_mitindoor67/solver.prototxt --weights C:/Users/mahtab/Desktop/finetune_mitindoor
  2. 67/places205CNN_iter_300000_upgraded.caffemodel 2>&1 | tee -a C:/Users/mahtab/Desktop/finetune_mitindoor67/modify_caffenet.log
  3. >>
  4. ./caffe : I0412 04:12:22.239899 4704 caffe.cpp:212] Use CPU.
  5. At line:1 char:1
  6. + ./caffe train --solver C:/Users/mahtab/Desktop/finetune_mitindoor67/s ...
  7. + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  8. + CategoryInfo : NotSpecified: (I0412 04:12:22....p:212] Use CPU.:String) [], Remote
  9. Exception
  10. + FullyQualifiedErrorId : NativeCommandError
  11.  
  12. I0412 04:12:22.239899 4704 solver.cpp:44] Initializing solver from parameters:
  13. test_iter: 134
  14. test_interval: 268
  15. base_lr: 1e-07
  16. display: 50
  17. max_iter: 100000
  18. lr_policy: "step"
  19. gamma: 0.1
  20. momentum: 0.9
  21. weight_decay: 0.0005
  22. stepsize: 20000
  23. snapshot: 10000
  24. snapshot_prefix: "C:/Users/mahtab/Desktop/finetune_mitindoor67"
  25. solver_mode: CPU
  26. net: "C:/Users/mahtab/Desktop/finetune_mitindoor67/SceneRecognitionCaffeNet.prototxt"
  27. train_state {
  28. level: 0
  29. stage: ""
  30. }
  31. I0412 04:12:22.239899 4704 solver.cpp:87] Creating training net from net file:
  32. C:/Users/mahtab/Desktop/finetune_mitindoor67/SceneRecognitionCaffeNet.prototxt
  33. I0412 04:12:22.239899 4704 net.cpp:294] The NetState phase (0) differed from the phase (1)
  34. specified by a rule in layer MITindoor67
  35. I0412 04:12:22.239899 4704 net.cpp:294] The NetState phase (0) differed from the phase (1)
  36. specified by a rule in layer accuracy
  37. I0412 04:12:22.239899 4704 net.cpp:51] Initializing net from parameters:
  38. name: "SceneRecognitionCaffeNet"
  39. state {
  40. phase: TRAIN
  41. level: 0
  42. stage: ""
  43. }
  44. layer {
  45. name: "MITindoor67"
  46. type: "Data"
  47. top: "data"
  48. top: "label"
  49. include {
  50. phase: TRAIN
  51. }
  52. transform_param {
  53. scale: 0.8
  54. mirror: true
  55. crop_size: 227
  56. mean_file: "mean.binaryproto"
  57. }
  58. data_param {
  59. source: "mydataset256_train_lmdb"
  60. batch_size: 20
  61. backend: LMDB
  62. }
  63. }
  64. layer {
  65. name: "conv1"
  66. type: "Convolution"
  67. bottom: "data"
  68. top: "conv1"
  69. param {
  70. lr_mult: 0
  71. decay_mult: 0
  72. }
  73. param {
  74. lr_mult: 0
  75. decay_mult: 0
  76. }
  77. convolution_param {
  78. num_output: 96
  79. kernel_size: 11
  80. stride: 4
  81. weight_filler {
  82. type: "gaussian"
  83. std: 0.01
  84. }
  85. bias_filler {
  86. type: "constant"
  87. value: 0
  88. }
  89. }
  90. }
  91. layer {
  92. name: "relu1"
  93. type: "ReLU"
  94. bottom: "conv1"
  95. top: "conv1"
  96. }
  97. layer {
  98. name: "pool1"
  99. type: "Pooling"
  100. bottom: "conv1"
  101. top: "pool1"
  102. pooling_param {
  103. pool: MAX
  104. kernel_size: 3
  105. stride: 2
  106. }
  107. }
  108. layer {
  109. name: "norm1"
  110. type: "LRN"
  111. bottom: "pool1"
  112. top: "norm1"
  113. lrn_param {
  114. local_size: 5
  115. alpha: 0.0001
  116. beta: 0.75
  117. }
  118. }
  119. layer {
  120. name: "conv2"
  121. type: "Convolution"
  122. bottom: "norm1"
  123. top: "conv2"
  124. param {
  125. lr_mult: 0
  126. decay_mult: 0
  127. }
  128. param {
  129. lr_mult: 0
  130. decay_mult: 0
  131. }
  132. convolution_param {
  133. num_output: 256
  134. pad: 2
  135. kernel_size: 5
  136. group: 2
  137. weight_filler {
  138. type: "gaussian"
  139. std: 0.01
  140. }
  141. bias_filler {
  142. type: "constant"
  143. value: 1
  144. }
  145. }
  146. }
  147. layer {
  148. name: "relu2"
  149. type: "ReLU"
  150. bottom: "conv2"
  151. top: "conv2"
  152. }
  153. layer {
  154. name: "pool2"
  155. type: "Pooling"
  156. bottom: "conv2"
  157. top: "pool2"
  158. pooling_param {
  159. pool: MAX
  160. kernel_size: 3
  161. stride: 2
  162. }
  163. }
  164. layer {
  165. name: "norm2"
  166. type: "LRN"
  167. bottom: "pool2"
  168. top: "norm2"
  169. lrn_param {
  170. local_size: 5
  171. alpha: 0.0001
  172. beta: 0.75
  173. }
  174. }
  175. layer {
  176. name: "conv3"
  177. type: "Convolution"
  178. bottom: "norm2"
  179. top: "conv3"
  180. param {
  181. lr_mult: 0
  182. decay_mult: 0
  183. }
  184. param {
  185. lr_mult: 0
  186. decay_mult: 0
  187. }
  188. convolution_param {
  189. num_output: 384
  190. pad: 1
  191. kernel_size: 3
  192. weight_filler {
  193. type: "gaussian"
  194. std: 0.01
  195. }
  196. bias_filler {
  197. type: "constant"
  198. value: 0
  199. }
  200. }
  201. }
  202. layer {
  203. name: "relu3"
  204. type: "ReLU"
  205. bottom: "conv3"
  206. top: "conv3"
  207. }
  208. layer {
  209. name: "conv4"
  210. type: "Convolution"
  211. bottom: "conv3"
  212. top: "conv4"
  213. param {
  214. lr_mult: 0
  215. decay_mult: 0
  216. }
  217. param {
  218. lr_mult: 0
  219. decay_mult: 0
  220. }
  221. convolution_param {
  222. num_output: 384
  223. pad: 1
  224. kernel_size: 3
  225. group: 2
  226. weight_filler {
  227. type: "gaussian"
  228. std: 0.01
  229. }
  230. bias_filler {
  231. type: "constant"
  232. value: 1
  233. }
  234. }
  235. }
  236. layer {
  237. name: "relu4"
  238. type: "ReLU"
  239. bottom: "conv4"
  240. top: "conv4"
  241. }
  242. layer {
  243. name: "conv5"
  244. type: "Convolution"
  245. bottom: "conv4"
  246. top: "conv5"
  247. param {
  248. lr_mult: 0
  249. decay_mult: 0
  250. }
  251. param {
  252. lr_mult: 0
  253. decay_mult: 0
  254. }
  255. convolution_param {
  256. num_output: 256
  257. pad: 1
  258. kernel_size: 3
  259. group: 2
  260. weight_filler {
  261. type: "gaussian"
  262. std: 0.01
  263. }
  264. bias_filler {
  265. type: "constant"
  266. value: 1
  267. }
  268. }
  269. }
  270. layer {
  271. name: "relu5"
  272. type: "ReLU"
  273. bottom: "conv5"
  274. top: "conv5"
  275. }
  276. layer {
  277. name: "pool5"
  278. type: "Pooling"
  279. bottom: "conv5"
  280. top: "pool5"
  281. pooling_param {
  282. pool: MAX
  283. kernel_size: 3
  284. stride: 2
  285. }
  286. }
  287. layer {
  288. name: "pool5_flatten"
  289. type: "Flatten"
  290. bottom: "pool5"
  291. top: "pool5_flatten"
  292. }
  293. layer {
  294. name: "fc6"
  295. type: "Convolution"
  296. bottom: "pool5_flatten"
  297. top: "fc6"
  298. param {
  299. lr_mult: 0
  300. decay_mult: 0
  301. }
  302. param {
  303. lr_mult: 0
  304. decay_mult: 0
  305. }
  306. convolution_param {
  307. num_output: 4096
  308. pad: 0
  309. kerne
  310. l_size: 7
  311. stride: 1
  312. }
  313. }
  314. layer {
  315. name: "relu6"
  316. type: "ReLU"
  317. bottom: "fc6"
  318. top: "fc6"
  319. }
  320. layer {
  321. name: "drop6"
  322. type: "Dropout"
  323. bottom: "fc6"
  324. top: "fc6"
  325. dropout_param {
  326. dropout_ratio: 0.5
  327. }
  328. }
  329. layer {
  330. name: "fc7"
  331. type: "Convolution"
  332. bottom: "fc6"
  333. top: "fc7"
  334. param {
  335. lr_mult: 0
  336. decay_mult: 0
  337. }
  338. param {
  339. lr_mult: 0
  340. decay_mult: 0
  341. }
  342. convolution_param {
  343. num_output: 4096
  344. kernel_size: 1
  345. stride: 1
  346. }
  347. }
  348. layer {
  349. name: "relu7"
  350. type: "ReLU"
  351. bottom: "fc7"
  352. top: "fc7"
  353. }
  354. layer {
  355. name: "drop7"
  356. type: "Dropout"
  357. bottom: "fc7"
  358. top: "fc7"
  359. dropout_param {
  360. dropout_ratio: 0.5
  361. }
  362. }
  363. layer {
  364. name: "fc8_mitindoor67"
  365. type: "Convolution"
  366. bottom: "fc7"
  367. top: "fc8_mitindoor67"
  368. param {
  369. lr_mult: 10
  370. decay_mult: 0
  371. }
  372. param {
  373. lr_mult: 20
  374. decay_mult: 0
  375. }
  376. convolution_param {
  377. num_output: 67
  378. kernel_size: 1
  379. stride: 1
  380. }
  381. }
  382. layer {
  383. name: "loss"
  384. type: "SoftmaxWithLoss"
  385. bottom: "fc8_mitindoor67"
  386. bottom: "label"
  387. top: "loss"
  388. }
  389. I0412 04:12:22.239899 4704 layer_factory.cpp:58] Creating layer MITindoor67
  390. I0412 04:12:22.239899 4704 db_lmdb.cpp:40] Opened lmdb mydataset256_train_lmdb
  391. I0412 04:12:22.239899 4704 net.cpp:84] Creating Layer MITindoor67
  392. I0412 04:12:22.239899 4704 net.cpp:380] MITindoor67 -> data
  393. I0412 04:12:22.239899 4704 net.cpp:380] MITindoor67 -> label
  394. I0412 04:12:22.239899 4704 data_transformer.cpp:25] Loading mean file from: mean.binaryproto
  395. I0412 04:12:22.257618 4704 common.cpp:36] System entropy source not available, using fallback
  396. algorithm to generate seed instead.
