def reset_eddl_net_params(net, weight='zeros', bias='zeros'):
layers = net.layers
for l in layers:
name = l.name
params = l.params
w_np = None
b_np = None
for index, p in enumerate(params):
if index == 0:
if weight == 'zeros':
w_np = np.zeros_like(p.getdata())
else:
w_np = np.ones_like(p.getdata())
if index == 1:
if bias == 'zeros':
b_np = np.zeros_like(p.getdata())
else:
b_np = np.ones_like(p.getdata())
w_np_t = Tensor.fromarray(w_np)
b_np_t = Tensor.fromarray(b_np)
# Update of the parameters
l.update_weights(w_np_t, b_np_t)
eddl.distributeParams(l)
def main(args):
if not os.path.isfile(args.input):
raise RuntimeError("input file '%s' not found" % args.input)
eddl.download_mnist()
print("importing net from", args.input)
net = eddl.import_net_from_onnx_file(args.input)
print("input.shape:", net.layers[0].input.shape)
print("output size =", len(net.lout))
eddl.build(
net,
eddl.rmsprop(0.01),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem),
False # do not initialize weights to random values
)
net.resize(args.batch_size) # resize manually since we don't use "fit"
eddl.summary(net)
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
x_test.div_(255.0)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def eddl_load_data_cifar(path=None,
download=False,
load_subset=False,
subset_size=4096):
"""
:param path: Path to CIFAR10 dataset
:param download: Default-False - download the dataset to current directory.
:param load_subset: Default-False - use subset of the dataset for testing purpose.
:param subset_size: Default-4096, the test size is subset_size/4.
:return: two tuples of (x_train, y_train), (x_test, y_test) .
"""
(x_train, y_train), (x_test, y_test) = resnet.load_cifar(path, download)
if load_subset:
x_subset_train = Tensor([subset_size, 3, 32, 32])
y_subset_train = Tensor([subset_size, 10])
eddl.next_batch([x_train], [x_subset_train])
eddl.next_batch([y_train], [y_subset_train])
x_subset_test = Tensor([math.ceil(subset_size / 4), 3, 32, 32])
y_subset_test = Tensor([math.ceil(subset_size / 4), 10])
eddl.next_batch([x_test], [x_subset_test])
eddl.next_batch([y_test], [y_subset_test])
return (x_subset_train, y_subset_train), (x_subset_test, y_subset_test)
return (x_train, y_train), (x_test, y_test)
def main(args):
img = ecvl.ImRead(args.in_img)
augs = ecvl.SequentialAugmentationContainer([
ecvl.AugRotate([-5, 5]),
ecvl.AugMirror(.5),
ecvl.AugFlip(.5),
ecvl.AugGammaContrast([3, 5]),
ecvl.AugAdditiveLaplaceNoise([0, 0.2 * 255]),
ecvl.AugCoarseDropout([0, 0.55], [0.02, 0.1], 0.5),
ecvl.AugAdditivePoissonNoise([0, 40]),
ecvl.AugResizeDim([500, 500]),
])
ecvl.AugmentationParam.SetSeed(0)
augs.Apply(img)
print("Executing ImageToTensor")
t = ecvl.ImageToTensor(img)
t.div_(128)
t.mult_(128)
print("Executing TensorToImage")
img = ecvl.TensorToImage(t)
print("Executing TensorToView")
ecvl.TensorToView(t)
_ = ecvl.AugmentationFactory.create(AUG_TXT)
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugRotate([-5, 5]),
ecvl.AugAdditiveLaplaceNoise([0, 0.2 * 255]),
ecvl.AugCoarseDropout([0, 0.55], [0.02, 0.1], 0),
ecvl.AugAdditivePoissonNoise([0, 40]),
ecvl.AugResizeDim([30, 30]),
])
test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim([30, 30]),
])
ds_augs = ecvl.DatasetAugmentations([training_augs, None, test_augs])
batch_size = 64
print("Creating a DLDataset")
d = ecvl.DLDataset(args.in_ds, batch_size, ds_augs, ecvl.ColorType.GRAY)
print("Create x and y")
x = Tensor(
