【2020年版】NVIDIA Jetson Nanoで TensorFlowの StyleGANを動かして、顔画像を生成

【2020年版】NVIDIA Jetson Nano、Jetson Xavier NXの便利スクリプト

【2020年】Jetson Xavier NX 開発者キットが安かったので衝動買いした件、標準販売価格５万円が４万４千円！

【2020年版】NVIDIA Jetson Nanoの初期設定、最高速で動かす設定、空きメモリを増やす方法等

Jetson Nano、Jetson Xavier NX 開発者キット TensorFlow on Jetson Platform

# StyleGAN
cd
git clone https://github.com/NVlabs/stylegan --depth 1
cd stylegan
python3 pretrained_example.py

# Traceback (most recent call last):
#   File "pretrained_example.py", line 12, in <module>
#     import numpy as np
# ModuleNotFoundError: No module named 'numpy'

# Install TensorFlow for Jetson Platform

# Install system packages required by TensorFlow
sudo apt-get update
sudo apt-get -y install libhdf5-serial-dev hdf5-tools libhdf5-dev zlib1g-dev zip libjpeg8-dev liblapack-dev libblas-dev gfortran

# Install and upgrade pip3.
sudo apt-get -y install python3-pip
# sudo pip3 install -U pip testresources setuptools

# Install Cython
#         raise OSError('Cython needs to be installed in Python as a module')
# sudo pip3 install --no-use-wheel --no-cache-dir Cython
# DEPRECATION: --no-use-wheel is deprecated and will be removed in the future.  Please use --no-binary :all: instead.
# https://kurozumi.github.io/pip/reference/pip_wheel.html
sudo pip3 install --no-binary :all: --no-cache-dir Cython

# Install the Python package dependencies.
sudo pip3 install -U numpy==1.16.1 future==0.17.1 mock==3.0.5 h5py==2.9.0 keras_preprocessing==1.0.5 keras_applications==1.0.8 gast==0.2.2 futures protobuf pybind11

#         raise OSError('Cython needs to be installed in Python as a module')
#     OSError: Cython needs to be installed in Python as a module
#     Running from numpy source directory.
#     /tmp/easy_install-na5g1t43/numpy-1.19.0/setup.py:460: UserWarning: Unrecognized setuptools command, proceeding with generating Cython sources and expanding templates
#     ----------------------------------------
# Command "python setup.py egg_info" failed with error code 1 in /tmp/pip-build-eoih3y93/h5py/

# TensorFlow 1.x Jetson Nano JetPack 4.3
# https://developer.download.nvidia.com/compute/redist/jp/v43/tensorflow/tensorflow-1.15.2+nv20.3-cp36-cp36m-linux_aarch64.whl
# sudo pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v43 tensorflow==1.15.2+nv20.3
#   File "/usr/share/python-wheels/requests-2.18.4-py2.py3-none-any.whl/requests/models.py", line 935, in raise_for_status
#     raise HTTPError(http_error_msg, response=self)
# requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://developer.download.nvidia.com/compute/redist/jp/v43/opt-einsum/
# --no-cache-dirを付ける
sudo pip3 install --pre --no-cache-dir --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v43 tensorflow==1.15.2+nv20.3

#   Running setup.py install for absl-py ... done
#   Running setup.py install for termcolor ... done
#   Running setup.py install for grpcio ... done
#   Running setup.py install for wrapt ... done
# Successfully installed absl-py-0.9.0 astor-0.8.1 google-pasta-0.2.0 grpcio-1.30.0 importlib-metadata-1.6.1 markdown-3.2.2 opt-einsum-3.2.1 tensorboard-1.15.0 tensorflow-1.15.2+nv20.3.tf1 tensorflow-estimator-1.15.1 termcolor-1.1.0 werkzeug-1.0.1 wrapt-1.12.1 zipp-3.1.0

# Verifying The Installation
# TF-1.15 tensorflow-1.15.2+nv20.3-cp36-cp36m-linux_aarch64.whl
python3 -c "import tensorflow; print (tensorflow.__version__)"
# 1.15.2

python3 pretrained_example.py
# Traceback (most recent call last):
#   File "pretrained_example.py", line 13, in <module>
#     import PIL.Image
# ModuleNotFoundError: No module named 'PIL'

