Guest User

ROCm RX580 MNIST

a guest
Jan 25th, 2021
50
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. /usr/bin/python3.8 /home/boris/PycharmProjects/keras-mnist/main.py
  2. Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
  3. 11493376/11490434 [==============================] - 1s 0us/step
  4. x_train shape: (60000, 28, 28, 1)
  5. 60000 train samples
  6. 10000 test samples
  7. 2021-01-25 11:24:12.072793: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
  8. 2021-01-25 11:24:12.073012: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libamdhip64.so
  9. 2021-01-25 11:24:12.149668: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1738] Found device 0 with properties:
  10. pciBusID: 0000:1d:00.0 name: Ellesmere [Radeon RX 470/480/570/570X/580/580X/590]     ROCm AMD GPU ISA: gfx803
  11. coreClock: 1.266GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 119.21GiB/s
  12. 2021-01-25 11:24:12.152244: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocblas.so
  13. 2021-01-25 11:24:12.153433: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libMIOpen.so
  14. 2021-01-25 11:24:12.165157: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocfft.so
  15. 2021-01-25 11:24:12.165443: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocrand.so
  16. 2021-01-25 11:24:12.165538: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
  17. 2021-01-25 11:24:12.165802: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE3 SSE4.1 SSE4.2 AVX AVX2 FMA
  18. To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
  19. 2021-01-25 11:24:12.166301: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set
  20. 2021-01-25 11:24:12.166364: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1738] Found device 0 with properties:
  21. pciBusID: 0000:1d:00.0 name: Ellesmere [Radeon RX 470/480/570/570X/580/580X/590]     ROCm AMD GPU ISA: gfx803
  22. coreClock: 1.266GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 119.21GiB/s
  23. 2021-01-25 11:24:12.166381: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocblas.so
  24. 2021-01-25 11:24:12.166389: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libMIOpen.so
  25. 2021-01-25 11:24:12.166396: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocfft.so
  26. 2021-01-25 11:24:12.166403: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocrand.so
  27. 2021-01-25 11:24:12.166453: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
  28. 2021-01-25 11:24:12.166513: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix:
  29. 2021-01-25 11:24:12.166521: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267]      0
  30. 2021-01-25 11:24:12.166525: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1280] 0:   N
  31. 2021-01-25 11:24:12.166630: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1406] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7700 MB memory) -> physical GPU (device: 0, name: Ellesmere [Radeon RX 470/480/570/570X/580/580X/590], pci bus id: 0000:1d:00.0)
  32. Model: "sequential"
  33. _________________________________________________________________
  34. Layer (type)                 Output Shape              Param #  
  35. =================================================================
  36. conv2d (Conv2D)              (None, 26, 26, 32)        320      
  37. _________________________________________________________________
  38. max_pooling2d (MaxPooling2D) (None, 13, 13, 32)        0        
  39. _________________________________________________________________
  40. conv2d_1 (Conv2D)            (None, 11, 11, 64)        18496    
  41. _________________________________________________________________
  42. max_pooling2d_1 (MaxPooling2 (None, 5, 5, 64)          0        
  43. _________________________________________________________________
  44. flatten (Flatten)            (None, 1600)              0        
  45. _________________________________________________________________
  46. dropout (Dropout)            (None, 1600)              0        
  47. _________________________________________________________________
  48. dense (Dense)                (None, 10)                16010    
  49. =================================================================
  50. Total params: 34,826
  51. Trainable params: 34,826
  52. Non-trainable params: 0
  53. _________________________________________________________________
  54. 2021-01-25 11:24:14.057724: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 169344000 exceeds 10% of free system memory.
  55. 2021-01-25 11:24:14.332118: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2)
  56. 2021-01-25 11:24:14.408011: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 3393200000 Hz
  57. Epoch 1/15
  58. 2021-01-25 11:24:15.355843: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library librocblas.so
  59. 2021-01-25 11:24:15.527084: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libMIOpen.so
  60. 422/422 [==============================] - 46s 29ms/step - loss: 0.8014 - accuracy: 0.7674 - val_loss: 0.1141 - val_accuracy: 0.9705
  61. Epoch 2/15
  62. 422/422 [==============================] - 2s 5ms/step - loss: 0.1795 - accuracy: 0.9514 - val_loss: 0.1155 - val_accuracy: 0.9752
  63. Epoch 3/15
  64. 422/422 [==============================] - 2s 5ms/step - loss: 0.2143 - accuracy: 0.9564 - val_loss: 0.0812 - val_accuracy: 0.9798
  65. Epoch 4/15
  66. 422/422 [==============================] - 2s 5ms/step - loss: 0.1167 - accuracy: 0.9666 - val_loss: 0.0878 - val_accuracy: 0.9815
  67. Epoch 5/15
  68. 422/422 [==============================] - 2s 5ms/step - loss: 0.1367 - accuracy: 0.9662 - val_loss: 0.0670 - val_accuracy: 0.9838
  69. Epoch 6/15
  70. 422/422 [==============================] - 2s 5ms/step - loss: 0.1081 - accuracy: 0.9716 - val_loss: 0.0560 - val_accuracy: 0.9848
  71. Epoch 7/15
  72. 422/422 [==============================] - 2s 5ms/step - loss: 0.0967 - accuracy: 0.9740 - val_loss: 0.0571 - val_accuracy: 0.9847
  73. Epoch 8/15
  74. 422/422 [==============================] - 2s 5ms/step - loss: 0.0843 - accuracy: 0.9752 - val_loss: 0.0632 - val_accuracy: 0.9855
  75. Epoch 9/15
  76. 422/422 [==============================] - 2s 5ms/step - loss: 0.0962 - accuracy: 0.9755 - val_loss: 0.0486 - val_accuracy: 0.9872
  77. Epoch 10/15
  78. 422/422 [==============================] - 2s 5ms/step - loss: 0.0908 - accuracy: 0.9761 - val_loss: 0.0481 - val_accuracy: 0.9883
  79. Epoch 11/15
  80. 422/422 [==============================] - 2s 5ms/step - loss: 0.0698 - accuracy: 0.9797 - val_loss: 0.0425 - val_accuracy: 0.9895
  81. Epoch 12/15
  82. 422/422 [==============================] - 2s 5ms/step - loss: 0.0696 - accuracy: 0.9792 - val_loss: 0.0479 - val_accuracy: 0.9885
  83. Epoch 13/15
  84. 422/422 [==============================] - 2s 5ms/step - loss: 0.0693 - accuracy: 0.9813 - val_loss: 0.0431 - val_accuracy: 0.9892
  85. Epoch 14/15
  86. 422/422 [==============================] - 2s 5ms/step - loss: 0.0603 - accuracy: 0.9825 - val_loss: 0.0493 - val_accuracy: 0.9885
  87. Epoch 15/15
  88. 422/422 [==============================] - 2s 5ms/step - loss: 0.0592 - accuracy: 0.9831 - val_loss: 0.0414 - val_accuracy: 0.9898
  89. Test loss: 0.047726474702358246
  90. Test accuracy: 0.9864000082015991
  91.  
  92. Process finished with exit code 0
  93.  
RAW Paste Data

Adblocker detected! Please consider disabling it...

We've detected AdBlock Plus or some other adblocking software preventing Pastebin.com from fully loading.

We don't have any obnoxious sound, or popup ads, we actively block these annoying types of ads!

Please add Pastebin.com to your ad blocker whitelist or disable your adblocking software.

×