[batch_size, d.n_channels_, d.resize_dims_[0], d.resize_dims_[1]])
y = Tensor([batch_size, len(d.classes_)])
# Load a batch of d.batch_size_ images into x and corresponding labels
# into y. Images are resized to the dimensions specified in the
# augmentations chain
print("Executing LoadBatch on training set")
d.LoadBatch(x, y)
# Change colortype and channels
img = ecvl.TensorToImage(x)
img.colortype_ = ecvl.ColorType.GRAY
img.channels_ = "xyc"
# Switch to Test split and load a batch of images
print("Executing LoadBatch on test set")
d.SetSplit(ecvl.SplitType.test)
d.LoadBatch(x, y)
def load_cifar(path=None, download=False):
if path is None:
path = "./"
if download:
eddl.download_cifar10()
print(path)
try:
x_train = Tensor.load(path + "/cifar_trX.bin")
y_train = Tensor.load(path + "/cifar_trY.bin")
except:
print(
"Fail to load the train set, make sure you supply the correct path"
)
exit()
try:
x_test = Tensor.load(path + "/cifar_tsX.bin")
y_test = Tensor.load(path + "/cifar_tsY.bin")
except:
print(
"Fail to load the test set, make sure you supply the correct path")
exit()
x_train.div_(255.0)
x_test.div_(255.0)
return (x_train, y_train), (x_test, y_test)
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([784])
layer = in_
layer = eddl.Reshape(layer, [1, 28, 28])
layer = eddl.RandomCropScale(layer, [0.9, 1.0])
layer = eddl.Reshape(layer, [-1])
layer = eddl.ReLu(
eddl.GaussianNoise(
eddl.BatchNormalization(eddl.Dense(layer, 1024), True), 0.3))
layer = eddl.ReLu(
eddl.GaussianNoise(
eddl.BatchNormalization(eddl.Dense(layer, 1024), True), 0.3))
layer = eddl.ReLu(
eddl.GaussianNoise(
eddl.BatchNormalization(eddl.Dense(layer, 1024), True), 0.3))
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net, eddl.sgd(0.01, 0.9), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
if args.small:
x_train = x_train.select([":6000"])
y_train = y_train.select([":6000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
x_train.div_(255.0)
x_test.div_(255.0)
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
# LR annealing
if args.epochs < 4:
return
eddl.setlr(net, [0.005, 0.9])
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs // 2)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
eddl.setlr(net, [0.001, 0.9])
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs // 2)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
eddl.setlr(net, [0.0001, 0.9])
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs // 4)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def read_input(filename, split_ratio=0.7):
data = np.load(filename)['d']
# shuffle data
sel_index = np.arange(data.shape[0])
np.random.shuffle(sel_index)
shuffled_data = data[sel_index]
shuffled_data = np.c_[shuffled_data, np.zeros(shuffled_data.shape[0])] # Add column for two class labels
shuffled_data[:,4][shuffled_data[:,3] == 0] = 1. ## [1] -> [1 0], [0]-->[0 1]
shuffled_data[:,[3,4]] = shuffled_data[:,[4,3]] ## Swap last two columns [1] --> [0 1], [0] --> [1 0]
# Split train test
n_train = int (shuffled_data.shape[0] * split_ratio )
train = shuffled_data[0:n_train]
test = shuffled_data[n_train:]
x_trn = train[:,:3]
y_trn = train[:,3:]
x_test = test[:,:3]
y_test = test[:,3:]
# Tensor creation
x_train_t = Tensor.fromarray(x_trn.astype(np.float32))
y_train_t = Tensor.fromarray(y_trn.astype(np.float32))
x_test_t = Tensor.fromarray(x_test.astype(np.float32))
y_test_t = Tensor.fromarray(y_test.astype(np.float32))
return x_train_t, y_train_t, x_test_t, y_test_t
def main(args):
