API tools faq
paste
Guest User

TF Dump Training with one device

a guest
Nov 1st, 2019
145
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 42.02 KB | None | 0 0
raw download clone embed print report
  1. Output with '/gpu:0'
  2. ds_valid.shuffle(len(list_paths_train), seed=42,
  3. reshuffle_each_iteration=True)
  4.  
  5. 2019-11-01 09:53:21.406893: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
  6. 2019-11-01 09:53:21.450823: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1546] Found device 0 with properties:
  7. pciBusID: 0000:86:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
  8. coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s
  9. 2019-11-01 09:53:21.451467: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1546] Found device 1 with properties:
  10. pciBusID: 0000:af:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
  11. coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s
  12. 2019-11-01 09:53:21.451755: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
  13. 2019-11-01 09:53:21.453373: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
  14. 2019-11-01 09:53:21.454649: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
  15. 2019-11-01 09:53:21.455396: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
  16. 2019-11-01 09:53:21.456894: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
  17. 2019-11-01 09:53:21.458026: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
  18. 2019-11-01 09:53:21.461598: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
  19. 2019-11-01 09:53:21.463936: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1688] Adding visible gpu devices: 0, 1
  20. 2019-11-01 09:53:21.464311: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
  21. 2019-11-01 09:53:21.498095: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2100000000 Hz
  22. 2019-11-01 09:53:21.508899: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4995c00 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
  23. 2019-11-01 09:53:21.508954: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
  24. 2019-11-01 09:53:21.772746: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4986d40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
  25. 2019-11-01 09:53:21.772787: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): GeForce RTX 2080 Ti, Compute Capability 7.5
  26. 2019-11-01 09:53:21.772797: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (1): GeForce RTX 2080 Ti, Compute Capability 7.5
  27. 2019-11-01 09:53:21.774090: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1546] Found device 0 with properties:
  28. pciBusID: 0000:86:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
  29. coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s
  30. 2019-11-01 09:53:21.774964: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1546] Found device 1 with properties:
  31. pciBusID: 0000:af:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
  32. coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s
  33. 2019-11-01 09:53:21.775025: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
  34. 2019-11-01 09:53:21.775048: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
  35. 2019-11-01 09:53:21.775067: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
  36. 2019-11-01 09:53:21.775087: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
  37. 2019-11-01 09:53:21.775107: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
  38. 2019-11-01 09:53:21.775126: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
  39. 2019-11-01 09:53:21.775147: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
  40. 2019-11-01 09:53:21.778445: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1688] Adding visible gpu devices: 0, 1
  41. 2019-11-01 09:53:21.778500: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
  42. 2019-11-01 09:53:21.781150: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1087] Device interconnect StreamExecutor with strength 1 edge matrix:
  43. 2019-11-01 09:53:21.781172: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1093] 0 1
  44. 2019-11-01 09:53:21.781184: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1106] 0: N N
  45. 2019-11-01 09:53:21.781195: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1106] 1: N N
  46. 2019-11-01 09:53:21.783844: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1232] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10312 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2080 Ti, pci bus id: 0000:86:00.0, compute capability: 7.5)
  47. 2019-11-01 09:53:21.785587: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1232] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 10312 MB memory) -> physical GPU (device: 1, name: GeForce RTX 2080 Ti, pci bus id: 0000:af:00.0, compute capability: 7.5)
  48. Model: "resnet50"
  49. __________________________________________________________________________________________________
  50. Layer (type) Output Shape Param # Connected to
  51. ==================================================================================================
  52. input_1 (InputLayer) [(None, 270, 270, 1) 0
