s434686/ium_z434686
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update 'train.py'

Browse Source
This commit is contained in:
Patryk Gałka 2023-05-11 21:24:52 +02:00
parent 02ca9f72b1
commit 457379e45a
1 changed files with 33 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
train.py
View File

@ -1,31 +1,44 @@
import pandas import pandas
import os import os
from sacred import Experiment
from sacred.observers import MongoObserver
from sacred.observers import FileStorageObserver
from keras.applications.densenet import layers from keras.applications.densenet import layers
from sklearn.model_selection import train_test_split
import tensorflow import tensorflow
EPOCHS = int(os.environ['EPOCHS']) exint = Experiment('z-s434686-training')
train_data_x = pandas.read_csv('./X_train.csv') exint.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017',
db_name='sacred'))
exint.observers.append(FileStorageObserver('my_runs'))
@exint.config
def my_config():
EPOCHS = int(os.environ['EPOCHS'])
train_data_x = exint.open_resource('./X_train.csv', 'r')
games_all = train_data_x.copy()
games_predict = train_data_x.pop('User_Score')
normalize = layers.Normalization()
_run.info["epochs"] = EPOCHS
games_all = train_data_x.copy() @exint.main
games_predict = train_data_x.pop('User_Score') def my_main(EPOCHS, games_all, games_predict,normalize):
normalize = layers.Normalization() _run.info["prepare_message_ts"] = str(datetime.now())
normalize.adapt(games_all) normalize.adapt(games_all)
norm_games_model = tensorflow.keras.Sequential([
normalize,
layers.Dense(64),
layers.Dense(1)
])
norm_games_model.compile(
loss=tensorflow.keras.losses.MeanSquaredError(),
optimizer=tensorflow.keras.optimizers.Adam())
norm_games_model = tensorflow.keras.Sequential([ norm_games_model.fit(games_all, games_predict, epochs=EPOCHS)
normalize,
layers.Dense(64),
layers.Dense(1)
])
norm_games_model.compile( norm_games_model.save('test')
loss=tensorflow.keras.losses.MeanSquaredError(), print(f'done:')
optimizer=tensorflow.keras.optimizers.Adam())
norm_games_model.fit(games_all, games_predict, epochs=EPOCHS) exint.run()
exint.add_artifact("test")
norm_games_model.save('test') exint.add_source_file('train.py')