  397. I0412 04:12:22.257618 4704 data_layer.cpp:45] output data size: 20,3,227,227
  398. I0412 04:12:22.270828 4704 net.cpp:122] Setting up MITindoor67
  399. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 3 227 227 (3091740)
  400. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 (20)
  401. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 12367040
  402. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer conv1
  403. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer conv1
  404. I0412 04:12:22.270828 4704 net.cpp:406] conv1 <- data
  405. I0412 04:12:22.270828 4704 net.cpp:380] conv1 -> conv1
  406. I0412 04:12:22.270828 4704 net.cpp:122] Setting up conv1
  407. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 96 55 55 (5808000)
  408. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 35599040
  409. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer relu1
  410. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer relu1
  411. I0412 04:12:22.270828 4704 net.cpp:406] relu1 <- conv1
  412. I0412 04:12:22.270828 4704 net.cpp:367] relu1 -> conv1 (in-place)
  413. I0412 04:12:22.270828 4704 net.cpp:122] Setting up relu1
  414. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 96 55 55 (5808000)
  415. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 58831040
  416. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer pool1
  417. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer pool1
  418. I0412 04:12:22.270828 4704 net.cpp:406] pool1 <- conv1
  419. I0412 04:12:22.270828 4704 net.cpp:380] pool1 -> pool1
  420. I0412 04:12:22.270828 4704 net.cpp:122] Setting up pool1
  421. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 96 27 27 (1399680)
  422. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 64429760
  423. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer norm1
  424. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer norm1
  425. I0412 04:12:22.270828 4704 net.cpp:406] norm1 <- pool1
  426. I0412 04:12:22.270828 4704 net.cpp:380] norm1 -> norm1
  427. I0412 04:12:22.270828 4704 net.cpp:122] Setting up norm1
  428. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 96 27 27 (1399680)
  429. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 70028480
  430. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer conv2
  431. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer conv2
  432. I0412 04:12:22.270828 4704 net.cpp:406] conv2 <- norm1
  433. I0412 04:12:22.270828 4704 net.cpp:380] conv2 -> conv2
  434. I0412 04:12:22.270828 4704 net.cpp:122] Setting up conv2
  435. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 256 27 27 (3732480)
  436. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 84958400
  437. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer relu2
  438. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer relu2
  439. I0412 04:12:22.270828 4704 net.cpp:406] relu2 <- conv2
  440. I0412 04:12:22.270828 4704 net.cpp:367] relu2 -> conv2 (in-place)
  441. I0412 04:12:22.270828 4704 net.cpp:122] Setting up relu2
  442. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 256 27 27 (3732480)
  443. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 99888320
  444. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer pool2
  445. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer pool2
  446. I0412 04:12:22.270828 4704 net.cpp:406] pool2 <- conv2
  447. I0412 04:12:22.270828 4704 net.cpp:380] pool2 -> pool2
  448. I0412 04:12:22.270828 4704 net.cpp:122] Setting up pool2
  449. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 256 13 13 (865280)
  450. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 103349440
  451. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer norm2
  452. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer norm2
  453. I0412 04:12:22.270828 4704 net.cpp:406] norm2 <- pool2
  454. I0412 04:12:22.270828 4704 net.cpp:380] norm2 -> norm2
  455. I0412 04:12:22.270828 4704 net.cpp:122] Setting up norm2
  456. I0412 04:12:22.270828 4704 net.cpp:129] Top shape: 20 256 13 13 (865280)
  457. I0412 04:12:22.270828 4704 net.cpp:137] Memory required for data: 106810560
  458. I0412 04:12:22.270828 4704 layer_factory.cpp:58] Creating layer conv3
  459. I0412 04:12:22.270828 4704 net.cpp:84] Creating Layer conv3
  460. I0412 04:12:22.270828 4704 net.cpp:406] conv3 <- norm2
  461. I0412 04:12:22.270828 4704 net.cpp:380] conv3 -> conv3
  462. I0412 04:12:22.286504 4704 net.cpp:122] Setting up conv3
  463. I0412 04:12:22.286504 4704 net.cpp:129] Top shape: 20 384 13 13 (1297920)
  464. I0412 04:12:22.286504 4704 net.cpp:137] Memory required for data: 112002240
  465. I0412 04:12:22.286504 4704 layer_factory.cpp:58] Creating layer relu3
  466. I0412 04:12:22.286504 4704 net.cpp:84] Creating Layer relu3
  467. I0412 04:12:22.286504 4704 net.cpp:406] relu3 <- conv3
  468. I0412 04:12:22.286504 4704 net.cpp:367] relu3 -> conv3 (in-place)
  469. I0412 04:12:22.286504 4704 net.cpp:122] Setting up relu3
  470. I0412 04:12:22.286504 4704 net.cpp:129] Top shape: 20 384 13 13 (1297920)
  471. I0412 04:12:22.286504 4704 net.cpp:137] Memory required for data: 117193920
  472. I0412 04:12:22.286504 4704 layer_factory.cpp:58] Creating layer conv4
  473. I0412 04:12:22.286504 4704 net.cpp:84] Creating Layer conv4
  474. I0412 04:12:22.286504 4704 net.cpp:406] conv4 <- conv3
  475. I0412 04:12:22.286504 4704 net.cpp:380] conv4 -> conv4
  476. I0412 04:12:22.286504 4704 net.cpp:122] Setting up conv4
  477. I0412 04:12:22.286504 4704 net.cpp:129] Top shape: 20 384 13 13 (1297920)
  478. I0412 04:12:22.286504 4704 net.cpp:137] Memory required for data: 122385600
  479. I0412 04:12:22.286504 4704 layer_factory.cpp:58] Creating layer relu4
  480. I0412 04:12:22.286504 4704 net.cpp:84] Creating Layer relu4
  481. I0412 04:12:22.286504 4704 net.cpp:406] relu4 <- conv4
  482. I0412 04:12:22.286504 4704 net.cpp:367] relu4 -> conv4 (in-place)
  483. I0412 04:12:22.286504 4704 net.cpp:122] Setting up relu4
  484. I0412 04:12:22.286504 4704 net.cpp:129] Top shape: 20 384 13 13 (1297920)
  485. I0412 04:12:22.286504 4704 net.cpp:137] Memory required for data: 127577280
  486. I0412 04:12:22.286504 4704 layer_factory.cpp:58] Creating layer conv5
  487. I0412 04:12:22.286504 4704 net.cpp:84] Creating Layer conv5
  488. I0412 04:12:22.286504 4704 net.cpp:406] conv5 <- conv4
  489. I0412 04:12:22.286504 4704 net.cpp:380] conv5 -> conv5
  490. I0412 04:12:22.302098 4704 net.cpp:122] Setting up conv5
  491. I0412 04:12:22.302098 4704 net.cpp:129] Top shape: 20 256 13 13 (865280)
  492. I0412 04:12:22.302098 4704 net.cpp:137] Memory required for data: 131038400
  493. I0412 04:12:22.302098 4704 layer_factory.cpp:58] Creating layer relu5
  494. I0412 04:12:22.302098 4704 net.cpp:84] Creating Layer relu5
  495. I0412 04:12:22.302098 4704 net.cpp:406] relu5 <- conv5
  496. I0412 04:12:22.302098 4704 net.cpp:367] relu5 -> conv5 (in-place)
  497. I0412 04:12:22.302098 4704 net.cpp:122] Setting up relu5
  498. I0412 04:12:22.302098 4704 net.cpp:129] Top shape: 20 256 13 13 (865280)
  499. I0412 04:12:22.302098 4704 net.cpp:137] Memory required for data: 134499520
  500. I0412 04:12:22.302098 4704 layer_factory.cpp:58] Creating layer pool5
  501. I0412 04:12:22.302098 4704 net.cpp:84] Creating Layer pool5