  53. __________________________________________________________________________________________________
  54. conv1_pad (ZeroPadding2D) (None, 276, 276, 1) 0 input_1[0][0]
  55. __________________________________________________________________________________________________
  56. conv1_conv (Conv2D) (None, 135, 135, 64) 3200 conv1_pad[0][0]
  57. __________________________________________________________________________________________________
  58. conv1_bn (BatchNormalization) (None, 135, 135, 64) 256 conv1_conv[0][0]
  59. __________________________________________________________________________________________________
  60. conv1_relu (Activation) (None, 135, 135, 64) 0 conv1_bn[0][0]
  61. __________________________________________________________________________________________________
  62. pool1_pad (ZeroPadding2D) (None, 137, 137, 64) 0 conv1_relu[0][0]
  63. __________________________________________________________________________________________________
  64. pool1_pool (MaxPooling2D) (None, 68, 68, 64) 0 pool1_pad[0][0]
  65. __________________________________________________________________________________________________
  66. conv2_block1_1_conv (Conv2D) (None, 68, 68, 64) 4160 pool1_pool[0][0]
  67. __________________________________________________________________________________________________
  68. conv2_block1_1_bn (BatchNormali (None, 68, 68, 64) 256 conv2_block1_1_conv[0][0]
  69. __________________________________________________________________________________________________
  70. conv2_block1_1_relu (Activation (None, 68, 68, 64) 0 conv2_block1_1_bn[0][0]
  71. __________________________________________________________________________________________________
  72. conv2_block1_2_conv (Conv2D) (None, 68, 68, 64) 36928 conv2_block1_1_relu[0][0]
  73. __________________________________________________________________________________________________
  74. conv2_block1_2_bn (BatchNormali (None, 68, 68, 64) 256 conv2_block1_2_conv[0][0]
  75. __________________________________________________________________________________________________
  76. conv2_block1_2_relu (Activation (None, 68, 68, 64) 0 conv2_block1_2_bn[0][0]
  77. __________________________________________________________________________________________________
  78. conv2_block1_0_conv (Conv2D) (None, 68, 68, 256) 16640 pool1_pool[0][0]
  79. __________________________________________________________________________________________________
  80. conv2_block1_3_conv (Conv2D) (None, 68, 68, 256) 16640 conv2_block1_2_relu[0][0]
  81. __________________________________________________________________________________________________
  82. conv2_block1_0_bn (BatchNormali (None, 68, 68, 256) 1024 conv2_block1_0_conv[0][0]
  83. __________________________________________________________________________________________________
  84. conv2_block1_3_bn (BatchNormali (None, 68, 68, 256) 1024 conv2_block1_3_conv[0][0]
  85. __________________________________________________________________________________________________
  86. conv2_block1_add (Add) (None, 68, 68, 256) 0 conv2_block1_0_bn[0][0]
  87. conv2_block1_3_bn[0][0]
  88. __________________________________________________________________________________________________
  89. conv2_block1_out (Activation) (None, 68, 68, 256) 0 conv2_block1_add[0][0]
  90. __________________________________________________________________________________________________
  91. conv2_block2_1_conv (Conv2D) (None, 68, 68, 64) 16448 conv2_block1_out[0][0]
  92. __________________________________________________________________________________________________
  93. conv2_block2_1_bn (BatchNormali (None, 68, 68, 64) 256 conv2_block2_1_conv[0][0]
  94. __________________________________________________________________________________________________
  95. conv2_block2_1_relu (Activation (None, 68, 68, 64) 0 conv2_block2_1_bn[0][0]
  96. __________________________________________________________________________________________________
  97. conv2_block2_2_conv (Conv2D) (None, 68, 68, 64) 36928 conv2_block2_1_relu[0][0]
  98. __________________________________________________________________________________________________
  99. conv2_block2_2_bn (BatchNormali (None, 68, 68, 64) 256 conv2_block2_2_conv[0][0]
  100. __________________________________________________________________________________________________
  101. conv2_block2_2_relu (Activation (None, 68, 68, 64) 0 conv2_block2_2_bn[0][0]
  102. __________________________________________________________________________________________________
  103. conv2_block2_3_conv (Conv2D) (None, 68, 68, 256) 16640 conv2_block2_2_relu[0][0]
  104. __________________________________________________________________________________________________
  105. conv2_block2_3_bn (BatchNormali (None, 68, 68, 256) 1024 conv2_block2_3_conv[0][0]
  106. __________________________________________________________________________________________________
  107. conv2_block2_add (Add) (None, 68, 68, 256) 0 conv2_block1_out[0][0]
  108. conv2_block2_3_bn[0][0]