# ModuleNotFoundError: No module named 'PIL'
sudo pip3 install pillow

sudo pip3 install pillow
# The directory '/home/jetson/.cache/pip/http' or its parent directory is not owned by the current user and the cache has been disabled. Please check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.
# The directory '/home/jetson/.cache/pip' or its parent directory is not owned by the current user and caching wheels has been disabled. check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.
# Requirement already satisfied: pillow in /usr/local/lib/python3.6/dist-packages

# jetson@jetson-desktop:~/stylegan $ pip3 -V
# pip 9.0.1 from /usr/lib/python3/dist-packages (python 3.6)

pretrained_example.py
# Using pre-trained networks
python3 pretrained_example.py

2020-06-26 00:02:43.493830: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
WARNING:tensorflow:From /home/jetson/stylegan/dnnlib/tflib/tfutil.py:34: The name tf.Dimension is deprecated. Please use tf.compat.v1.Dimension instead.

WARNING:tensorflow:From /home/jetson/stylegan/dnnlib/tflib/tfutil.py:74: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

WARNING:tensorflow:From /home/jetson/stylegan/dnnlib/tflib/tfutil.py:128: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.

WARNING:tensorflow:From /home/jetson/stylegan/dnnlib/tflib/tfutil.py:97: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.
...
2020-06-26 00:02:49.388855: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2020-06-26 00:02:49.389325: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x122db0f0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-06-26 00:02:49.389382: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-06-26 00:02:49.397224: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2020-06-26 00:02:49.455965: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-26 00:02:49.456256: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x12288d50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-06-26 00:02:49.456316: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): NVIDIA Tegra X1, Compute Capability 5.3
2020-06-26 00:02:49.456738: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-26 00:02:49.456852: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1639] Found device 0 with properties:
name: NVIDIA Tegra X1 major: 5 minor: 3 memoryClockRate(GHz): 0.9216
pciBusID: 0000:00:00.0
...
2020-06-26 00:02:50.625538: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1325] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 807 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X1, pci bus id: 0000:00:00.0, compute capability: 5.3)
Downloading https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ .... done
WARNING:tensorflow:From /home/jetson/stylegan/dnnlib/tflib/network.py:142: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

Gs                              Params    OutputShape          WeightShape
---                             ---       ---                  ---
latents_in                      -         (?, 512)             -
...
G_synthesis/noise17             -         (1, 1, 1024, 1024)   -
images_out                      -         (?, 3, 1024, 1024)   -
---                             ---       ---                  ---
Total                           26219627

2020-06-26 00:05:21.044356: W tensorflow/core/common_runtime/bfc_allocator.cc:239] Allocator (GPU_0_bfc) ran out of memory trying to allocate 313.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.

Allocator (GPU_0_bfc) ran out of memory trying to allocate 313.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
　意味：メモリがもっと沢山あれば、パフォーマンス（動作速度）が良くなるよ。

# Using pre-trained networks
python3 pretrained_example.py

# 2020-06-26 00:08:18.306368: W tensorflow/core/common_runtime/bfc_allocator.cc:239] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.27GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
# https://stackoverflow.com/questions/37327312/what-can-i-do-to-run-specific-tensorflow-calculations-on-a-cpu-as-part-of-a-gpu
# What can I do to run specific TensorFlow calculations on a CPU as part of a GPU implementation ?