eddl.download_cifar10()
num_classes = 10
in_ = eddl.Input([3, 32, 32])
layer = in_
layer = eddl.RandomCropScale(layer, [0.8, 1.0])
layer = eddl.RandomHorizontalFlip(layer)
layer = eddl.ReLu(BG(eddl.Conv(layer, 64, [3, 3], [1, 1], "same", False)))
layer = eddl.Pad(layer, [0, 1, 1, 0])
for i in range(3):
layer = ResBlock(layer, 64, 0, i == 0)
for i in range(4):
layer = ResBlock(layer, 128, i == 0)
for i in range(6):
layer = ResBlock(layer, 256, i == 0)
for i in range(3):
layer = ResBlock(layer, 512, i == 0)
layer = eddl.MaxPool(layer, [4, 4])
layer = eddl.Reshape(layer, [-1])
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net, eddl.sgd(0.001, 0.9), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
eddl.plot(net, "model.pdf", "TB")
x_train = Tensor.load("cifar_trX.bin")
y_train = Tensor.load("cifar_trY.bin")
x_train.div_(255.0)
x_test = Tensor.load("cifar_tsX.bin")
y_test = Tensor.load("cifar_tsY.bin")
x_test.div_(255.0)
if args.small:
# this is slow, make it really small
x_train = x_train.select([":500"])
y_train = y_train.select([":500"])
x_test = x_test.select([":100"])
y_test = y_test.select([":100"])
lr = 0.01
for j in range(3):
lr /= 10.0
eddl.setlr(net, [lr, 0.9])
for i in range(args.epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def update_eddl_net_params(keras_params_d, net, include_top=True):
if include_top:
layers_l = [(l.name, l.params[0].getShape(), l.params[1].getShape(), l)
for l in net.layers
if 'conv' in l.name or 'dense' in l.name]
keras_l = [k for k in sorted(keras_params_d.keys())]
else:
layers_l = [(l.name, l.params[0].getShape(), l.params[1].getShape(), l)
for l in net.layers if 'conv' in l.name]
keras_l = [k for k in sorted(keras_params_d.keys()) if 'conv' in k]
for index, k in enumerate(keras_l):
w_np = keras_params_d[k]['w']
b_np = keras_params_d[k]['b']
l = layers_l[index]
# Transpose to match eddl tensor shape for convolutional layer
if 'conv' in l[0]:
print("Conv before transpose", w_np.shape)
w_np = np.transpose(w_np, (3, 2, 0, 1))
# dense layer immediatly after the flattening. he order of weight is different because previous feature maps are channel last in Keras
# but EDDL expects as they are channel first
if l[0] == 'dense1':
x = keras_params_d[keras_l[index - 1]]['w'].shape[0]
y = keras_params_d[keras_l[index - 1]]['w'].shape[1]
n_ch = keras_params_d[keras_l[index - 1]]['w'].shape[3]
print('After flattening. #Channels of previous layers is: %d' %
n_ch)
# Converting w_np as the previous feature maps was channel first
outputs = w_np.shape[1]
print(w_np.shape)
w_np_ch_f = np.zeros_like(w_np)
for o in range(outputs):
for offset in range(n_ch):
lll = w_np[offset::n_ch, o].shape[0]
w_np_ch_f[offset:offset + lll, o] = w_np[offset::n_ch, o]
# Shapes check
eddl_w_shape = np.array(l[1])
eddl_b_shape = np.array(l[2])
print(l[0], k)
print(eddl_w_shape, w_np.shape)
print(eddl_b_shape, b_np.shape)
# converting numpy arrays to tensor
w_np_t = Tensor.fromarray(w_np)
b_np_t = Tensor.fromarray(b_np)
# Update of the parameters
l[3].update_weights(w_np_t, b_np_t)
eddl.distributeParams(l[3])
def main(args):
eddl.download_cifar10()
num_classes = 10
in_ = eddl.Input([3, 32, 32])
layer = in_
layer = eddl.MaxPool(eddl.ReLu(Normalization(
eddl.Conv(layer, 32, [3, 3], [1, 1])
)), [2, 2])
layer = eddl.MaxPool(eddl.ReLu(Normalization(
eddl.Conv(layer, 64, [3, 3], [1, 1])
)), [2, 2])
layer = eddl.MaxPool(eddl.ReLu(Normalization(
eddl.Conv(layer, 128, [3, 3], [1, 1])
)), [2, 2])