  109. __________________________________________________________________________________________________
  110. conv2_block2_out (Activation) (None, 68, 68, 256) 0 conv2_block2_add[0][0]
  111. __________________________________________________________________________________________________
  112. conv2_block3_1_conv (Conv2D) (None, 68, 68, 64) 16448 conv2_block2_out[0][0]
  113. __________________________________________________________________________________________________
  114. conv2_block3_1_bn (BatchNormali (None, 68, 68, 64) 256 conv2_block3_1_conv[0][0]
  115. __________________________________________________________________________________________________
  116. conv2_block3_1_relu (Activation (None, 68, 68, 64) 0 conv2_block3_1_bn[0][0]
  117. __________________________________________________________________________________________________
  118. conv2_block3_2_conv (Conv2D) (None, 68, 68, 64) 36928 conv2_block3_1_relu[0][0]
  119. __________________________________________________________________________________________________
  120. conv2_block3_2_bn (BatchNormali (None, 68, 68, 64) 256 conv2_block3_2_conv[0][0]
  121. __________________________________________________________________________________________________
  122. conv2_block3_2_relu (Activation (None, 68, 68, 64) 0 conv2_block3_2_bn[0][0]
  123. __________________________________________________________________________________________________
  124. conv2_block3_3_conv (Conv2D) (None, 68, 68, 256) 16640 conv2_block3_2_relu[0][0]
  125. __________________________________________________________________________________________________
  126. conv2_block3_3_bn (BatchNormali (None, 68, 68, 256) 1024 conv2_block3_3_conv[0][0]
  127. __________________________________________________________________________________________________
  128. conv2_block3_add (Add) (None, 68, 68, 256) 0 conv2_block2_out[0][0]
  129. conv2_block3_3_bn[0][0]
  130. __________________________________________________________________________________________________
  131. conv2_block3_out (Activation) (None, 68, 68, 256) 0 conv2_block3_add[0][0]
  132. __________________________________________________________________________________________________
  133. conv3_block1_1_conv (Conv2D) (None, 34, 34, 128) 32896 conv2_block3_out[0][0]
  134. __________________________________________________________________________________________________
  135. conv3_block1_1_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block1_1_conv[0][0]
  136. __________________________________________________________________________________________________
  137. conv3_block1_1_relu (Activation (None, 34, 34, 128) 0 conv3_block1_1_bn[0][0]
  138. __________________________________________________________________________________________________
  139. conv3_block1_2_conv (Conv2D) (None, 34, 34, 128) 147584 conv3_block1_1_relu[0][0]
  140. __________________________________________________________________________________________________
  141. conv3_block1_2_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block1_2_conv[0][0]
  142. __________________________________________________________________________________________________
  143. conv3_block1_2_relu (Activation (None, 34, 34, 128) 0 conv3_block1_2_bn[0][0]
  144. __________________________________________________________________________________________________
  145. conv3_block1_0_conv (Conv2D) (None, 34, 34, 512) 131584 conv2_block3_out[0][0]
  146. __________________________________________________________________________________________________
  147. conv3_block1_3_conv (Conv2D) (None, 34, 34, 512) 66048 conv3_block1_2_relu[0][0]
  148. __________________________________________________________________________________________________
  149. conv3_block1_0_bn (BatchNormali (None, 34, 34, 512) 2048 conv3_block1_0_conv[0][0]
  150. __________________________________________________________________________________________________
  151. conv3_block1_3_bn (BatchNormali (None, 34, 34, 512) 2048 conv3_block1_3_conv[0][0]
  152. __________________________________________________________________________________________________
  153. conv3_block1_add (Add) (None, 34, 34, 512) 0 conv3_block1_0_bn[0][0]
  154. conv3_block1_3_bn[0][0]
  155. __________________________________________________________________________________________________
  156. conv3_block1_out (Activation) (None, 34, 34, 512) 0 conv3_block1_add[0][0]
  157. __________________________________________________________________________________________________
  158. conv3_block2_1_conv (Conv2D) (None, 34, 34, 128) 65664 conv3_block1_out[0][0]
  159. __________________________________________________________________________________________________
  160. conv3_block2_1_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block2_1_conv[0][0]
  161. __________________________________________________________________________________________________
  162. conv3_block2_1_relu (Activation (None, 34, 34, 128) 0 conv3_block2_1_bn[0][0]
  163. __________________________________________________________________________________________________