# https://github.com/tensorflow/tensorflow/issues/35264
# ran out of memory trying to allocate #35264

free -h
              total        used        free      shared  buff/cache   available
Mem:           3.9G        1.0G        2.6G        3.1M        293M        3.2G
Swap:          6.0G        106M        5.9G

# example.png
ls -l results/
# -rw-rw-r-- 1 jetson jetson 1678371  6月 26 00:35 example.png

generate_figures.py
# A more advanced example is given in generate_figures.py
python3 generate_figures.py

# メモリ不足で死亡 OOM = Out Of Memory
  (0) Resource exhausted: OOM when allocating tensor with shape[8,16,1024,1024] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node Gs/_Run/Gs/G_synthesis/cond/cond/cond/cond/cond/cond/cond/1024x1024/Conv0_up/conv2d_transpose (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

         [[Gs/_Run/saturate_cast/_1421]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

  (1) Resource exhausted: OOM when allocating tensor with shape[8,16,1024,1024] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node Gs/_Run/Gs/G_synthesis/cond/cond/cond/cond/cond/cond/cond/1024x1024/Conv0_up/conv2d_transpose (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

# Google Driveの転送量が多すぎでダウンロードの打ち止め Google Drive quota exceeded
Downloading https://drive.google.com/uc?id=1MQywl0FNt6lHu8E_EUqnRbviagS7fbiJ ............ failed
Traceback (most recent call last):
  File "generate_figures.py", line 159, in <module>
    main()
  File "generate_figures.py", line 154, in main
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure12-uncurated-cats.png'), load_Gs(url_cats), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=1)
  File "generate_figures.py", line 33, in load_Gs
    with dnnlib.util.open_url(url, cache_dir=config.cache_dir) as f:
  File "/home/jetson/stylegan/dnnlib/util.py", line 378, in open_url
    raise IOError("Google Drive quota exceeded")
OSError: Google Drive quota exceeded
# Google Driveの転送量が多すぎでダウンロードの打ち止め Google Drive quota exceeded
# 翌日とかに時間を置いて再度試す（転送量がリセットされるのでダウンロードできる）

pretrained_example.py
　黄色行が追加、変更の行。
...
    # Print network details.
    Gs.print_layers()

    for i in range(100):
      print(i)

      # Pick latent vector.
      rnd = np.random.RandomState()
      latents = rnd.randn(1, Gs.input_shape[1])

      # Generate image.
      fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
      images = Gs.run(latents, None, truncation_psi=0.7, randomize_noise=True, output_transform=fmt)

      # Save image.
      os.makedirs(config.result_dir, exist_ok=True)
      png_filename = os.path.join(config.result_dir, 'example_'+ str(i).zfill(3) +'.png')
      PIL.Image.fromarray(images[0], 'RGB').save(png_filename)

...

def main():
    tflib.init_tf()
    os.makedirs(config.result_dir, exist_ok=True)
#    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure02-uncurated-ffhq.png'), load_Gs(url_ffhq), cx=0, cy=0, cw=1024, ch=1024, rows=3, lods=[0,1,2,2,3,3], seed=5)
#    draw_style_mixing_figure(os.path.join(config.result_dir, 'figure03-style-mixing.png'), load_Gs(url_ffhq), w=1024, h=1024, src_seeds=[639,701,687,615,2268], dst_seeds=[888,829,1898,1733,1614,845], style_ranges=[range(0,4)]*3+[range(4,8)]*2+[range(8,18)])
#    draw_noise_detail_figure(os.path.join(config.result_dir, 'figure04-noise-detail.png'), load_Gs(url_ffhq), w=1024, h=1024, num_samples=100, seeds=[1157,1012])
#    draw_noise_components_figure(os.path.join(config.result_dir, 'figure05-noise-components.png'), load_Gs(url_ffhq), w=1024, h=1024, seeds=[1967,1555], noise_ranges=[range(0, 18), range(0, 0), range(8, 18), range(0, 8)], flips=[1])
#    draw_truncation_trick_figure(os.path.join(config.result_dir, 'figure08-truncation-trick.png'), load_Gs(url_ffhq), w=1024, h=1024, seeds=[91,388], psis=[1, 0.7, 0.5, 0, -0.5, -1])
#    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure10-uncurated-bedrooms.png'), load_Gs(url_bedrooms), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=0)
#    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure11-uncurated-cars.png'), load_Gs(url_cars), cx=0, cy=64, cw=512, ch=384, rows=4, lods=[0,1,2,2,3,3], seed=2)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure12-uncurated-cats.png'), load_Gs(url_cats), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=1)