layer = eddl.MaxPool(eddl.ReLu(Normalization(
eddl.Conv(layer, 256, [3, 3], [1, 1])
)), [2, 2])
layer = eddl.GlobalMaxPool(layer)
layer = eddl.Flatten(layer)
layer = eddl.Activation(eddl.Dense(layer, 128), "relu")
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net,
eddl.adam(0.001),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("cifar_trX.bin")
y_train = Tensor.load("cifar_trY.bin")
x_train.div_(255.0)
x_test = Tensor.load("cifar_tsX.bin")
y_test = Tensor.load("cifar_tsY.bin")
x_test.div_(255.0)
if args.small:
x_train = x_train.select([":5000"])
y_train = y_train.select([":5000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
for i in range(args.epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def main(args):
eddl.download_cifar10()
num_classes = 10
in_ = eddl.Input([3, 32, 32])
layer = in_
layer = eddl.RandomCropScale(layer, [0.8, 1.0])
layer = eddl.RandomFlip(layer, 1)
layer = eddl.ReLu(BG(eddl.Conv(layer, 64, [3, 3], [1, 1])))
layer = eddl.Pad(layer, [0, 1, 1, 0])
layer = ResBlock(layer, 64, 2, True)
layer = ResBlock(layer, 64, 2, False)
layer = ResBlock(layer, 128, 2, True)
layer = ResBlock(layer, 128, 2, False)
layer = ResBlock(layer, 256, 2, True)
layer = ResBlock(layer, 256, 2, False)
layer = ResBlock(layer, 256, 2, True)
layer = ResBlock(layer, 256, 2, False)
layer = eddl.Reshape(layer, [-1])
layer = eddl.ReLu(BG(eddl.Dense(layer, 512)))
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net,
eddl.sgd(0.01, 0.9),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
eddl.plot(net, "model.pdf", "TB")
x_train = Tensor.load("cifar_trX.bin")
y_train = Tensor.load("cifar_trY.bin")
x_train.div_(255.0)
x_test = Tensor.load("cifar_tsX.bin")
y_test = Tensor.load("cifar_tsY.bin")
x_test.div_(255.0)
if args.small:
x_train = x_train.select([":5000"])
y_train = y_train.select([":5000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
for i in range(args.epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def test_py_metric():
shape = [8, 10]
a = np.random.random(shape).astype(np.float32)
b = np.random.random(shape).astype(np.float32)
t, y = Tensor.fromarray(a), Tensor.fromarray(b)
v = MSEMetric().value(t, y)
exp_v = eddl.getMetric("mse").value(t, y)
assert v == pytest.approx(exp_v)
v = CategoricalAccuracy().value(t, y)
exp_v = eddl.getMetric("categorical_accuracy").value(t, y)
assert v == pytest.approx(exp_v)
def main(args):
eddl.download_cifar10()
num_classes = 10
in_ = eddl.Input([3, 32, 32])
layer = in_
layer = eddl.RandomCropScale(layer, [0.8, 1.0])
layer = eddl.RandomFlip(layer, 1)
layer = eddl.RandomCutout(layer, [0.1, 0.3], [0.1, 0.3])
layer = eddl.MaxPool(Block3_2(layer, 64))
layer = eddl.MaxPool(Block3_2(layer, 128))
layer = eddl.MaxPool(Block1(Block3_2(layer, 256), 256))
layer = eddl.MaxPool(Block1(Block3_2(layer, 512), 512))
layer = eddl.MaxPool(Block1(Block3_2(layer, 512), 512))
layer = eddl.Reshape(layer, [-1])
layer = eddl.Activation(eddl.Dense(layer, 512), "relu")
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net,
eddl.sgd(0.001, 0.9),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.setlogfile(net, "vgg16")
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("cifar_trX.bin")
y_train = Tensor.load("cifar_trY.bin")
x_train.div_(255.0)
x_test = Tensor.load("cifar_tsX.bin")
y_test = Tensor.load("cifar_tsY.bin")
x_test.div_(255.0)
if args.small:
x_train = x_train.select([":5000"])
y_train = y_train.select([":5000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