  164. conv3_block2_2_conv (Conv2D) (None, 34, 34, 128) 147584 conv3_block2_1_relu[0][0]
  165. __________________________________________________________________________________________________
  166. conv3_block2_2_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block2_2_conv[0][0]
  167. __________________________________________________________________________________________________
  168. conv3_block2_2_relu (Activation (None, 34, 34, 128) 0 conv3_block2_2_bn[0][0]
  169. __________________________________________________________________________________________________
  170. conv3_block2_3_conv (Conv2D) (None, 34, 34, 512) 66048 conv3_block2_2_relu[0][0]
  171. __________________________________________________________________________________________________
  172. conv3_block2_3_bn (BatchNormali (None, 34, 34, 512) 2048 conv3_block2_3_conv[0][0]
  173. __________________________________________________________________________________________________
  174. conv3_block2_add (Add) (None, 34, 34, 512) 0 conv3_block1_out[0][0]
  175. conv3_block2_3_bn[0][0]
  176. __________________________________________________________________________________________________
  177. conv3_block2_out (Activation) (None, 34, 34, 512) 0 conv3_block2_add[0][0]
  178. __________________________________________________________________________________________________
  179. conv3_block3_1_conv (Conv2D) (None, 34, 34, 128) 65664 conv3_block2_out[0][0]
  180. __________________________________________________________________________________________________
  181. conv3_block3_1_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block3_1_conv[0][0]
  182. __________________________________________________________________________________________________
  183. conv3_block3_1_relu (Activation (None, 34, 34, 128) 0 conv3_block3_1_bn[0][0]
  184. __________________________________________________________________________________________________
  185. conv3_block3_2_conv (Conv2D) (None, 34, 34, 128) 147584 conv3_block3_1_relu[0][0]
  186. __________________________________________________________________________________________________
  187. conv3_block3_2_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block3_2_conv[0][0]
  188. __________________________________________________________________________________________________
  189. conv3_block3_2_relu (Activation (None, 34, 34, 128) 0 conv3_block3_2_bn[0][0]
  190. __________________________________________________________________________________________________
  191. conv3_block3_3_conv (Conv2D) (None, 34, 34, 512) 66048 conv3_block3_2_relu[0][0]
  192. __________________________________________________________________________________________________
  193. conv3_block3_3_bn (BatchNormali (None, 34, 34, 512) 2048 conv3_block3_3_conv[0][0]
  194. __________________________________________________________________________________________________
  195. conv3_block3_add (Add) (None, 34, 34, 512) 0 conv3_block2_out[0][0]
  196. conv3_block3_3_bn[0][0]
  197. __________________________________________________________________________________________________
  198. conv3_block3_out (Activation) (None, 34, 34, 512) 0 conv3_block3_add[0][0]
  199. __________________________________________________________________________________________________
  200. conv3_block4_1_conv (Conv2D) (None, 34, 34, 128) 65664 conv3_block3_out[0][0]
  201. __________________________________________________________________________________________________
  202. conv3_block4_1_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block4_1_conv[0][0]
  203. __________________________________________________________________________________________________
  204. conv3_block4_1_relu (Activation (None, 34, 34, 128) 0 conv3_block4_1_bn[0][0]
  205. __________________________________________________________________________________________________
  206. conv3_block4_2_conv (Conv2D) (None, 34, 34, 128) 147584 conv3_block4_1_relu[0][0]
  207. __________________________________________________________________________________________________
  208. conv3_block4_2_bn (BatchNormali (None, 34, 34, 128) 512 conv3_block4_2_conv[0][0]
  209. __________________________________________________________________________________________________
  210. conv3_block4_2_relu (Activation (None, 34, 34, 128) 0 conv3_block4_2_bn[0][0]
  211. __________________________________________________________________________________________________
  212. conv3_block4_3_conv (Conv2D) (None, 34, 34, 512) 66048 conv3_block4_2_relu[0][0]
  213. __________________________________________________________________________________________________
  214. conv3_block4_3_bn (BatchNormali (None, 34, 34, 512) 2048 conv3_block4_3_conv[0][0]
  215. __________________________________________________________________________________________________
  216. conv3_block4_add (Add) (None, 34, 34, 512) 0 conv3_block3_out[0][0]
  217. conv3_block4_3_bn[0][0]
  218. __________________________________________________________________________________________________
  219. conv3_block4_out (Activation) (None, 34, 34, 512) 0 conv3_block4_add[0][0]
