Ph.D. Course (6) 썸네일형 리스트형 [etc.] tf.compat.v1.saved_model.load [reference] https://www.tensorflow.org/api_docs/python/tf/compat/v1/saved_model/load [etc.] Tensorflow 2.x : contrib issue Normally, you can use Tensorflow 1.x code in Tensorflow 2.x with tensorflow.compat.v1.x. But It doesn't working with contrib. So you need to use tf.keras when you try to normalize or etc. in tensorflow2.x. ex) r1 = rf.keras.regularizers.L1(l1=1-e4) r2 = rf.keras.regularizers.L2(l2=1-e4) [etc] The option verbose in Tensorflow2.0 fit and evaluate function verbose: 'auto', 0, 1, or 2. Verbosity mode. 0 = silent, 1 = progress bar, 2 = one line per epoch. 'auto' defaults to 1 for most cases, but 2 when used with ParameterServerStrategy. Note that the progress bar is not particularly useful when logged to a file, so verbose=2 is recommended when not running interactively (eg, in a production environment). [reference] https://keras.io/api/models/model.. [NVIDIA NANO] Adding Swap Memory git clone https://github.com/JetsonHacksNano/installSwapfile cd installSwapfile ./installSwapfile.sh then reboot the board If you got the error sudo swapoff -a [reference] https://jetsonhacks.com/2019/04/14/jetson-nano-use-more-memory/ [NVIDA NANO] Jetpack 4.6.2 Tensorflow setup Follow commans below sudo apt-get update sudo apt-get install libhdf5-serial-dev hdf5-tools libhdf5-dev zlib1g-dev zip libjpeg8-dev liblapack-dev libblas-dev gfortran sudo pip3 install -U pip testresources setuptools sudo ln -s /usr/include/locale.h /usr/include/xlocale.h sudo pip3 install -U numpy==1.19.4 future mock keras_preprocessing keras_applications gast==0.2.1 protobuf pybind11 cython pk.. [NVIDIA NANO] nvcc error If you got the error like image below sudo vi ~/.bashrc Insert the code at the bottom export PATH=/usr/local/cuda-10.2/bin${PATH:+:${PATH}} export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}} Then save the file and execute it with source(command) source ~/.bashrc 이전 1 다음