  502. I0412 04:12:22.302098 4704 net.cpp:406] pool5 <- conv5
  503. I0412 04:12:22.302098 4704 net.cpp:380] pool5 -> pool5
  504. I0412 04:12:22.302098 4704 net.cpp:122] Setting up pool5
  505. I0412 04:12:22.302098 4704 net.cpp:129] Top shape: 20 256 6 6 (184320)
  506. I0412 04:12:22.302098 4704 net.cpp:137] Memory required for data: 135236800
  507. I0412 04:12:22.302098 4704 layer_factory.cpp:58] Creating layer pool5_flatten
  508. I0412 04:12:22.302098 4704 net.cpp:84] Creating Layer pool5_flatten
  509. I0412 04:12:22.302098 4704 net.cpp:406] pool5_flatten <- pool5
  510. I0412 04:12:22.302098 4704 net.cpp:380] pool5_flatten -> pool5_flatten
  511. I0412 04:12:22.302098 4704 net.cpp:122] Setting up pool5_flatten
  512. I0412 04:12:22.302098 4704 net.cpp:129] Top shape: 20 9216 (184320)
  513. I0412 04:12:22.302098 4704 net.cpp:137] Memory required for data: 135974080
  514. I0412 04:12:22.302098 4704 layer_factory.cpp:58] Creating layer fc6
  515. I0412 04:12:22.302098 4704 net.cpp:84] Creating Layer fc6
  516. I0412 04:12:22.302098 4704 net.cpp:406] fc6 <- pool5_flatten
  517. I0412 04:12:22.302098 4704 net.cpp:380] fc6 -> fc6
  518. I0412 04:12:22.333617 4704 net.cpp:122] Setting up fc6
  519. I0412 04:12:22.333617 4704 net.cpp:129] Top shape: 20 4096 (81920)
  520. I0412 04:12:22.333617 4704 net.cpp:137] Memory required for data: 136301760
  521. I0412 04:12:22.333617 4704 layer_factory.cpp:58] Creating layer relu6
  522. I0412 04:12:22.333617 4704 net.cpp:84] Creating Layer relu6
  523. I0412 04:12:22.333617 4704 net.cpp:406] relu6 <- fc6
  524. I0412 04:12:22.333617 4704 net.cpp:367] relu6 -> fc6 (in-place)
  525. I0412 04:12:22.333617 4704 net.cpp:122] Setting up relu6
  526. I0412 04:12:22.333617 4704 net.cpp:129] Top shape: 20 4096 (81920)
  527. I0412 04:12:22.333617 4704 net.cpp:137] Memory required for data: 136629440
  528. I0412 04:12:22.333617 4704 layer_factory.cpp:58] Creating layer drop6
  529. I0412 04:12:22.333617 4704 net.cpp:84] Creating Layer drop6
  530. I0412 04:12:22.333617 4704 net.cpp:406] drop6 <- fc6
  531. I0412 04:12:22.333617 4704 net.cpp:367] drop6 -> fc6 (in-place)
  532. I0412 04:12:22.333617 4704 net.cpp:122] Setting up drop6
  533. I0412 04:12:22.333617 4704 net.cpp:129] Top shape: 20 4096 (81920)
  534. I0412 04:12:22.333617 4704 net.cpp:137] Memory required for data: 136957120
  535. I0412 04:12:22.333617 4704 layer_factory.cpp:58] Creating layer fc7
  536. I0412 04:12:22.333617 4704 net.cpp:84] Creating Layer fc7
  537. I0412 04:12:22.333617 4704 net.cpp:406] fc7 <- fc6
  538. I0412 04:12:22.333617 4704 net.cpp:380] fc7 -> fc7
  539. I0412 04:12:22.364234 4704 net.cpp:122] Setting up fc7
  540. I0412 04:12:22.364234 4704 net.cpp:129] Top shape: 20 4096 (81920)
  541. I0412 04:12:22.364234 4704 net.cpp:137] Memory required for data: 137284800
  542. I0412 04:12:22.364234 4704 layer_factory.cpp:58] Creating layer relu7
  543. I0412 04:12:22.364234 4704 net.cpp:84] Creating Layer relu7
  544. I0412 04:12:22.364234 4704 net.cpp:406] relu7 <- fc7
  545. I0412 04:12:22.364234 4704 net.cpp:367] relu7 -> fc7 (in-place)
  546. I0412 04:12:22.364234 4704 net.cpp:122] Setting up relu7
  547. I0412 04:12:22.364234 4704 net.cpp:129] Top shape: 20 4096 (81920)
  548. I0412 04:12:22.364234 4704 net.cpp:137] Memory required for data: 137612480
  549. I0412 04:12:22.364234 4704 layer_factory.cpp:58] Creating layer drop7
  550. I0412 04:12:22.364234 4704 net.cpp:84] Creating Layer drop7
  551. I0412 04:12:22.364234 4704 net.cpp:406] drop7 <- fc7
  552. I0412 04:12:22.364234 4704 net.cpp:367] drop7 -> fc7 (in-place)
  553. I0412 04:12:22.364234 4704 net.cpp:122] Setting up drop7
  554. I0412 04:12:22.364234 4704 net.cpp:129] Top shape: 20 4096 (81920)
  555. I0412 04:12:22.364234 4704 net.cpp:137] Memory required for data: 137940160
  556. I0412 04:12:22.364234 4704 layer_factory.cpp:58] Creating layer fc8_mitindoor67
  557. I0412 04:12:22.364234 4704 net.cpp:84] Creating Layer fc8_mitindoor67
  558. I0412 04:12:22.364234 4704 net.cpp:406] fc8_mitindoor67 <- fc7
  559. I0412 04:12:22.364234 4704 net.cpp:380] fc8_mitindoor67 -> fc8_mitindoor67
  560. I0412 04:12:22.364234 4704 net.cpp:122] Setting up fc8_mitindoor67
  561. I0412 04:12:22.364234 4704 net.cpp:129] Top shape: 20 67 (1340)
  562. I0412 04:12:22.364234 4704 net.cpp:137] Memory required for data: 137945520
  563. I0412 04:12:22.364234 4704 layer_factory.cpp:58] Creating layer loss
  564. I0412 04:12:22.364234 4704 net.cpp:84] Creating Layer loss
  565. I0412 04:12:22.364234 4704 net.cpp:406] loss <- fc8_mitindoor67
  566. I0412 04:12:22.364234 4704 net.cpp:406] loss <- label
  567. I0412 04:12:22.364234 4704 net.cpp:380] loss -> loss
  568. I0412 04:12:22.364234 4704 layer_factory.cpp:58] Creating layer loss
  569. I0412 04:12:22.364234 4704 net.cpp:122] Setting up loss
  570. I0412 04:12:22.364234 4704 net.cpp:129] Top shape: (1)
  571. I0412 04:12:22.364234 4704 net.cpp:132] with loss weight 1
  572. I0412 04:12:22.364234 4704 net.cpp:137] Memory required for data: 137945524
  573. I0412 04:12:22.364234 4704 net.cpp:198] loss needs backward computation.
  574. I0412 04:12:22.364234 4704 net.cpp:198] fc8_mitindoor67 needs backward computation.
  575. I0412 04:12:22.364234 4704 net.cpp:200] drop7 does not need backward computation.
  576. I0412 04:12:22.364234 4704 net.cpp:200] relu7 does not need backward computation.
  577. I0412 04:12:22.364234 4704 net.cpp:200] fc7 does not need backward computation.
  578. I0412 04:12:22.364234 4704 net.cpp:200] drop6 does not need backward computation.
  579. I0412 04:12:22.364234 4704 net.cpp:200] relu6 does not need backward computation.
  580. I0412 04:12:22.364234 4704 net.cpp:200] fc6 does not need backward computation.
  581. I0412 04:12:22.364234 4704 net.cpp:200] pool5_flatten does not need backward computation.
  582. I0412 04:12:22.364234 4704 net.cpp:200] pool5 does not need backward computation.
  583. I0412 04:12:22.364234 4704 net.cpp:200] relu5 does not need backward computation.
  584. I0412 04:12:22.364234 4704 net.cpp:200] conv5 does not need backward computation.
  585. I0412 04:12:22.364234 4704 net.cpp:200] relu4 does not need backward computation.
  586. I0412 04:12:22.364234 4704 net.cpp:200] conv4 does not need backward computation.
  587. I0412 04:12:22.364234 4704 net.cpp:200] relu3 does not need backward computation.
  588. I0412 04:12:22.364234 4704 net.cpp:200] conv3 does not need backward computation.
  589. I0412 04:12:22.364234 4704 net.cpp:200] norm2 does not need backward computation.
  590. I0412 04:12:22.364234 4704 net.cpp:200] pool2 does not need backward computation.
  591. I0412 04:12:22.364234 4704 net.cpp:200] relu2 does not need backward computation.
  592. I0412 04:12:22.364234 4704 net.cpp:200] conv2 does not need backward computation.
  593. I0412 04:12:22.364234 4704 net.cpp:200] norm1 does not need backward computation.
  594. I0412 04:12:22.364234 4704 net.cpp:200] pool1 does not need backward computation.
  595. I0412 04:12:22.364234 4704 net.cpp:200] relu1 does not need backward computation.
  596. I0412 04:12:22.364234 4704 net.cpp:200] conv1 does not need backward computation.
  597. I0412 04:12:22.364234 4704 net.cpp:200] MITindoor67 does not need backward computatio
  598. n.