  220. __________________________________________________________________________________________________
  221. conv4_block1_1_conv (Conv2D) (None, 17, 17, 256) 131328 conv3_block4_out[0][0]
  222. __________________________________________________________________________________________________
  223. conv4_block1_1_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block1_1_conv[0][0]
  224. __________________________________________________________________________________________________
  225. conv4_block1_1_relu (Activation (None, 17, 17, 256) 0 conv4_block1_1_bn[0][0]
  226. __________________________________________________________________________________________________
  227. conv4_block1_2_conv (Conv2D) (None, 17, 17, 256) 590080 conv4_block1_1_relu[0][0]
  228. __________________________________________________________________________________________________
  229. conv4_block1_2_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block1_2_conv[0][0]
  230. __________________________________________________________________________________________________
  231. conv4_block1_2_relu (Activation (None, 17, 17, 256) 0 conv4_block1_2_bn[0][0]
  232. __________________________________________________________________________________________________
  233. conv4_block1_0_conv (Conv2D) (None, 17, 17, 1024) 525312 conv3_block4_out[0][0]
  234. __________________________________________________________________________________________________
  235. conv4_block1_3_conv (Conv2D) (None, 17, 17, 1024) 263168 conv4_block1_2_relu[0][0]
  236. __________________________________________________________________________________________________
  237. conv4_block1_0_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block1_0_conv[0][0]
  238. __________________________________________________________________________________________________
  239. conv4_block1_3_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block1_3_conv[0][0]
  240. __________________________________________________________________________________________________
  241. conv4_block1_add (Add) (None, 17, 17, 1024) 0 conv4_block1_0_bn[0][0]
  242. conv4_block1_3_bn[0][0]
  243. __________________________________________________________________________________________________
  244. conv4_block1_out (Activation) (None, 17, 17, 1024) 0 conv4_block1_add[0][0]
  245. __________________________________________________________________________________________________
  246. conv4_block2_1_conv (Conv2D) (None, 17, 17, 256) 262400 conv4_block1_out[0][0]
  247. __________________________________________________________________________________________________
  248. conv4_block2_1_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block2_1_conv[0][0]
  249. __________________________________________________________________________________________________
  250. conv4_block2_1_relu (Activation (None, 17, 17, 256) 0 conv4_block2_1_bn[0][0]
  251. __________________________________________________________________________________________________
  252. conv4_block2_2_conv (Conv2D) (None, 17, 17, 256) 590080 conv4_block2_1_relu[0][0]
  253. __________________________________________________________________________________________________
  254. conv4_block2_2_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block2_2_conv[0][0]
  255. __________________________________________________________________________________________________
  256. conv4_block2_2_relu (Activation (None, 17, 17, 256) 0 conv4_block2_2_bn[0][0]
  257. __________________________________________________________________________________________________
  258. conv4_block2_3_conv (Conv2D) (None, 17, 17, 1024) 263168 conv4_block2_2_relu[0][0]
  259. __________________________________________________________________________________________________
  260. conv4_block2_3_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block2_3_conv[0][0]
  261. __________________________________________________________________________________________________
  262. conv4_block2_add (Add) (None, 17, 17, 1024) 0 conv4_block1_out[0][0]
  263. conv4_block2_3_bn[0][0]
  264. __________________________________________________________________________________________________
  265. conv4_block2_out (Activation) (None, 17, 17, 1024) 0 conv4_block2_add[0][0]
  266. __________________________________________________________________________________________________
  267. conv4_block3_1_conv (Conv2D) (None, 17, 17, 256) 262400 conv4_block2_out[0][0]
  268. __________________________________________________________________________________________________
  269. conv4_block3_1_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block3_1_conv[0][0]
  270. __________________________________________________________________________________________________
  271. conv4_block3_1_relu (Activation (None, 17, 17, 256) 0 conv4_block3_1_bn[0][0]
  272. __________________________________________________________________________________________________
  273. conv4_block3_2_conv (Conv2D) (None, 17, 17, 256) 590080 conv4_block3_1_relu[0][0]
  274. __________________________________________________________________________________________________