    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure12-uncurated-cats_2.png'), load_Gs(url_cats), cx=0, cy=0, cw=256, ch=256, rows=2, lods=[0,0,1,1], seed=12345)

    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure11-uncurated-cars.png'), load_Gs(url_cars), cx=0, cy=64, cw=512, ch=384, rows=4, lods=[0,1,2,2,3,3], seed=2)

import tensorflow as tf

mnist = tf.keras.datasets.mnist

(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
#  tf.keras.layers.Dense(512, activation=tf.nn.relu),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)

nano mnist.py
python3 mnist.py

2020-06-25 23:57:41.028458: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
11493376/11490434 [==============================] - 1s 0us/step
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
Train on 60000 samples
2020-06-25 23:57:50.724827: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2020-06-25 23:57:52.062096: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:57:52.062250: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1639] Found device 0 with properties:
name: NVIDIA Tegra X1 major: 5 minor: 3 memoryClockRate(GHz): 0.9216
pciBusID: 0000:00:00.0
2020-06-25 23:57:52.062359: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-06-25 23:57:54.269765: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2020-06-25 23:57:54.594083: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2020-06-25 23:57:55.444668: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2020-06-25 23:57:56.411056: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2020-06-25 23:57:56.777884: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2020-06-25 23:58:02.277521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2020-06-25 23:58:02.277789: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:02.278006: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:02.278093: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1767] Adding visible gpu devices: 0
2020-06-25 23:58:02.299945: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2020-06-25 23:58:02.300485: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x76e9020 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-06-25 23:58:02.300542: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-06-25 23:58:02.590697: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:02.590989: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x61b2e80 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-06-25 23:58:02.591050: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): NVIDIA Tegra X1, Compute Capability 5.3
2020-06-25 23:58:02.591468: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:02.591587: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1639] Found device 0 with properties:
name: NVIDIA Tegra X1 major: 5 minor: 3 memoryClockRate(GHz): 0.9216
pciBusID: 0000:00:00.0
2020-06-25 23:58:02.591663: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-06-25 23:58:02.591728: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2020-06-25 23:58:02.591774: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2020-06-25 23:58:02.591819: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2020-06-25 23:58:02.591860: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2020-06-25 23:58:02.591900: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2020-06-25 23:58:02.591941: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2020-06-25 23:58:02.592075: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:02.592243: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:02.592324: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1767] Adding visible gpu devices: 0
2020-06-25 23:58:02.592417: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-06-25 23:58:03.855489: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1180] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-06-25 23:58:03.855572: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1186]      0
2020-06-25 23:58:03.855609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1199] 0:   N
2020-06-25 23:58:03.855914: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:03.856151: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:950] ARM64 does not support NUMA - returning NUMA node zero
2020-06-25 23:58:03.856306: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1325] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 74 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X1, pci bus id: 0000:00:00.0, compute capability: 5.3)
Epoch 1/5
2020-06-25 23:58:04.501848: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
60000/60000 [==============================] - 34s 562us/sample - loss: 0.2949 - acc: 0.9151
Epoch 2/5
60000/60000 [==============================] - 17s 292us/sample - loss: 0.1449 - acc: 0.9566
Epoch 3/5
60000/60000 [==============================] - 16s 270us/sample - loss: 0.1077 - acc: 0.9673
Epoch 4/5
60000/60000 [==============================] - 16s 261us/sample - loss: 0.0905 - acc: 0.9719
Epoch 5/5
60000/60000 [==============================] - 16s 261us/sample - loss: 0.0757 - acc: 0.9760
10000/10000 [==============================] - 2s 165us/sample - loss: 0.0766 - acc: 0.9762

Jetson Nano JetPack 4.3で下記のインストールコマンドだと下記のエラーが出る

# TF-1.15 tensorflow-1.15.2+nv20.3-cp36-cp36m-linux_aarch64.whl
sudo pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v43 'tensorflow<2'