  599. I0412 04:12:22.536056 4704 net.cpp:242] This network produces output loss
  600. I0412 04:12:22.536056 4704 net.cpp:255] Network initialization done.
  601. I0412 04:12:22.536056 4704 solver.cpp:172] Creating test net (#0) specified by net file:
  602. C:/Users/mahtab/Desktop/finetune_mitindoor67/SceneRecognitionCaffeNet.prototxt
  603. I0412 04:12:22.536056 4704 net.cpp:294] The NetState phase (1) differed from the phase (0)
  604. specified by a rule in layer MITindoor67
  605. I0412 04:12:22.536056 4704 net.cpp:51] Initializing net from parameters:
  606. name: "SceneRecognitionCaffeNet"
  607. state {
  608. phase: TEST
  609. }
  610. layer {
  611. name: "MITindoor67"
  612. type: "Data"
  613. top: "data"
  614. top: "label"
  615. include {
  616. phase: TEST
  617. }
  618. transform_param {
  619. mirror: false
  620. crop_size: 227
  621. mean_file: "mean.binaryproto"
  622. }
  623. data_param {
  624. source: "mydataset256_test_lmdb"
  625. batch_size: 10
  626. backend: LMDB
  627. }
  628. }
  629. layer {
  630. name: "conv1"
  631. type: "Convolution"
  632. bottom: "data"
  633. top: "conv1"
  634. param {
  635. lr_mult: 0
  636. decay_mult: 0
  637. }
  638. param {
  639. lr_mult: 0
  640. decay_mult: 0
  641. }
  642. convolution_param {
  643. num_output: 96
  644. kernel_size: 11
  645. stride: 4
  646. weight_filler {
  647. type: "gaussian"
  648. std: 0.01
  649. }
  650. bias_filler {
  651. type: "constant"
  652. value: 0
  653. }
  654. }
  655. }
  656. layer {
  657. name: "relu1"
  658. type: "ReLU"
  659. bottom: "conv1"
  660. top: "conv1"
  661. }
  662. layer {
  663. name: "pool1"
  664. type: "Pooling"
  665. bottom: "conv1"
  666. top: "pool1"
  667. pooling_param {
  668. pool: MAX
  669. kernel_size: 3
  670. stride: 2
  671. }
  672. }
  673. layer {
  674. name: "norm1"
  675. type: "LRN"
  676. bottom: "pool1"
  677. top: "norm1"
  678. lrn_param {
  679. local_size: 5
  680. alpha: 0.0001
  681. beta: 0.75
  682. }
  683. }
  684. layer {
  685. name: "conv2"
  686. type: "Convolution"
  687. bottom: "norm1"
  688. top: "conv2"
  689. param {
  690. lr_mult: 0
  691. decay_mult: 0
  692. }
  693. param {
  694. lr_mult: 0
  695. decay_mult: 0
  696. }
  697. convolution_param {
  698. num_output: 256
  699. pad: 2
  700. kernel_size: 5
  701. group: 2
  702. weight_filler {
  703. type: "gaussian"
  704. std: 0.01
  705. }
  706. bias_filler {
  707. type: "constant"
  708. value: 1
  709. }
  710. }
  711. }
  712. layer {
  713. name: "relu2"
  714. type: "ReLU"
  715. bottom: "conv2"
  716. top: "conv2"
  717. }
  718. layer {
  719. name: "pool2"
  720. type: "Pooling"
  721. bottom: "conv2"
  722. top: "pool2"
  723. pooling_param {
  724. pool: MAX
  725. kernel_size: 3
  726. stride: 2
  727. }
  728. }
  729. layer {
  730. name: "norm2"
  731. type: "LRN"
  732. bottom: "pool2"
  733. top: "norm2"
  734. lrn_param {
  735. local_size: 5
  736. alpha: 0.0001
  737. beta: 0.75
  738. }
  739. }
  740. layer {
  741. name: "conv3"
  742. type: "Convolution"
  743. bottom: "norm2"
  744. top: "conv3"
  745. param {
  746. lr_mult: 0
  747. decay_mult: 0
  748. }
  749. param {
  750. lr_mult: 0
  751. decay_mult: 0
  752. }
  753. convolution_param {
  754. num_output: 384
  755. pad: 1
  756. kernel_size: 3
  757. weight_filler {
  758. type: "gaussian"
  759. std: 0.01
  760. }
  761. bias_filler {
  762. type: "constant"
  763. value: 0
  764. }
  765. }
  766. }
  767. layer {
  768. name: "relu3"
  769. type: "ReLU"
  770. bottom: "conv3"
  771. top: "conv3"
  772. }
  773. layer {
  774. name: "conv4"
  775. type: "Convolution"
  776. bottom: "conv3"
  777. top: "conv4"
  778. param {
  779. lr_mult: 0
  780. decay_mult: 0
  781. }
  782. param {
  783. lr_mult: 0
  784. decay_mult: 0
  785. }
  786. convolution_param {
  787. num_output: 384
  788. pad: 1
  789. kernel_size: 3
  790. group: 2
  791. weight_filler {
  792. type: "gaussian"
  793. std: 0.01
  794. }
  795. bias_filler {
  796. type: "constant"
  797. value: 1
  798. }
  799. }
  800. }
  801. layer {
  802. name: "relu4"
  803. type: "ReLU"
  804. bottom: "conv4"
  805. top: "conv4"
  806. }
  807. layer {
  808. name: "conv5"
  809. type: "Convolution"
  810. bottom: "conv4"
  811. top: "conv5"
  812. param {
  813. lr_mult: 0
  814. decay_mult: 0
  815. }
  816. param {
  817. lr_mult: 0
  818. decay_mult: 0
  819. }
  820. convolution_param {
  821. num_output: 256
  822. pad: 1
  823. kernel_size: 3
  824. group: 2
  825. weight_filler {
  826. type: "gaussian"
  827. std: 0.01
  828. }
  829. bias_filler {
  830. type: "constant"
  831. value: 1
  832. }
  833. }
  834. }
  835. layer {
  836. name: "relu5"
  837. type: "ReLU"
  838. bottom: "conv5"
  839. top: "conv5"
  840. }
  841. layer {
  842. name: "pool5"
  843. type: "Pooling"
  844. bottom: "conv5"
  845. top: "pool5"
  846. pooling_param {
  847.  
  848. pool: MAX
  849. kernel_size: 3
  850. stride: 2
  851. }
  852. }
  853. layer {
  854. name: "pool5_flatten"
  855. type: "Flatten"
  856. bottom: "pool5"
  857. top: "pool5_flatten"
  858. }
  859. layer {
  860. name: "fc6"
  861. type: "Convolution"
  862. bottom: "pool5_flatten"
  863. top: "fc6"
  864. param {
  865. lr_mult: 0
  866. decay_mult: 0
  867. }
  868. param {
  869. lr_mult: 0
  870. decay_mult: 0
  871. }
  872. convolution_param {
  873. num_output: 4096
  874. pad: 0
  875. kernel_size: 7
  876. stride: 1
  877. }
  878. }
  879. layer {
  880. name: "relu6"
  881. type: "ReLU"
  882. bottom: "fc6"
  883. top: "fc6"
  884. }
  885. layer {
  886. name: "drop6"
  887. type: "Dropout"
  888. bottom: "fc6"
  889. top: "fc6"
  890. dropout_param {
  891. dropout_ratio: 0.5
  892. }
  893. }
  894. layer {
  895. name: "fc7"
  896. type: "Convolution"
  897. bottom: "fc6"
  898. top: "fc7"
  899. param {
  900. lr_mult: 0
  901. decay_mult: 0
  902. }
  903. param {
  904. lr_mult: 0
  905. decay_mult: 0
  906. }
  907. convolution_param {
  908. num_output: 4096
  909. kernel_size: 1
  910. stride: 1
  911. }
  912. }
  913. layer {
  914. name: "relu7"
  915. type: "ReLU"
  916. bottom: "fc7"
  917. top: "fc7"
  918. }
  919. layer {
  920. name: "drop7"
  921. type: "Dropout"
  922. bottom: "fc7"
  923. top: "fc7"
  924. dropout_param {
  925. dropout_ratio: 0.5
  926. }
  927. }
  928. layer {
  929. name: "fc8_mitindoor67"
  930. type: "Convolution"
  931. bottom: "fc7"
  932. top: "fc8_mitindoor67"
  933. param {
  934. lr_mult: 10
  935. decay_mult: 0
  936. }
  937. param {
  938. lr_mult: 20
  939. decay_mult: 0
  940. }
  941. convolution_param {
  942. num_output: 67
  943. kernel_size: 1
  944. stride: 1
  945. }
  946. }
  947. layer {
  948. name: "loss"
  949. type: "SoftmaxWithLoss"
  950. bottom: "fc8_mitindoor67"
  951. bottom: "label"
  952. top: "loss"
  953. }
  954. layer {
  955. name: "accuracy"
  956. type: "Accuracy"
  957. bottom: "fc8_mitindoor67"
  958. bottom: "label"
  959. top: "accuracy"
  960. include {
  961. phase: TEST
  962. }
  963. }
  964. I0412 04:12:22.598542 4704 layer_factory.cpp:58] Creating layer MITindoor67
  965. I0412 04:12:22.598542 4704 db_lmdb.cpp:40] Opened lmdb mydataset256_test_lmdb
  966. I0412 04:12:22.598542 4704 net.cpp:84] Creating Layer MITindoor67
  967. I0412 04:12:22.598542 4704 net.cpp:380] MITindoor67 -> data
  968. I0412 04:12:22.598542 4704 net.cpp:380] MITindoor67 -> label
  969. I0412 04:12:22.598542 4704 data_transformer.cpp:25] Loading mean file from: mean.binaryproto
  970. I0412 04:12:22.598542 4704 data_layer.cpp:45] output data size: 10,3,227,227
  971. I0412 04:12:22.614207 4704 net.cpp:122] Setting up MITindoor67
  972. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 3 227 227 (1545870)
  973. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 (10)
  974. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 6183520
  975. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer label_MITindoor67_1_split
  976. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer label_MITindoor67_1_split
  977. I0412 04:12:22.614207 4704 net.cpp:406] label_MITindoor67_1_split <- label
  978. I0412 04:12:22.614207 4704 net.cpp:380] label_MITindoor67_1_split -> label_MITindoor67_1_split_0