  275. conv4_block3_2_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block3_2_conv[0][0]
  276. __________________________________________________________________________________________________
  277. conv4_block3_2_relu (Activation (None, 17, 17, 256) 0 conv4_block3_2_bn[0][0]
  278. __________________________________________________________________________________________________
  279. conv4_block3_3_conv (Conv2D) (None, 17, 17, 1024) 263168 conv4_block3_2_relu[0][0]
  280. __________________________________________________________________________________________________
  281. conv4_block3_3_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block3_3_conv[0][0]
  282. __________________________________________________________________________________________________
  283. conv4_block3_add (Add) (None, 17, 17, 1024) 0 conv4_block2_out[0][0]
  284. conv4_block3_3_bn[0][0]
  285. __________________________________________________________________________________________________
  286. conv4_block3_out (Activation) (None, 17, 17, 1024) 0 conv4_block3_add[0][0]
  287. __________________________________________________________________________________________________
  288. conv4_block4_1_conv (Conv2D) (None, 17, 17, 256) 262400 conv4_block3_out[0][0]
  289. __________________________________________________________________________________________________
  290. conv4_block4_1_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block4_1_conv[0][0]
  291. __________________________________________________________________________________________________
  292. conv4_block4_1_relu (Activation (None, 17, 17, 256) 0 conv4_block4_1_bn[0][0]
  293. __________________________________________________________________________________________________
  294. conv4_block4_2_conv (Conv2D) (None, 17, 17, 256) 590080 conv4_block4_1_relu[0][0]
  295. __________________________________________________________________________________________________
  296. conv4_block4_2_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block4_2_conv[0][0]
  297. __________________________________________________________________________________________________
  298. conv4_block4_2_relu (Activation (None, 17, 17, 256) 0 conv4_block4_2_bn[0][0]
  299. __________________________________________________________________________________________________
  300. conv4_block4_3_conv (Conv2D) (None, 17, 17, 1024) 263168 conv4_block4_2_relu[0][0]
  301. __________________________________________________________________________________________________
  302. conv4_block4_3_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block4_3_conv[0][0]
  303. __________________________________________________________________________________________________
  304. conv4_block4_add (Add) (None, 17, 17, 1024) 0 conv4_block3_out[0][0]
  305. conv4_block4_3_bn[0][0]
  306. __________________________________________________________________________________________________
  307. conv4_block4_out (Activation) (None, 17, 17, 1024) 0 conv4_block4_add[0][0]
  308. __________________________________________________________________________________________________
  309. conv4_block5_1_conv (Conv2D) (None, 17, 17, 256) 262400 conv4_block4_out[0][0]
  310. __________________________________________________________________________________________________
  311. conv4_block5_1_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block5_1_conv[0][0]
  312. __________________________________________________________________________________________________
  313. conv4_block5_1_relu (Activation (None, 17, 17, 256) 0 conv4_block5_1_bn[0][0]
  314. __________________________________________________________________________________________________
  315. conv4_block5_2_conv (Conv2D) (None, 17, 17, 256) 590080 conv4_block5_1_relu[0][0]
  316. __________________________________________________________________________________________________
  317. conv4_block5_2_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block5_2_conv[0][0]
  318. __________________________________________________________________________________________________
  319. conv4_block5_2_relu (Activation (None, 17, 17, 256) 0 conv4_block5_2_bn[0][0]
  320. __________________________________________________________________________________________________
  321. conv4_block5_3_conv (Conv2D) (None, 17, 17, 1024) 263168 conv4_block5_2_relu[0][0]
  322. __________________________________________________________________________________________________
  323. conv4_block5_3_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block5_3_conv[0][0]
  324. __________________________________________________________________________________________________
  325. conv4_block5_add (Add) (None, 17, 17, 1024) 0 conv4_block4_out[0][0]
  326. conv4_block5_3_bn[0][0]
  327. __________________________________________________________________________________________________
  328. conv4_block5_out (Activation) (None, 17, 17, 1024) 0 conv4_block5_add[0][0]
  329. __________________________________________________________________________________________________
