Training a simple TensorFlow neural network model for classifying handwritten digits from the MNIST dataset

tensorflow_convnet_training_terminal_output.txt

(tensorflow)cedric@starlite:~
$ python -m tensorflow.models.image.mnist.convolutional
I tensorflow/stream_executor/dso_loader.cc:101] successfully opened CUDA library libcublas.so.7.0 locally
I tensorflow/stream_executor/dso_loader.cc:101] successfully opened CUDA library libcudnn.so.6.5 locally
I tensorflow/stream_executor/dso_loader.cc:101] successfully opened CUDA library libcufft.so.7.0 locally
I tensorflow/stream_executor/dso_loader.cc:101] successfully opened CUDA library libcuda.so locally
I tensorflow/stream_executor/dso_loader.cc:101] successfully opened CUDA library libcurand.so.7.0 locally
Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:909] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_init.cc:102] Found device 0 with properties: 
name: GeForce 840M
major: 5 minor: 0 memoryClockRate (GHz) 1.124
pciBusID 0000:03:00.0
Total memory: 2.00GiB
Free memory: 1.72GiB
I tensorflow/core/common_runtime/gpu/gpu_init.cc:126] DMA: 0 
I tensorflow/core/common_runtime/gpu/gpu_init.cc:136] 0:   Y 
I tensorflow/core/common_runtime/gpu/gpu_device.cc:680] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce 840M, pci bus id: 0000:03:00.0)
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 1.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 2.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 4.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 8.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 16.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 32.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 64.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 128.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 256.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 512.0KiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 1.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 2.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 4.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 8.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 16.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 32.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 64.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 128.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 256.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 512.00MiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 1.00GiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:51] Creating bin of max chunk size 2.00GiB
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:73] Allocating 1.52GiB bytes.
I tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:83] GPU 0 memory begins at 0x5011c0000 extends to 0x5628d8000
Initialized!
Step 0 (epoch 0.00), 7.7 ms
Minibatch loss: 12.054, learning rate: 0.010000
Minibatch error: 90.6%
Validation error: 84.6%
Step 100 (epoch 0.12), 74.0 ms
Minibatch loss: 3.294, learning rate: 0.010000
Minibatch error: 4.7%
Validation error: 7.3%
Step 200 (epoch 0.23), 73.2 ms
Minibatch loss: 3.472, learning rate: 0.010000
Minibatch error: 12.5%
Validation error: 3.9%
Step 300 (epoch 0.35), 73.9 ms
Minibatch loss: 3.201, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 3.4%
Step 400 (epoch 0.47), 77.1 ms
Minibatch loss: 3.209, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 2.8%
Step 500 (epoch 0.58), 73.8 ms
Minibatch loss: 3.305, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 2.6%
Step 600 (epoch 0.70), 77.0 ms
Minibatch loss: 3.231, learning rate: 0.010000
Minibatch error: 9.4%
Validation error: 2.7%
Step 700 (epoch 0.81), 73.4 ms
Minibatch loss: 3.013, learning rate: 0.010000
Minibatch error: 3.1%
Validation error: 2.4%
Step 800 (epoch 0.93), 73.4 ms
Minibatch loss: 3.113, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 2.2%
Step 900 (epoch 1.05), 73.8 ms
Minibatch loss: 2.929, learning rate: 0.009500
Minibatch error: 3.1%
Validation error: 1.5%
Step 1000 (epoch 1.16), 80.8 ms
Minibatch loss: 2.853, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.7%
Step 1100 (epoch 1.28), 81.1 ms
Minibatch loss: 2.820, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.5%
Step 1200 (epoch 1.40), 79.9 ms
Minibatch loss: 2.914, learning rate: 0.009500
Minibatch error: 7.8%