  979. I0412 04:12:22.614207 4704 net.cpp:380] label_MITindoor67_1_split -> label_MITindoor67_1_split_1
  980. I0412 04:12:22.614207 4704 net.cpp:122] Setting up label_MITindoor67_1_split
  981. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 (10)
  982. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 (10)
  983. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 6183600
  984. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer conv1
  985. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer conv1
  986. I0412 04:12:22.614207 4704 net.cpp:406] conv1 <- data
  987. I0412 04:12:22.614207 4704 net.cpp:380] conv1 -> conv1
  988. I0412 04:12:22.614207 4704 net.cpp:122] Setting up conv1
  989. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 96 55 55 (2904000)
  990. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 17799600
  991. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer relu1
  992. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer relu1
  993. I0412 04:12:22.614207 4704 net.cpp:406] relu1 <- conv1
  994. I0412 04:12:22.614207 4704 net.cpp:367] relu1 -> conv1 (in-place)
  995. I0412 04:12:22.614207 4704 net.cpp:122] Setting up relu1
  996. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 96 55 55 (2904000)
  997. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 29415600
  998. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer pool1
  999. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer pool1
  1000. I0412 04:12:22.614207 4704 net.cpp:406] pool1 <- conv1
  1001. I0412 04:12:22.614207 4704 net.cpp:380] pool1 -> pool1
  1002. I0412 04:12:22.614207 4704 net.cpp:122] Setting up pool1
  1003. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 96 27 27 (699840)
  1004. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 32214960
  1005. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer norm1
  1006. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer norm1
  1007. I0412 04:12:22.614207 4704 net.cpp:406] norm1 <- pool1
  1008. I0412 04:12:22.614207 4704 net.cpp:380] norm1 -> norm1
  1009. I0412 04:12:22.614207 4704 net.cpp:122] Setting up norm1
  1010. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 96 27 27 (699840)
  1011. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 35014320
  1012. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer conv2
  1013. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer conv2
  1014. I0412 04:12:22.614207 4704 net.cpp:406] conv2 <- norm1
  1015. I0412 04:12:22.614207 4704 net.cpp:380] conv2 -> conv2
  1016. I0412 04:12:22.614207 4704 net.cpp:122] Setting up conv2
  1017. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 256 27 27 (1866240)
  1018. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 42479280
  1019. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer relu2
  1020. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer relu2
  1021. I0412 04:12:22.614207 4704 net.cpp:406] relu2 <- conv2
  1022. I0412 04:12:22.614207 4704 net.cpp:367] relu2 -> conv2 (in-place)
  1023. I0412 04:12:22.614207 4704 net.cpp:122] Setting up relu2
  1024. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 256 27 27 (1866240)
  1025. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 49944240
  1026. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer pool2
  1027. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer pool2
  1028. I0412 04:12:22.614207 4704 net.cpp:406] pool2 <- conv2
  1029. I0412 04:12:22.614207 4704 net.cpp:380] pool2 -> pool2
  1030. I0412 04:12:22.614207 4704 net.cpp:122] Setting up pool2
  1031. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 256 13 13 (432640)
  1032. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 51674800
  1033. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer norm2
  1034. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer norm2
  1035. I0412 04:12:22.614207 4704 net.cpp:406] norm2 <- pool2
  1036. I0412 04:12:22.614207 4704 net.cpp:380] norm2 -> norm2
  1037. I0412 04:12:22.614207 4704 net.cpp:122] Setting up norm2
  1038. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 256 13 13 (432640)
  1039. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 53405360
  1040. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer conv3
  1041. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer conv3
  1042. I0412 04:12:22.614207 4704 net.cpp:406] conv3 <- norm2
  1043. I0412 04:12:22.614207 4704 net.cpp:380] conv3 -> conv3
  1044. I0412 04:12:22.614207 4704 net.cpp:122] Setting up conv3
  1045. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 384 13 13 (648960)
  1046. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 56001200
  1047. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer relu3
  1048. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer relu3
  1049. I0412 04:12:22.614207 4704 net.cpp:406] relu3 <- conv3
  1050. I0412 04:12:22.614207 4704 net.cpp:367] relu3 -> conv3 (in-place)
  1051. I0412 04:12:22.614207 4704 net.cpp:122] Setting up relu3
  1052. I0412 04:12:22.614207 4704 net.cpp:129] Top shape: 10 384 13 13 (648960)
  1053. I0412 04:12:22.614207 4704 net.cpp:137] Memory required for data: 58597040
  1054. I0412 04:12:22.614207 4704 layer_factory.cpp:58] Creating layer conv4
  1055. I0412 04:12:22.614207 4704 net.cpp:84] Creating Layer conv4
  1056. I0412 04:12:22.614207 4704 net.cpp:406] conv4 <- conv3
  1057. I0412 04:12:22.614207 4704 net.cpp:380] conv4 -> conv4
  1058. I0412 04:12:22.629875 4704 net.cpp:122] Setting up conv4
  1059. I0412 04:12:22.629875 4704 net.cpp:129] Top shape: 10 384 13 13 (648960)
  1060. I0412 04:12:22.629875 4704 net.cpp:137] Memory required for data: 61192880
  1061. I0412 04:12:22.629875 4704 layer_factory.cpp:58] Creating layer relu4
  1062. I0412 04:12:22.629875 4704 net.cpp:84] Creating Layer relu4
  1063. I0412 04:12:22.629875 4704 net.cpp:406] relu4 <- conv4
  1064. I0412 04:12:22.629875 4704 net.cpp:367] relu4 -> conv4 (in-place)
  1065. I0412 04:12:22.629875 4704 net.cpp:122] Setting up relu4
  1066. I0412 04:12:22.629875 4704 net.cpp:129] Top shape: 10 384 13 13 (648960)
  1067. I0412 04:12:22.629875 4704 net.cpp:137] Memory required for data: 63788720
  1068. I0412 04:12:22.629875 4704 layer_factory.cpp:58] Creating layer conv5
  1069. I0412 04:12:22.629875 4704 net.cpp:84] Creating Layer conv5
  1070. I0412 04:12:22.629875 4704 net.cpp:406] conv5 <- conv4
  1071. I0412 04:12:22.629875 4704 net.cpp:380] conv5 -> conv5
  1072. I0412 04:12:22.629875 4704 net.cpp:122] Setting up conv5
  1073. I0412 04:12:22.629875 4704 net.cpp:129] Top shape: 10 256 13 13 (432640)
  1074. I0412 04:12:22.629875 4704 net.cpp:137] Memory required for data: 65519280
  1075. I0412 04:12:22.629875 4704 layer_factory.cpp:58] Creating layer relu5
  1076. I0412 04:12:22.629875 4704 net.cpp:84] Creating Layer relu5
  1077. I0412 04:12:22.629875 4704 net.cpp:406] relu5 <- conv5
  1078. I0412 04:12:22.629875 4704 net.cpp:367] relu5 -> conv5 (in-place)
  1079. I0412 04:12:22.629875 4704 net.cpp:122] Setting up relu5
  1080. I0412 04:12:22.629875 4704 net.cpp:129] Top shape: 10 256 13 13 (432640)
  1081. I0412 04:12:22.629875 4704 net.cpp:137] Memory required for data: 67249840
  1082. I0412 04:12:22.629875 4704 layer_factory.cpp:58] Creating layer pool5
  1083. I0412 04:12:22.629875 4704 net.cpp:84] Creating Layer pool5
  1084. I0412 04:12:22.629875 4704 net.cpp:406] pool5 <- conv5
  1085. I0412 04:12:22.629875 4704 net.cpp:380] pool5 -> pool5
  1086. I0412 04:12:22.629875 4704 net.cpp:122] Setting up pool5
  1087. I0412 04:12:22.629875 4704 net.cpp:129] Top shape: 10 256 6 6 (92160)
  1088. I0412 04:12:22.629875 4704 net.cpp:137] Memory required for data: 67618480
  1089. I0412 04:12:22.629875 4704 layer_factory.cpp:58] Creating layer pool5_flatten
  1090. I0412 04:12:22.629875 4704 net.cpp:84] Creating Layer pool5_flatten
  1091. I0412 04:12:22.629875 4704 net.cpp:406] pool5_flatten <- pool5
  1092. I0412 04:12:22.629875 4704 net.cpp:380] pool5_flatten -> pool5_flatten
  1093. I0412 04:12:22.629875 4704 net.cpp:122] Setting up pool5_flatten
  1094. I0412 04:12:22.629875 4704 net.cpp:129] Top shape: 10 9216 (92160)
  1095. I0412 04:12:22.629875 4704 net.cpp:137] Memory required for data: 67987120