  330. conv4_block6_1_conv (Conv2D) (None, 17, 17, 256) 262400 conv4_block5_out[0][0]
  331. __________________________________________________________________________________________________
  332. conv4_block6_1_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block6_1_conv[0][0]
  333. __________________________________________________________________________________________________
  334. conv4_block6_1_relu (Activation (None, 17, 17, 256) 0 conv4_block6_1_bn[0][0]
  335. __________________________________________________________________________________________________
  336. conv4_block6_2_conv (Conv2D) (None, 17, 17, 256) 590080 conv4_block6_1_relu[0][0]
  337. __________________________________________________________________________________________________
  338. conv4_block6_2_bn (BatchNormali (None, 17, 17, 256) 1024 conv4_block6_2_conv[0][0]
  339. __________________________________________________________________________________________________
  340. conv4_block6_2_relu (Activation (None, 17, 17, 256) 0 conv4_block6_2_bn[0][0]
  341. __________________________________________________________________________________________________
  342. conv4_block6_3_conv (Conv2D) (None, 17, 17, 1024) 263168 conv4_block6_2_relu[0][0]
  343. __________________________________________________________________________________________________
  344. conv4_block6_3_bn (BatchNormali (None, 17, 17, 1024) 4096 conv4_block6_3_conv[0][0]
  345. __________________________________________________________________________________________________
  346. conv4_block6_add (Add) (None, 17, 17, 1024) 0 conv4_block5_out[0][0]
  347. conv4_block6_3_bn[0][0]
  348. __________________________________________________________________________________________________
  349. conv4_block6_out (Activation) (None, 17, 17, 1024) 0 conv4_block6_add[0][0]
  350. __________________________________________________________________________________________________
  351. conv5_block1_1_conv (Conv2D) (None, 9, 9, 512) 524800 conv4_block6_out[0][0]
  352. __________________________________________________________________________________________________
  353. conv5_block1_1_bn (BatchNormali (None, 9, 9, 512) 2048 conv5_block1_1_conv[0][0]
  354. __________________________________________________________________________________________________
  355. conv5_block1_1_relu (Activation (None, 9, 9, 512) 0 conv5_block1_1_bn[0][0]
  356. __________________________________________________________________________________________________
  357. conv5_block1_2_conv (Conv2D) (None, 9, 9, 512) 2359808 conv5_block1_1_relu[0][0]
  358. __________________________________________________________________________________________________
  359. conv5_block1_2_bn (BatchNormali (None, 9, 9, 512) 2048 conv5_block1_2_conv[0][0]
  360. __________________________________________________________________________________________________
  361. conv5_block1_2_relu (Activation (None, 9, 9, 512) 0 conv5_block1_2_bn[0][0]
  362. __________________________________________________________________________________________________
  363. conv5_block1_0_conv (Conv2D) (None, 9, 9, 2048) 2099200 conv4_block6_out[0][0]
  364. __________________________________________________________________________________________________
  365. conv5_block1_3_conv (Conv2D) (None, 9, 9, 2048) 1050624 conv5_block1_2_relu[0][0]
  366. __________________________________________________________________________________________________
  367. conv5_block1_0_bn (BatchNormali (None, 9, 9, 2048) 8192 conv5_block1_0_conv[0][0]
  368. __________________________________________________________________________________________________
  369. conv5_block1_3_bn (BatchNormali (None, 9, 9, 2048) 8192 conv5_block1_3_conv[0][0]
  370. __________________________________________________________________________________________________
  371. conv5_block1_add (Add) (None, 9, 9, 2048) 0 conv5_block1_0_bn[0][0]
  372. conv5_block1_3_bn[0][0]
  373. __________________________________________________________________________________________________
  374. conv5_block1_out (Activation) (None, 9, 9, 2048) 0 conv5_block1_add[0][0]
  375. __________________________________________________________________________________________________
  376. conv5_block2_1_conv (Conv2D) (None, 9, 9, 512) 1049088 conv5_block1_out[0][0]
  377. __________________________________________________________________________________________________
  378. conv5_block2_1_bn (BatchNormali (None, 9, 9, 512) 2048 conv5_block2_1_conv[0][0]
  379. __________________________________________________________________________________________________
  380. conv5_block2_1_relu (Activation (None, 9, 9, 512) 0 conv5_block2_1_bn[0][0]
  381. __________________________________________________________________________________________________
  382. conv5_block2_2_conv (Conv2D) (None, 9, 9, 512) 2359808 conv5_block2_1_relu[0][0]
  383. __________________________________________________________________________________________________
  384. conv5_block2_2_bn (BatchNormali (None, 9, 9, 512) 2048 conv5_block2_2_conv[0][0]
