sayakpaul

# Calculate batch size
batch_size_per_replica = 32
batch_size = batch_size_per_replica * strategy.num_replicas_in_sync

sayakpaul

import tensorflow as tf
import os
os.environ["TF_DETERMINISTIC_OPS"] = "1"

sayakpaul

SEED = 666
import tensorflow as tf
tf.random.set_seed(SEED)
import numpy as np
np.random.seed(SEED)

sayakpaul

sweep_config = {
    "method": "random", #grid, random
    "metric": {
      "name": "accuracy",
      "goal": "maximize"   
    },
    "parameters": {
        "epochs": {
            "values": [10, 15, 20]
        },

sayakpaul

# Set up model checkpoint callback
filepath = wandb.run.dir + "/{epoch:02d}-{val_accuracy:.2f}.ckpt"
checkpoint = tf.keras.callbacks.ModelCheckpoint(filepath,
    monitor="val_accuracy", 
    verbose=1, 
    save_best_only=True, mode="max")

sayakpaul

{
  'Cargo': 1,
  'Military': 2,
  'Carrier': 3,
  'Cruise': 4,
  'Tankers': 5
}

sayakpaul

├── train
│   ├── images [8932 entries]
│   └── train.csv
└── test_ApKoW4T.csv

sayakpaul

policy = tf.keras.mixed_precision.experimental.Policy('mixed_float16')

model = tf.keras.models.Sequential(
   tf.keras.layers.Input((100,)),
   tf.keras.layers.Dense(10, dtype=policy),
   tf.keras.layers.Dense(10, dtype=policy),
   # Softmax should be done in float32 for numeric stability.
   tf.keras.layers.Activation('Softmax', dtype='float32')

)

sayakpaul

from tensorflow.keras import backend as K
K.clear_session()

sayakpaul

policy = tf.keras.mixed_precision.experimental.Policy('mixed_float16')

model = tf.keras.models.Sequential(
  tf.keras.layers.Input((100,)),
  tf.keras.layers.Dense(10, dtype=policy),
  # Softmax should be done in float32 for numeric stability.
  tf.keras.layers.Activation('Softmax', dtype='float32')
)