wtf scripts to check tensorflow setup
parent
ac33fbe4ff
commit
aaa0091db8
|
@ -0,0 +1,25 @@
|
|||
#!/bin/bash
|
||||
# wut-tf
|
||||
#
|
||||
# Starts worker client.
|
||||
#
|
||||
# Usage:
|
||||
# wut-tf
|
||||
# Example:
|
||||
# wut-tf
|
||||
#
|
||||
# Note:
|
||||
# Each node needs a unique index number.
|
||||
#
|
||||
# NOTE!
|
||||
# This generates the node number based off the hostname.
|
||||
# The hosts are ml0 through ml5.
|
||||
|
||||
HOSTNUM=`hostname | sed -e 's/ml//g'`
|
||||
|
||||
#export TF_CONFIG='{"cluster": {"worker": [ "ml0-int:2222", "ml1-int:2222", "ml2-int:2222", "ml3-int:2222", "ml4-int:2222", "ml5-int:2222"]}, "task": {"index": '$HOSTNUM', "type": "worker"}}'
|
||||
export TF_CONFIG='{"cluster": {"worker": [ "ml1-int:2222", "ml2-int:2222", "ml3-int:2222", "ml4-int:2222", "ml5-int:2222"]}}'
|
||||
|
||||
echo $TF_CONFIG
|
||||
python3 wut-tf.py
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
#!/usr/bin/env python3
|
||||
#
|
||||
# wut-tf.py
|
||||
#
|
||||
# https://spacecruft.org/spacecruft/satnogs-wut
|
||||
#
|
||||
# Distributed Learning
|
||||
|
||||
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||
from __future__ import print_function
|
||||
import os
|
||||
import json
|
||||
import numpy as np
|
||||
import datetime
|
||||
import tensorflow as tf
|
||||
import tensorflow.python.keras
|
||||
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
|
||||
from tensorflow.python.keras import optimizers
|
||||
from tensorflow.python.keras import Sequential
|
||||
from tensorflow.python.keras.layers import Activation, Dropout, Flatten, Dense
|
||||
from tensorflow.python.keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D
|
||||
from tensorflow.python.keras.layers import Input, concatenate
|
||||
from tensorflow.python.keras.models import load_model
|
||||
from tensorflow.python.keras.models import Model
|
||||
from tensorflow.python.keras.preprocessing import image
|
||||
from tensorflow.python.keras.preprocessing.image import img_to_array
|
||||
from tensorflow.python.keras.preprocessing.image import ImageDataGenerator
|
||||
from tensorflow.python.keras.preprocessing.image import load_img
|
||||
os.environ["TF_CONFIG"] = json.dumps({
|
||||
"cluster": {
|
||||
"worker": [ "ml1-int:2222", "ml2-int:2222", "ml3-int:2222", "ml4-int:2222", "ml5-int:2222" ]
|
||||
}#,
|
||||
#"task": {"type": "worker", "index": 0 },
|
||||
})
|
||||
print("Tensorflow Version: ", tf.__version__)
|
||||
print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
|
||||
print("Num CPUs Available: ", len(tf.config.experimental.list_physical_devices('CPU')))
|
||||
print(tf.config.experimental.list_physical_devices())
|
||||
#with tf.device("GPU:0"):
|
||||
# tf.ones(()) # Make sure we can run on GPU
|
||||
print("XLA_FLAGS='{}'".format(os.getenv("XLA_FLAGS")))
|
||||
print(os.getenv("XLA_FLAGS"))
|
||||
tf.keras.backend.clear_session()
|
||||
IMG_HEIGHT = 416
|
||||
IMG_WIDTH= 804
|
||||
batch_size = 32
|
||||
epochs = 4
|
||||
BUFFER_SIZE = 10000
|
||||
NUM_WORKERS = 6
|
||||
GLOBAL_BATCH_SIZE = 64 * NUM_WORKERS
|
||||
#strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy()
|
||||
#strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy(
|
||||
# tf.distribute.experimental.CollectiveCommunication.RING)
|
||||
AUTOTUNE = tf.data.experimental.AUTOTUNE
|
||||
NUM_TOTAL_IMAGES=100
|
||||
tf.config.optimizer.set_jit(True)
|
||||
#tf.summary.trace_on(profiler=True)
|
||||
#tf.summary.trace_export(name=trace-export,profiler_outdir=logs)
|
||||
options = tf.data.Options()
|
||||
|
Loading…
Reference in New Issue