MikeOfZen

MikeOfZen / affinity

Created November 21, 2019 07:28

[Select CPU core]

	start /affinity 1 program.exe

	this will run program.exe on the first CPU as "1" is the hex value of the affinity mask

	CPU3 CPU2 CPU1 CPU0 Bin Hex
	---- ---- ---- ---- --- ---
	OFF OFF OFF ON = 0001 = 1
	OFF OFF ON OFF = 0010 = 2
	OFF OFF ON ON = 0011 = 3
	OFF ON OFF OFF = 0100 = 4

MikeOfZen / catsdogs-transfer-learning-inception-tpu-tensorboard.ipynb

Last active January 21, 2021 18:04

TPU training error .ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

MikeOfZen / get_layers_above

Created November 5, 2019 19:06

[Cut TF model] use this to slice a keras model in half. useful for transfer learning in large models #tf #python

	def get_next_level(layer,model):
	def wrap_list(val):
	if type(val) is list:
	return val
	return [val]
	r=[]
	for output_t in wrap_list(layer.output):
	r+=[x for x in model.layers if output_t.name in [y.name for y in wrap_list(x.input)]]
	return r

MikeOfZen / tfds_split

Last active October 31, 2019 22:45

[tfds get dataset] get dataset and do split 3 way #tf #python #split #dataset #tfds

	DATA_DIR="/tmp"

	test_split, valid_split, train_split = tfds.Split.TRAIN.subsplit([10, 10, 80])

	test_set = tfds.load("cats_vs_dogs:4..",data_dir=DATA_DIR, split="train[:10%]", as_supervised=True)
	valid_set = tfds.load("cats_vs_dogs:4..",data_dir=DATA_DIR, split="train[10%:20%]", as_supervised=True)
	train_set = tfds.load("cats_vs_dogs:4..",data_dir=DATA_DIR, split="train[20%:]", as_supervised=True)

	#tfds.load is called multiple times for each slice, the 'train' split name is taken from the dataset documentation