  1096. I0412 04:12:22.629875 4704 layer_factory.cpp:58] Creating layer fc6
  1097. I0412 04:12:22.629875 4704 net.cpp:84] Creating Layer fc6
  1098. I0412 04:12:22.629875 4704 net.cpp:406] fc6 <- pool5_flatten
  1099. I0412 04:12:22.629875 4704 net.cpp:380] fc6 -> fc6
  1100. I0412 04:12:22.677767 4704 net.cpp:122] Setting up fc6
  1101. I0412 04:12:22.677767 4704 net.cpp:129] Top shape: 10 4096 (40960)
  1102. I0412 04:12:22.677767 4704 net.cpp:137] Memory required for data: 68150960
  1103. I0412 04:12:22.677767 4704 layer_factory.cpp:58] Creating layer relu6
  1104. I0412 04:12:22.677767 4704 net.cpp:84] Creating Layer relu6
  1105. I0412 04:12:22.677767 4704 net.cpp:406] relu6 <- fc6
  1106. I0412 04:12:22.677767 4704 net.cpp:367] relu6 -> fc6 (in-place)
  1107. I0412 04:12:22.677767 4704 net.cpp:122] Setting up relu6
  1108. I0412 04:12:22.677767 4704 net.cpp:129] Top shape: 10 4096 (40960)
  1109. I0412 04:12:22.677767 4704 net.cpp:137] Memory required for data: 68314800
  1110. I0412 04:12:22.677767 4704 layer_factory.cpp:58] Creating layer drop6
  1111. I0412 04:12:22.677767 4704 net.cpp:84] Creating Layer drop6
  1112. I0412 04:12:22.677767 4704 net.cpp:406] drop6 <- fc6
  1113. I0412 04:12:22.677767 4704 net.cpp:367] drop6 -> fc6 (in-place)
  1114. I0412 04:12:22.677767 4704 net.cpp:122] Setting up drop6
  1115. I0412 04:12:22.677767 4704 net.cpp:129] Top shape: 10 4096 (40960)
  1116. I0412 04:12:22.677767 4704 net.cpp:137] Memory required for data: 68478640
  1117. I0412 04:12:22.677767 4704 layer_factory.cpp:58] Creating layer fc7
  1118. I0412 04:12:22.677767 4704 net.cpp:84] Creating Layer fc7
  1119. I0412 04:12:22.677767 4704 net.cpp:406] fc7 <- fc6
  1120. I0412 04:12:22.677767 4704 net.cpp:380] fc7 -> fc7
  1121. I0412 04:12:22.692293 4704 net.cpp:122] Setting up fc7
  1122. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: 10 4096 (40960)
  1123. I0412 04:12:22.692293 4704 net.cpp:137] Memory required for data: 68642480
  1124. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer relu7
  1125. I0412 04:12:22.692293 4704 net.cpp:84] Creating Layer relu7
  1126. I0412 04:12:22.692293 4704 net.cpp:406] relu7 <- fc7
  1127. I0412 04:12:22.692293 4704 net.cpp:367] relu7 -> fc7 (in-place)
  1128. I0412 04:12:22.692293 4704 net.cpp:122] Setting up relu7
  1129. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: 10 4096 (40960)
  1130. I0412 04:12:22.692293 4704 net.cpp:137] Memory required for data: 68806320
  1131. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer drop7
  1132. I0412 04:12:22.692293 4704 net.cpp:84] Creating Layer drop7
  1133. I0412 04:12:22.692293 4704 net.cpp:406] drop7 <- fc7
  1134. I0412 04:12:22.692293 4704 net.cpp:367] drop7 -> fc7 (in-place)
  1135. I0412 04:12:22.692293 4704 net.cpp:122] Setting up drop7
  1136. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: 10 4096 (40960)
  1137. I0412 04:12:22.692293 4704 net.cpp:137] Memory required for data: 68970160
  1138. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer fc8_mitindoor67
  1139. I0412 04:12:22.692293 4704 net.cpp:84] Creating Layer fc8_mitindoor67
  1140. I0412 04:12:22.692293 4704 net.cpp:406] fc8_mitindoor67 <- fc7
  1141. I0412 04:12:22.692293 4704 net.cpp:380] fc8_mitindoor67 -> fc8_mitindoor67
  1142. I0412 04:12:22.692293 4704 net.cpp:122] Setting up fc8_mitindoor67
  1143. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: 10 67 (670)
  1144. I0412 04:12:22.692293 4704 net.cpp:137] Memory required for data: 68972840
  1145. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer
  1146. fc8_mitindoor67_fc8_mitindoor67_0_split
  1147. I0412 04:12:22.692293 4704 net.cpp:84] Creating Layer fc8_mitindoor67_fc8_mitindoor67_0_split
  1148. I0412 04:12:22.692293 4704 net.cpp:406] fc8_mitindoor67_fc8_mitindoor67_0_split <-
  1149. fc8_mitindoor67
  1150. I0412 04:12:22.692293 4704 net.cpp:380] fc8_mitindoor67_fc8_mitindoor67_0_split ->
  1151. fc8_mitindoor67_fc8_mitindoor67_0_split_0
  1152. I0412 04:12:22.692293 4704 net.cpp:380] fc8_mitindoor67_fc8_mitindoor67_0_split ->
  1153. fc8_mitindoor67_fc8_mitindoor67_0_split_1
  1154. I0412 04:12:22.692293 4704 net.cpp:122] Setting up fc8_mitindoor67_fc8_mitindoor67_0_split
  1155. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: 10 67 (670)
  1156. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: 10 67 (670)
  1157. I0412 04:12:22.692293 4704 net.cpp:137] Memory required for data: 68978200
  1158. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer loss
  1159. I0412 04:12:22.692293 4704 net.cpp:84] Creating Layer loss
  1160. I0412 04:12:22.692293 4704 net.cpp:406] loss <- fc8_mitindoor67_fc8_mitindoor67_0_split_0
  1161. I0412 04:12:22.692293 4704 net.cpp:406] loss <- label_MITindoor67_1_split_0
  1162. I0412 04:12:22.692293 4704 net.cpp:380] loss -> loss
  1163. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer loss
  1164. I0412 04:12:22.692293 4704 net.cpp:122] Setting up loss
  1165. I0412 04:12:22.692293 4704 net.cpp:129] Top shape: (1)
  1166. I0412 04:12:22.692293 4704 net.cpp:132] with loss weight 1
  1167. I0412 04:12:22.692293 4704 net.cpp:137] Memory required for data: 68978204
  1168. I0412 04:12:22.692293 4704 layer_factory.cpp:58] Creating layer accuracy
  1169. I0412 04:12:22.692293 4704 net.cpp:84] Creating Layer accuracy
  1170. I0412 04:12:22.692293 4704 net.cpp:406] accuracy <- fc8_mitindoor67_fc8_mitindoor67_0_split_1
  1171. I0412 04:12:22.692293 4704 net.cpp:406] accuracy <- label_MITindoor67_1_split_1
  1172. I0412 04:12:22.692293 4704 net.cpp:380] accuracy -> accuracy
  1173. I0412 04:12:22.692293 4704 net.cpp:122] Setting up accuracy
  1174. I0412 04:12:22.707957 4704 net.cpp:129] Top shape: (1)
  1175. I0412 04:12:22.707957 4704 net.cpp:137] Memory required for data: 68978208
  1176. I0412 04:12:22.707957 4704 net.cpp:200] accuracy does not need backward computation.
  1177. I0412 04:12:22.707957 4704 net.cpp:198] loss needs backward computation.
  1178. I0412 04:12:22.707957 4704 net.cpp:198] fc8_mitindoor67_fc8_mitindoor67_0_split needs backward
  1179. computation.
  1180. I0412 04:12:22.707957 4704 net.cpp:198] fc8_mitindoor67 needs backward computation.
  1181. I0412 04:12:22.707957 4704 net.cpp:200] drop7 does not need backward computation.
  1182. I0412 04:12:22.707957 4704 net.cpp:200] relu7 does not need backward computation.
  1183. I0412 04:12:22.707957 4704 net.cpp:200] fc7 does not need backward computation.
  1184. I0412 04:12:22.707957 4704 net.cpp:200] drop6 does not need backward computation.
  1185. I0412 04:12:22.707957 4704 net.cpp:200] relu6 does not need backward computation.
  1186. I0412 04:12:22.707957 4704 net.cpp:200] fc6 does not need backward computation.
  1187. I0412 04:12:22.707957 4704 net.cpp:200] pool5_flatten does not need backward computation.
  1188. I0412 04:12:22.707957 4704 net.cpp:200] pool5 does not need backward computation.
  1189. I0412 04:12:22.707957 4704 net.cpp:200] relu5 d
  1190. oes not need backward computation.
  1191. I0412 04:12:22.707957 4704 net.cpp:200] conv5 does not need backward computation.
  1192. I0412 04:12:22.707957 4704 net.cpp:200] relu4 does not need backward computation.
  1193. I0412 04:12:22.707957 4704 net.cpp:200] conv4 does not need backward computation.
  1194. I0412 04:12:22.707957 4704 net.cpp:200] relu3 does not need backward computation.
  1195. I0412 04:12:22.707957 4704 net.cpp:200] conv3 does not need backward computation.
  1196. I0412 04:12:22.707957 4704 net.cpp:200] norm2 does not need backward computation.
  1197. I0412 04:12:22.707957 4704 net.cpp:200] pool2 does not need backward computation.
  1198. I0412 04:12:22.707957 4704 net.cpp:200] relu2 does not need backward computation.
  1199. I0412 04:12:22.707957 4704 net.cpp:200] conv2 does not need backward computation.
  1200. I0412 04:12:22.707957 4704 net.cpp:200] norm1 does not need backward computation.
  1201. I0412 04:12:22.707957 4704 net.cpp:200] pool1 does not need backward computation.
  1202. I0412 04:12:22.707957 4704 net.cpp:200] relu1 does not need backward computation.
  1203. I0412 04:12:22.707957 4704 net.cpp:200] conv1 does not need backward computation.
  1204. I0412 04:12:22.707957 4704 net.cpp:200] label_MITindoor67_1_split does not need backward
  1205. computation.
