from tensorflow.keras.models import load_model
from andi_funcs import import_tracks, package_tracks
import os
# Specify path to track data folder containing task2.txt
path = ''
"""
Import data
"""
# Import x data
tracks_1D, tracks_2D = import_tracks(path + '/task2.txt')
"""
1D
"""
model = load_model('../Task2_Classification/Models/1D.h5')
res_1D = model.predict(package_tracks(tracks_1D, dimensions=1, max_T=2001))
# max_T set to 2001 as competition data contains some tracks longer than 1000
"""
2D
"""
model = load_model('../Task2_Classification/Models/2D.h5')
res_2D = model.predict(package_tracks(tracks_2D, dimensions=2, max_T=2001))
"""
Save
import os
import sys
sys.path.append(os.path.dirname(os.path.realpath(__file__)) + '/../..')
from andi_funcs import TrackGeneratorClassification, import_tracks, import_labels, package_tracks
from models import classification_model_1d
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.models import load_model
import numpy as np
# Load validation data
tracks_val = package_tracks(
import_tracks('../../Datasets/Validation/task2.txt')[0],
dimensions=1,
max_T=1001)
classes_val = import_labels('../../Datasets/Validation/ref2.txt')[0]
tracks_test = package_tracks(import_tracks('../../Datasets/Test/task2.txt')[0],
dimensions=1,
max_T=1001)
# Run model
model = classification_model_1d()
model.compile(optimizer=Adam(learning_rate=0.001),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.summary()
history = model.fit(TrackGeneratorClassification(batches=200,
batch_size=32,
dimensions=1,