  385. __________________________________________________________________________________________________
  386. conv5_block2_2_relu (Activation (None, 9, 9, 512) 0 conv5_block2_2_bn[0][0]
  387. __________________________________________________________________________________________________
  388. conv5_block2_3_conv (Conv2D) (None, 9, 9, 2048) 1050624 conv5_block2_2_relu[0][0]
  389. __________________________________________________________________________________________________
  390. conv5_block2_3_bn (BatchNormali (None, 9, 9, 2048) 8192 conv5_block2_3_conv[0][0]
  391. __________________________________________________________________________________________________
  392. conv5_block2_add (Add) (None, 9, 9, 2048) 0 conv5_block1_out[0][0]
  393. conv5_block2_3_bn[0][0]
  394. __________________________________________________________________________________________________
  395. conv5_block2_out (Activation) (None, 9, 9, 2048) 0 conv5_block2_add[0][0]
  396. __________________________________________________________________________________________________
  397. conv5_block3_1_conv (Conv2D) (None, 9, 9, 512) 1049088 conv5_block2_out[0][0]
  398. __________________________________________________________________________________________________
  399. conv5_block3_1_bn (BatchNormali (None, 9, 9, 512) 2048 conv5_block3_1_conv[0][0]
  400. __________________________________________________________________________________________________
  401. conv5_block3_1_relu (Activation (None, 9, 9, 512) 0 conv5_block3_1_bn[0][0]
  402. __________________________________________________________________________________________________
  403. conv5_block3_2_conv (Conv2D) (None, 9, 9, 512) 2359808 conv5_block3_1_relu[0][0]
  404. __________________________________________________________________________________________________
  405. conv5_block3_2_bn (BatchNormali (None, 9, 9, 512) 2048 conv5_block3_2_conv[0][0]
  406. __________________________________________________________________________________________________
  407. conv5_block3_2_relu (Activation (None, 9, 9, 512) 0 conv5_block3_2_bn[0][0]
  408. __________________________________________________________________________________________________
  409. conv5_block3_3_conv (Conv2D) (None, 9, 9, 2048) 1050624 conv5_block3_2_relu[0][0]
  410. __________________________________________________________________________________________________
  411. conv5_block3_3_bn (BatchNormali (None, 9, 9, 2048) 8192 conv5_block3_3_conv[0][0]
  412. __________________________________________________________________________________________________
  413. conv5_block3_add (Add) (None, 9, 9, 2048) 0 conv5_block2_out[0][0]
  414. conv5_block3_3_bn[0][0]
  415. __________________________________________________________________________________________________
  416. conv5_block3_out (Activation) (None, 9, 9, 2048) 0 conv5_block3_add[0][0]
  417. __________________________________________________________________________________________________
  418. avg_pool (GlobalAveragePooling2 (None, 2048) 0 conv5_block3_out[0][0]
  419. __________________________________________________________________________________________________
  420. probs (Dense) (None, 3) 6147 avg_pool[0][0]
  421. ==================================================================================================
  422. Total params: 23,587,587
  423. Trainable params: 23,534,467
  424. Non-trainable params: 53,120
  425. __________________________________________________________________________________________________
  426. Train for 563.0 steps, validate for 179.0 steps
  427. Epoch 1/10
  428. 2019-11-01 09:53:28.832570: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
  429. 2019-11-01 09:53:30.675227: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
  430. 563/563 [==============================] - 141s 250ms/step - loss: 0.1185 - accuracy: 0.9616 - val_loss: 0.5751 - val_accuracy: 0.8078
  431. Epoch 2/10
  432. 563/563 [==============================] - 130s 231ms/step - loss: 0.0400 - accuracy: 0.9865 - val_loss: 0.8953 - val_accuracy: 0.7119
  433. Epoch 3/10
  434. 563/563 [==============================] - 130s 231ms/step - loss: 0.0478 - accuracy: 0.9870 - val_loss: 25.3537 - val_accuracy: 0.3367
  435. Epoch 4/10
  436. 563/563 [==============================] - 130s 230ms/step - loss: 0.0309 - accuracy: 0.9906 - val_loss: 0.0576 - val_accuracy: 0.9946
  437. Epoch 5/10
  438. 563/563 [==============================] - 129s 230ms/step - loss: 0.0210 - accuracy: 0.9940 - val_loss: 0.0780 - val_accuracy: 0.9916
  439. Epoch 6/10
  440. 563/563 [==============================] - 130s 230ms/step - loss: 0.0227 - accuracy: 0.9937 - val_loss: 0.0595 - val_accuracy: 0.9887
  441. Epoch 7/10
  442. 563/563 [==============================] - 129s 230ms/step - loss: 0.0160 - accuracy: 0.9949 - val_loss: 0.0536 - val_accuracy: 0.9946
  443. Epoch 8/10
  444. 81/563 [===>..........................] - ETA: 1:39 - loss: 0.0222 - accuracy: 0.9945
Add Comment
Please, Sign In to add comment
Public Pastes
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!