  1206. I0412 04:12:22.707957 4704 net.cpp:200] MITindoor67 does not need backward computation.
  1207. I0412 04:12:22.707957 4704 net.cpp:242] This network produces output accuracy
  1208. I0412 04:12:22.707957 4704 net.cpp:242] This network produces output loss
  1209. I0412 04:12:22.707957 4704 net.cpp:255] Network initialization done.
  1210. I0412 04:12:22.707957 4704 solver.cpp:56] Solver scaffolding done.
  1211. I0412 04:12:22.707957 4704 caffe.cpp:155] Finetuning from
  1212. C:/Users/mahtab/Desktop/finetune_mitindoor67/places205CNN_iter_300000_upgraded.caffemodel
  1213. I0412 04:12:22.895382 4704 upgrade_proto.cpp:53] Attempting to upgrade input file specified
  1214. using deprecated V1LayerParameter:
  1215. C:/Users/mahtab/Desktop/finetune_mitindoor67/places205CNN_iter_300000_upgraded.caffemodel
  1216. I0412 04:12:23.145401 4704 upgrade_proto.cpp:61] Successfully upgraded file specified using
  1217. deprecated V1LayerParameter
  1218. I0412 04:12:23.161070 4704 net.cpp:744] Ignoring source layer data
  1219. I0412 04:12:23.192430 4704 net.cpp:744] Ignoring source layer fc8
  1220. I0412 04:12:23.427315 4704 upgrade_proto.cpp:53] Attempting to upgrade input file specified
  1221. using deprecated V1LayerParameter:
  1222. C:/Users/mahtab/Desktop/finetune_mitindoor67/places205CNN_iter_300000_upgraded.caffemodel
  1223. I0412 04:12:23.630440 4704 upgrade_proto.cpp:61] Successfully upgraded file specified using
  1224. deprecated V1LayerParameter
  1225. I0412 04:12:23.646035 4704 net.cpp:744] Ignoring source layer data
  1226. I0412 04:12:23.677067 4704 net.cpp:744] Ignoring source layer fc8
  1227. I0412 04:12:23.708406 4704 caffe.cpp:249] Starting Optimization
  1228. I0412 04:12:23.708406 4704 solver.cpp:272] Solving SceneRecognitionCaffeNet
  1229. I0412 04:12:23.708406 4704 solver.cpp:273] Learning Rate Policy: step
  1230. I0412 04:12:23.770778 4704 solver.cpp:330] Iteration 0, Testing net (#0)
  1231. I0412 04:13:47.208680 4232 data_layer.cpp:73] Restarting data prefetching from start.
  1232. I0412 04:13:49.770946 4704 solver.cpp:397] Test net output #0: accuracy = 0
  1233. I0412 04:13:49.770946 4704 solver.cpp:397] Test net output #1: loss = 4.20469 (* 1 = 4.20469
  1234. loss)
  1235. I0412 04:13:51.082967 4704 solver.cpp:218] Iteration 0 (0 iter/s, 87.374s/50 iters), loss =4.20469
  1236. I0412 04:13:51.082967 4704 solver.cpp:237] Train net output #0: loss = 4.20469 (* 1 =4.20469 loss)
  1237. I0412 04:13:51.082967 4704 sgd_solver.cpp:105] Iteration 0, lr = 1e-07
  1238. I0412 04:14:58.489819 4704 solver.cpp:218] Iteration 50 (0.741774 iter/s, 67.406s/50 iters),loss = 4.04563
  1239. I0412 04:14:58.489819 4704 solver.cpp:237] Train net output #0: loss = 4.04563 (* 1 =4.04563 loss)
  1240. I0412 04:14:58.489819 4704 sgd_solver.cpp:105] Iteration 50, lr = 1e-07
  1241. I0412 04:16:05.783648 4704 solver.cpp:218] Iteration 100 (0.743019 iter/s, 67.293s/50 iters),loss = 3.89188
  1242. I0412 04:16:05.783648 4704 solver.cpp:237] Train net output #0: loss = 3.89188 (* 1 =3.89188 loss)
  1243. I0412 04:16:05.783648 4704 sgd_solver.cpp:105] Iteration 100, lr = 1e-07
  1244. I0412 04:17:13.099241 4704 solver.cpp:218] Iteration 150 (0.742776 iter/s, 67.315s/50 iters),loss = 3.69574
  1245. I0412 04:17:13.099241 4704 solver.cpp:237] Train net output #0: loss = 3.69574 (* 1 =3.69574 loss)
  1246. I0412 04:17:13.099241 4704 sgd_solver.cpp:105] Iteration 150, lr = 1e-07
  1247. I0412 04:18:20.946854 4704 solver.cpp:218] Iteration 200 (0.736952 iter/s, 67.847s/50 iters),loss = 3.53715
  1248. I0412 04:18:20.946854 4704 solver.cpp:237] Train net output #0: loss = 3.53715 (* 1 =3.53715 loss)
  1249. I0412 04:18:20.946854 4704 sgd_solver.cpp:105] Iteration 200, lr = 1e-07
  1250. I0412 04:19:28.125959 4704 solver.cpp:218] Iteration 250 (0.74428 iter/s, 67.179s/50 iters),loss = 3.3488
  1251. I0412 04:19:28.125959 4704 solver.cpp:237] Train net output #0: loss = 3.3488 (* 1 = 3.3488loss)
  1252. I0412 04:19:28.125959 4704 sgd_solver.cpp:105] Iteration 250, lr = 1e-07
  1253. I0412 04:19:51.017532 4704 solver.cpp:330] Iteration 268, Testing net (#0)
  1254. I0412 04:21:16.677172 4704 solver.cpp:397] Test net output #0: accuracy = 1
  1255. I0412 04:21:16.677172 4704 solver.cpp:397] Test net output #1: loss = 3.3788 (* 1 = 3.3788loss)
  1256. I0412 04:22:01.020563 4704 solver.cpp:218] Iteration 300 (0.327024 iter/s, 152.894s/50 iters),loss = 3.14588
  1257. I0412 04:22:01.020563 4704 solver.cpp:237] Train net output #0: loss = 3.14588 (* 1 =3.14588 loss)
  1258. I0412 04:22:01.020563 4704 sgd_solver.cpp:105] Iteration 300, lr = 1e-07
  1259. I0412 04:23:08.178277 4704 solver.cpp:218] Iteration 350 (0.744524 iter/s, 67.157s/50 iters),loss = 3.00576
  1260. I0412 04:23:08.178277 4704 solver.cpp:237] Train net output #0: loss = 3.00576 (* 1 =3.00576 loss)
  1261. I0412 04:23:08.178277 4704 sgd_solver.cpp:105] Iteration 350, lr = 1e-07
  1262. I0412 04:24:15.349581 4704 solver.cpp:218] Iteration 400 (0.744369 iter/s, 67.171s/50 iters),loss = 2.83526
  1263. I0412 04:24:15.349581 4704 solver.cpp:237] Train net output #0: loss = 2.83526 (* 1 =2.83526 loss)
  1264. I0412 04:24:15.349581 4704 sgd_solver.cpp:105] Iteration 400, lr = 1e-07
  1265. I0412 04:25:22.693616 4704 solver.cpp:218] Iteration 450 (0.742457 iter/s, 67.344s/50 iters),loss = 2.59777
  1266. I0412 04:25:22.693616 4704 solver.cpp:237] Train net output #0: loss = 2.59777 (* 1 =2.59777 loss)
  1267. I0412 04:25:22.693616 4704 sgd_solver.cpp:105] Iteration 450, lr = 1e-07
  1268. I0412 04:26:29.989542 4704 solver.cpp:218] Iteration 500 (0.742997 iter/s, 67.295s/50 iters),loss = 2.58771
  1269. I0412 04:26:29.989542 4704 solver.cpp:237] Train net output #0: loss = 2.58771 (* 1 =2.58771 loss)
  1270. I0412 04:26:29.989542 4704 sgd_solver.cpp:105] Iteration 500, lr = 1e-07
  1271. I0412 04:27:17.091591 4704 solver.cpp:330] Iteration 536, Testing net (#0)
  1272. I0412 04:28:42.646239 4704 solver.cpp:397] Test net output #0: accuracy = 1
  1273. I0412 04:28:42.646239 4704 solver.cpp:397] Test net output #1: loss = 2.58355 (* 1 = 2.58355loss)
  1274. I0412 04:29:02.723795 4704 solver.cpp:218] Iteration 550 (0.327367 iter/s, 152.734s/50 iters),loss = 2.41916
  1275. I0412 04:29:02.723795 4704 solver.cpp:237] Train net output #0: loss = 2.41916 (* 1 =2.41916 loss)
  1276. I0412 04:29:02.723795 4704 sgd_solver.cpp:105] Iteration 550, lr = 1e-07
  1277. I0412 04:30:10.005543 4704 solver.cpp:218] Iteration 600 (0.743152 iter/s, 67.281s/50 iters),loss = 2.17474