Collecting astor>=0.6.0 (from tensorflow<2)
Exception:
Traceback (most recent call last):
  File "/usr/lib/python3/dist-packages/pip/basecommand.py", line 215, in main
    status = self.run(options, args)
  File "/usr/lib/python3/dist-packages/pip/commands/install.py", line 342, in run
    requirement_set.prepare_files(finder)
  File "/usr/lib/python3/dist-packages/pip/req/req_set.py", line 380, in prepare_files
    ignore_dependencies=self.ignore_dependencies))
  File "/usr/lib/python3/dist-packages/pip/req/req_set.py", line 554, in _prepare_file
    require_hashes
  File "/usr/lib/python3/dist-packages/pip/req/req_install.py", line 278, in populate_link
    self.link = finder.find_requirement(self, upgrade)
  File "/usr/lib/python3/dist-packages/pip/index.py", line 465, in find_requirement
    all_candidates = self.find_all_candidates(req.name)
  File "/usr/lib/python3/dist-packages/pip/index.py", line 423, in find_all_candidates
    for page in self._get_pages(url_locations, project_name):
  File "/usr/lib/python3/dist-packages/pip/index.py", line 568, in _get_pages
    page = self._get_page(location)
  File "/usr/lib/python3/dist-packages/pip/index.py", line 683, in _get_page
    return HTMLPage.get_page(link, session=self.session)
  File "/usr/lib/python3/dist-packages/pip/index.py", line 795, in get_page
    resp.raise_for_status()
  File "/usr/share/python-wheels/requests-2.18.4-py2.py3-none-any.whl/requests/models.py", line 935, in raise_for_status
    raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://developer.download.nvidia.com/compute/redist/jp/v43/astor/

●解決方法
Unable to install TensorFlow on Jetson Nano because of “404” on NVidia server


--no-cache-dir
　を付ける。

pip3 install --pre --no-cache-dir --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v42 tensorflow-gpu

【2020年版】NVIDIA Jetson Nanoで StyleGANの改良版の StyleGAN2で自然な画像を生成

【2020年版】Jetson Nanoで StyleGANを動かして可愛い美少女のアニメ顔を大量生産する方法

【2020年版】NVIDIA Jetson Nano、Jetson Xavier NXの便利スクリプト

【2020年】Jetson Xavier NX 開発者キットが安かったので衝動買いした件、標準販売価格５万円が４万４千円！

【2020年版】NVIDIA Jetson用に最新の CMake 3.17.3をビルドしてインストールする方法

【2020年版】NVIDIA JetPack 4.4 DP Developer Previewで OpenPoseのビルドエラーの対策方法

Jetson Nano、Jetson Xavier NX 開発者キット TensorFlow on Jetson Platform

NVIDIA Jetson Nano 開発者キットを買ってみた。メモリ容量 4GB LPDDR4 RAM

【2020年版】NVIDIA Jetson Nanoの初期設定、最高速で動かす設定、空きメモリを増やす方法等

【2020年版】NVIDIA Jetson Nano JetPackのバージョン情報まとめ、JetPack 4.4は仕様変更の影響が大きい

【2020年版】NVIDIA Jetson Nano対応の FFmpegをビルドする手順

【2020年版】NVIDIA Jetson Nano対応の OpenPoseをビルドする手順

NVIDIA Jetson Nanoで OpenCV 3をビルドしてインストールする方法、NVCaffe等の OpenCV 4未対応を動かす

NVIDIA Jetson Nanoで Visual Studio Code Open Sourceをビルドして実行する

【2020年版】NVIDIA Jetson Nanoで StyleGANの改良版の StyleGAN2で自然な画像を生成

【2020年版】Jetson Nanoで StyleGANを動かして可愛い美少女のアニメ顔を大量生産する方法

【メモリ8GB】Raspberry Pi 4 Model B 8GBを KSYで最安値で購入。ベンチマークレビュー

【Vulkan】Raspberry Pi 4 Model Bで Vulkanドライバをビルドして 3Dグラフィックのデモを動かす

PIP機能付きの 4K対応の 4入力 1出力の HDMIセレクターを買ってみた、HDMI機器が複数有る場合に便利

EDID保持機能付きの 4K対応の 4入力 2出力の マトリックス切り替え HDMIセレクター、液晶画面 2台と使用で最強