Validation error: 1.6%
Step 1300 (epoch 1.51), 81.0 ms
Minibatch loss: 2.761, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.6%
Step 1400 (epoch 1.63), 76.2 ms
Minibatch loss: 2.790, learning rate: 0.009500
Minibatch error: 4.7%
Validation error: 1.5%
Step 1500 (epoch 1.75), 74.1 ms
Minibatch loss: 2.859, learning rate: 0.009500
Minibatch error: 6.2%
Validation error: 1.3%
Step 1600 (epoch 1.86), 74.7 ms
Minibatch loss: 2.686, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.3%
Step 1700 (epoch 1.98), 81.2 ms
Minibatch loss: 2.650, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.4%
Step 1800 (epoch 2.09), 86.8 ms
Minibatch loss: 2.677, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.3%
Step 1900 (epoch 2.21), 82.0 ms
Minibatch loss: 2.657, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.1%
Step 2000 (epoch 2.33), 77.1 ms
Minibatch loss: 2.635, learning rate: 0.009025
Minibatch error: 3.1%
Validation error: 1.2%
Step 2100 (epoch 2.44), 77.4 ms
Minibatch loss: 2.590, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.1%
Step 2200 (epoch 2.56), 76.7 ms
Minibatch loss: 2.577, learning rate: 0.009025
Minibatch error: 0.0%
Validation error: 1.1%
Step 2300 (epoch 2.68), 76.6 ms
Minibatch loss: 2.565, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.1%
Step 2400 (epoch 2.79), 76.6 ms
Minibatch loss: 2.500, learning rate: 0.009025
Minibatch error: 0.0%
Validation error: 1.2%
Step 2500 (epoch 2.91), 76.5 ms
Minibatch loss: 2.478, learning rate: 0.009025
Minibatch error: 0.0%
Validation error: 1.2%
Step 2600 (epoch 3.03), 78.4 ms
Minibatch loss: 2.462, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.2%
Step 2700 (epoch 3.14), 76.4 ms
Minibatch loss: 2.477, learning rate: 0.008574
Minibatch error: 3.1%
Validation error: 1.1%
Step 2800 (epoch 3.26), 75.7 ms
Minibatch loss: 2.422, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.3%
Step 2900 (epoch 3.37), 74.9 ms
Minibatch loss: 2.492, learning rate: 0.008574
Minibatch error: 3.1%
Validation error: 1.3%
Step 3000 (epoch 3.49), 75.4 ms
Minibatch loss: 2.406, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.1%
Step 3100 (epoch 3.61), 75.4 ms
Minibatch loss: 2.372, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.1%
Step 3200 (epoch 3.72), 76.4 ms
Minibatch loss: 2.332, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.1%
Step 3300 (epoch 3.84), 83.8 ms
Minibatch loss: 2.320, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.1%
Step 3400 (epoch 3.96), 81.6 ms
Minibatch loss: 2.299, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.1%
Step 3500 (epoch 4.07), 76.2 ms
Minibatch loss: 2.274, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 1.0%
Step 3600 (epoch 4.19), 77.9 ms
Minibatch loss: 2.255, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 0.9%
Step 3700 (epoch 4.31), 77.3 ms
Minibatch loss: 2.238, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 1.0%
Step 3800 (epoch 4.42), 78.4 ms
Minibatch loss: 2.236, learning rate: 0.008145
Minibatch error: 1.6%
Validation error: 1.0%
Step 3900 (epoch 4.54), 78.9 ms
Minibatch loss: 2.291, learning rate: 0.008145
Minibatch error: 3.1%
Validation error: 1.0%
Step 4000 (epoch 4.65), 77.9 ms
Minibatch loss: 2.211, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 1.0%
Step 4100 (epoch 4.77), 77.0 ms
Minibatch loss: 2.179, learning rate: 0.008145
Minibatch error: 1.6%
Validation error: 1.0%
Step 4200 (epoch 4.89), 77.4 ms
Minibatch loss: 2.216, learning rate: 0.008145
Minibatch error: 1.6%
Validation error: 1.0%
Step 4300 (epoch 5.00), 78.1 ms
Minibatch loss: 2.197, learning rate: 0.007738
Minibatch error: 1.6%
Validation error: 1.0%
Step 4400 (epoch 5.12), 76.3 ms
Minibatch loss: 2.146, learning rate: 0.007738
Minibatch error: 1.6%
Validation error: 0.9%
Step 4500 (epoch 5.24), 76.6 ms
Minibatch loss: 2.160, learning rate: 0.007738
Minibatch error: 3.1%
Validation error: 1.0%
Step 4600 (epoch 5.35), 76.3 ms
Minibatch loss: 2.106, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 4700 (epoch 5.47), 76.4 ms
Minibatch loss: 2.079, learning rate: 0.007738
Minibatch error: 1.6%
Validation error: 1.0%
Step 4800 (epoch 5.59), 76.4 ms
Minibatch loss: 2.059, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 4900 (epoch 5.70), 76.1 ms
Minibatch loss: 2.044, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 5000 (epoch 5.82), 76.5 ms