  1278. I0412 04:30:10.005543 4704 solver.cpp:237] Train net output #0: loss = 2.17474 (* 1 =2.17474 loss)
  1279. I0412 04:30:10.005543 4704 sgd_solver.cpp:105] Iteration 600, lr = 1e-07
  1280. I0412 04:31:17.192559 4704 solver.cpp:218] Iteration 650 (0.744192 iter/s, 67.187s/50 iters),loss = 2.06964
  1281. I0412 04:31:17.192559 4704 solver.cpp:237] Train net output #0: loss = 2.06964 (* 1 =2.06964 loss)
  1282. I0412 04:31:17.192559 4704 sgd_solver.cpp:105] Iteration 650, lr = 1e-07
  1283. I0412 04:32:24.360908 4704 solver.cpp:218] Iteration 700 (0.744402 iter/s, 67.168s/50 iters),loss = 1.89071
  1284. I0412 04:32:24.360908 4704 solver.cpp:237] Train net output #0: loss = 1.89071 (* 1 =1.89071 loss)
  1285. I0412 04:32:24.360908 4704 sgd_solver.cpp:105] Iteration 700, lr = 1e-07
  1286. I0412 04:33:31.505738 4704 solver.cpp:218] Iteration 750 (0.744668 iter/s, 67.144s/50 iters),loss = 1.87087
  1287. I0412 04:33:31.505738 4704 solver.cpp:237] Train net output #0: loss = 1.87087 (* 1 =1.87087 loss)
  1288. I0412 04:33:31.505738 4704 sgd_solver.cpp:105] Iteration 750, lr = 1e-07
  1289. I0412 04:34:38.818370 4704 solver.cpp:218] Iteration 800 (0.74281 iter/s, 67.312s/50 iters),loss = 1.69662
  1290. I0412 04:34:38.818370 4704 solver.cpp:237] Train net output #0: loss = 1.69662 (* 1 =1.69662 loss)
  1291. I0412 04:34:38.818370 4704 sgd_solver.cpp:105] Iteration 800, lr = 1e-07
  1292. I0412 04:34:42.958595 4704 solver.cpp:330] Iteration 804, Testing net (#0)
  1293. I0412 04:36:08.349354 4704 solver.cpp:397] Test net output #0: accuracy = 1
  1294. I0412 04:36:08.365051 4704 solver.cpp:397] Test net output #1: loss = 1.90856 (* 1 = 1.90856loss)
  1295. I0412 04:37:11.380419 4704 solver.cpp:218] Iteration 850 (0.327736 iter/s, 152.562s/50 iters),loss = 1.68572
  1296. I0412 04:37:11.380419 4704 solver.cpp:237] Train net output #0: loss = 1.68572 (* 1 =1.68572 loss)
  1297. I0412 04:37:11.380419 4704 sgd_solver.cpp:105] Iteration 850, lr = 1e-07
  1298. I0412 04:38:18.349567 4704 solver.cpp:218] Iteration 900 (0.746614 iter/s, 66.969s/50 iters),loss = 1.5322
  1299. I0412 04:38:18.349567 4704 solver.cpp:237] Train net output #0: loss = 1.5322 (* 1 = 1.5322loss)
  1300. I0412 04:38:18.349567 4704 sgd_solver.cpp:105] Iteration 900, lr = 1e-07
  1301. I0412 04:39:25.224520 4704 solver.cpp:218] Iteration 950 (0.747675 iter/s, 66.874s/50 iters),loss = 1.35434
  1302. I0412 04:39:25.224520 4704 solver.cpp:237] Train net output #0: loss = 1.35434 (* 1 =1.35434 loss)
  1303. I0412 04:39:25.224520 4704 sgd_solver.cpp:105] Iteration 950, lr = 1e-07
  1304. I0412 04:40:32.130380 4704 solver.cpp:218] Iteration 1000 (0.747328 iter/s, 66.905s/50 iters),loss = 1.30102
  1305. I0412 04:40:32.130380 4704 solver.cpp:237] Train net output #0: loss = 1.30102 (* 1 =1.30102 loss)
  1306. I0412 04:40:32.130380 4704 sgd_solver.cpp:105] Iteration 1000, lr = 1e-07
  1307. I0412 04:41:40.880671 4704 solver.cpp:218] Iteration 1050 (0.727273 iter/s, 68.75s/50 iters),loss = 1.24691
  1308. I0412 04:41:40.880671 4704 solver.cpp:237] Train net output #0: loss = 1.24691 (* 1 =1.24691 loss)
  1309. I0412 04:41:40.880671 4704 sgd_solver.cpp:105] Iteration 1050, lr = 1e-07
  1310. I0412 04:42:09.927634 4704 solver.cpp:330] Iteration 1072, Testing net (#0)
  1311. I0412 04:43:38.349730 4704 solver.cpp:397] Test net output #0: accuracy = 1
  1312. I0412 04:43:38.349730 4704 solver.cpp:397] Test net output #1: loss = 1.40134 (* 1 = 1.40134loss)
  1313. I0412 04:44:18.818953 4704 solver.cpp:218] Iteration 1100 (0.31658 iter/s, 157.938s/50 iters),loss = 1.18656
  1314. I0412 04:44:18.818953 4704 solver.cpp:237] Train net output #0: loss = 1.18656 (* 1 =1.18656 loss)
  1315. I0412 04:44:18.818953 4704 sgd_solver.cpp:105] Iteration 1100, lr = 1e-07
  1316. I0412 04:45:29.631006 4704 solver.cpp:218] Iteration 1150 (0.706095 iter/s, 70.812s/50 iters),loss = 1.06573
  1317. I0412 04:45:29.631006 4704 solver.cpp:237] Train net output #0: loss = 1.06573 (* 1 =1.06573 loss)
  1318. I0412 04:45:29.631006 4704 sgd_solver.cpp:105] Iteration 1150, lr = 1e-07
  1319. I0412 04:46:36.709095 4704 solver.cpp:218] Iteration 1200 (0.745401 iter/s, 67.078s/50 iters),loss = 1.0079
  1320. I0412 04:46:36.709095 4704 solver.cpp:237] Train net output #0: loss = 1.0079 (* 1 = 1.0079loss)
  1321. I0412 04:46:36.709095 4704 sgd_solver.cpp:105] Iteration 1200, lr = 1e-07
  1322. I0412 04:47:43.599740 4704 solver.cpp:218] Iteration 1250 (0.747496 iter/s, 66.89s/50 iters),loss = 0.896948
  1323. I0412 04:47:43.599740 4704 solver.cpp:237] Train net output #0: loss = 0.896948 (* 1 =0.896948 loss)
  1324. I0412 04:47:43.599740 4704 sgd_solver.cpp:105] Iteration 1250, lr = 1e-07
  1325. I0412 04:48:50.458986 4704 solver.cpp:218] Iteration 1300 (0.747842 iter/s, 66.859s/50 iters),loss = 0.760583
  1326. I0412 04:48:50.458986 4704 solver.cpp:237] Train net output #0: loss = 0.760583 (* 1 =0.760583 loss)
  1327. I0412 04:48:50.458986 4704 sgd_solver.cpp:105] Iteration 1300, lr = 1e-07
  1328. I0412 04:49:42.693409 4704 solver.cpp:330] Iteration 1340, Testing net (#0)
  1329. I0412 04:51:07.927647 4704 solver.cpp:397] Test net output #0: accuracy = 1
  1330. I0412 04:51:07.927647 4704 solver.cpp:397] Test net output #1: loss = 1.05483 (* 1 = 1.05483loss)
  1331. I0412 04:51:22.568167 4704 solver.cpp:218] Iteration 1350 (0.328746 iter/s, 152.093s/50 iters),loss = 0.775195
  1332. I0412 04:51:22.568167 4704 solver.cpp:237] Train net output #0: loss = 0.775195 (* 1 =0.775195 loss)
  1333. I0412 04:51:22.568167 4704 sgd_solver.cpp:105] Iteration 1350, lr = 1e-07
  1334. I0412 04:52:29.552525 4704 solver.cpp:218] Iteration 1400 (0.746447 iter/s, 66.984s/50 iters),loss = 0.718551
  1335. I0412 04:52:29.552525 4704 solver.cpp:237] Train net output #0: loss = 0.718551 (* 1 =0.718551 loss)
  1336. I0412 04:52:29.552525 4704 sgd_solver.cpp:105] Iteration 1400, lr = 1e-07
  1337. I0412 04:53:37.411788 4704 solver.cpp:218] Iteration 1450 (0.736822 iter/s, 67.859s/50 iters),loss = 0.691536
  1338. I0412 04:53:37.411788 4704 solver.cpp:237] Train net output #0: loss = 0.691536 (* 1 =0.691536 loss)
  1339. I0412 04:53:37.411788 4704 sgd_solver.cpp:105] Iteration 1450, lr = 1e-07
  1340. I0412 04:54:44.599256 4704 solver.cpp:218] Iteration 1500 (0.744192 iter/s, 67.187s/50 iters),loss = 0.834102
  1341. I0412 04:54:44.599256 4704 solver.cpp:237] Train net output #0: loss = 0.834102 (* 1 =0.834102 loss)
  1342. I0412 04:54:44.599256 4704 sgd_solver.cpp:105] Iteration 1500, lr = 1e-07
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!