def main(args):
batch_size = 128
ds_train, ds_test, info = load_data(batch_size)
image_shape = info.features["image"].shape
image_size = tf.reduce_prod(image_shape)
num_train_samples = info.splits["train"].num_examples
num_test_samples = info.splits["test"].num_examples
cnn = Cnn()
if "init_model" in args.cnn_mode:
cnn.create_model(batch_size=batch_size,
image_shape=image_shape,
feature_outputs=int(100))
if "train" in args.cnn_mode:
cnn.train(ds_train,
ds_test,
epochs=10,
steps_per_epoch=int(num_train_samples / batch_size))
if "save" in args.cnn_mode:
cnn.save()
if "load" in args.cnn_mode:
cnn.load_combined_model()
if "test" in args.cnn_mode:
cnn.test(ds_test)
gp = DeepKernelGP(ds_train,
num_train_samples,
image_size,
10,
cnn.feature_extractor,
num_inducing_points=100)
if "train" in args.gp_mode:
gp.train(10000)
if "test" in args.gp_mode:
gp.test(ds_test, image_size, batch_size, num_test_samples)
trainingLoss.append(trainLoss)
#prints if weights are unchanged
weights2 = []
unchangedWeights = 0
for param in cnn.parameters():
weights2.append(param.clone())
for i in zip(weights1, weights2):
if torch.equal(i[0], i[1]):
unchangedWeights += 1
if unchangedWeights > 0:
print(unchangedWeights, "of", len(weights1), "Weights Unchanged")
print("Testing")
testAcc, testLoss = cnn.test(testImgs, testOneHotVecs,
cfg.testBatchSize)
testingAccuracy.append(testAcc)
testingLoss.append(testLoss)
#plots accuracy
plt.plot(epochs,
trainingAccuracy,
label="Training Accuracy",
color="green")
plt.plot(epochs, testingAccuracy, label="Testing Accuracy", color="blue")
plt.plot(epochs, [1 / numSubjects] * cfg.epochs,
label="Blind Guessing Accuracy",
color="purple")
plt.xlabel("epochs")
plt.ylabel("Accuracy (Decimal)")