Minibatch loss: 2.131, learning rate: 0.007738
Minibatch error: 3.1%
Validation error: 1.0%
Step 5100 (epoch 5.93), 76.3 ms
Minibatch loss: 2.008, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 5200 (epoch 6.05), 76.4 ms
Minibatch loss: 2.085, learning rate: 0.007351
Minibatch error: 3.1%
Validation error: 0.9%
Step 5300 (epoch 6.17), 76.1 ms
Minibatch loss: 1.984, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.9%
Step 5400 (epoch 6.28), 76.4 ms
Minibatch loss: 1.963, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 5500 (epoch 6.40), 76.3 ms
Minibatch loss: 1.955, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 5600 (epoch 6.52), 76.2 ms
Minibatch loss: 1.927, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 5700 (epoch 6.63), 76.3 ms
Minibatch loss: 1.917, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 1.1%
Step 5800 (epoch 6.75), 76.3 ms
Minibatch loss: 1.898, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 5900 (epoch 6.87), 76.4 ms
Minibatch loss: 1.888, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.9%
Step 6000 (epoch 6.98), 76.4 ms
Minibatch loss: 1.877, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 1.0%
Step 6100 (epoch 7.10), 76.5 ms
Minibatch loss: 1.859, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6200 (epoch 7.21), 76.3 ms
Minibatch loss: 1.843, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.9%
Step 6300 (epoch 7.33), 76.5 ms
Minibatch loss: 1.839, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6400 (epoch 7.45), 77.6 ms
Minibatch loss: 1.879, learning rate: 0.006983
Minibatch error: 3.1%
Validation error: 0.8%
Step 6500 (epoch 7.56), 77.8 ms
Minibatch loss: 1.808, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.9%
Step 6600 (epoch 7.68), 77.5 ms
Minibatch loss: 1.826, learning rate: 0.006983
Minibatch error: 1.6%
Validation error: 0.9%
Step 6700 (epoch 7.80), 77.3 ms
Minibatch loss: 1.786, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6800 (epoch 7.91), 77.6 ms
Minibatch loss: 1.771, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.9%
Step 6900 (epoch 8.03), 77.4 ms
Minibatch loss: 1.759, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.9%
Step 7000 (epoch 8.15), 77.0 ms
Minibatch loss: 1.807, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.8%
Step 7100 (epoch 8.26), 77.5 ms
Minibatch loss: 1.753, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.9%
Step 7200 (epoch 8.38), 77.0 ms
Minibatch loss: 1.743, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.8%
Step 7300 (epoch 8.49), 77.1 ms
Minibatch loss: 1.721, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.8%
Step 7400 (epoch 8.61), 77.4 ms
Minibatch loss: 1.702, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.7%
Step 7500 (epoch 8.73), 77.2 ms
Minibatch loss: 1.695, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.7%
Step 7600 (epoch 8.84), 77.6 ms
Minibatch loss: 1.810, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.8%
Step 7700 (epoch 8.96), 77.4 ms
Minibatch loss: 1.667, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.9%
Step 7800 (epoch 9.08), 77.8 ms
Minibatch loss: 1.664, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.8%
Step 7900 (epoch 9.19), 77.2 ms
Minibatch loss: 1.648, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.8%
Step 8000 (epoch 9.31), 77.6 ms
Minibatch loss: 1.664, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 8100 (epoch 9.43), 77.5 ms
Minibatch loss: 1.628, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.8%
Step 8200 (epoch 9.54), 77.9 ms
Minibatch loss: 1.633, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.8%
Step 8300 (epoch 9.66), 77.4 ms
Minibatch loss: 1.611, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.7%
Step 8400 (epoch 9.77), 77.8 ms
Minibatch loss: 1.597, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.8%
Step 8500 (epoch 9.89), 77.3 ms
Minibatch loss: 1.598, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Test error: 0.8%

TensorFlow is an open source software library for machine intelligence/learning.

For this training, I have deployed computation to one GPU in a desktop.

Note: TensorFlow version used was built from source from git master branch with GPU support enabled.

GPU support using NVIDIA:

• CUDA SDK 7.0
• CUDA library: CUDA Deep Neural Network (CUDNN) 6.5 v2