for i in range(args.epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def main(args):
eddl.download_mnist()
in_ = eddl.Input([784])
target = eddl.Reshape(in_, [1, 28, 28])
layer = in_
layer = eddl.Reshape(layer, [1, 28, 28])
layer = eddl.ReLu(eddl.Conv(layer, 8, [3, 3]))
layer = eddl.ReLu(eddl.Conv(layer, 16, [3, 3]))
layer = eddl.ReLu(eddl.Conv(layer, 8, [3, 3]))
out = eddl.Sigmoid(eddl.Conv(layer, 1, [3, 3]))
net = eddl.Model([in_], [])
eddl.build(
net,
eddl.adam(0.001),
[],
[],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
x_train = Tensor.load("mnist_trX.bin")
if args.small:
x_train = x_train.select([":6000"])
x_train.div_(255.0)
mse = eddl.newloss(mse_loss, [out, target], "mse_loss")
dicei = eddl.newloss(dice_loss_img, [out, target], "dice_loss_img")
dicep = eddl.newloss(dice_loss_pixel, [out, target], "dice_loss_pixel")
batch = Tensor([args.batch_size, 784])
num_batches = x_train.shape[0] // args.batch_size
for i in range(args.epochs):
print("Epoch %d/%d (%d batches)" % (i + 1, args.epochs, num_batches))
diceploss = 0.0
diceiloss = 0.0
mseloss = 0
for j in range(num_batches):
print("Batch %d " % j, end="", flush=True)
eddl.next_batch([x_train], [batch])
eddl.zeroGrads(net)
eddl.forward(net, [batch])
diceploss += eddl.compute_loss(dicep) / args.batch_size
print("diceploss = %.6f " % (diceploss / (j + 1)), end="")
diceiloss += eddl.compute_loss(dicei) / args.batch_size
print("diceiloss = %.6f " % (diceiloss / (j + 1)), end="")
mseloss += eddl.compute_loss(mse) / args.batch_size
print("mseloss = %.6f\r" % (mseloss / (j + 1)), end="")
eddl.optimize(dicep)
eddl.update(net)
print()
print("All done")
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([784])
layer = in_
layer = eddl.Reshape(layer, [1, 784]) # image as a 1D signal with depth 1
layer = eddl.MaxPool1D(eddl.ReLu(eddl.Conv1D(layer, 16, [3], [1])), [4],
[4])
layer = eddl.MaxPool1D(
eddl.ReLu(eddl.Conv1D(layer, 32, [3], [1])),
[4],
[4],
)
layer = eddl.MaxPool1D(
eddl.ReLu(eddl.Conv1D(layer, 64, [3], [1])),
[4],
[4],
)
layer = eddl.MaxPool1D(
eddl.ReLu(eddl.Conv1D(layer, 64, [3], [1])),
[4],
[4],
)
layer = eddl.Reshape(layer, [-1])
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net, eddl.rmsprop(0.01), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
if args.small:
x_train = x_train.select([":6000"])
y_train = y_train.select([":6000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
x_train.div_(255.0)
x_test.div_(255.0)
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([784])
layer = in_
layer = eddl.Activation(eddl.Dense(layer, 1024), "relu")
layer = eddl.Activation(eddl.Dense(layer, 1024), "relu")
layer = eddl.Activation(eddl.Dense(layer, 1024), "relu")
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
acc = CategoricalAccuracy()
net.build(
eddl.sgd(0.01, 0.9),
[eddl.getLoss("soft_cross_entropy")],
[acc],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
# y_test = Tensor.load("mnist_tsY.bin")
x_train.div_(255.0)
x_test.div_(255.0)
num_samples = x_train.shape[0]
num_batches = num_samples // args.batch_size
test_samples = x_test.shape[0]
test_batches = test_samples // args.batch_size
eddl.set_mode(net, TRMODE)
for i in range(args.epochs):
for j in range(num_batches):
print("Epoch %d/%d (batch %d/%d)" %
(i + 1, args.epochs, j + 1, num_batches))
indices = np.random.randint(0, num_samples, args.batch_size)
eddl.train_batch(net, [x_train], [y_train], indices)
for j in range(test_batches):
print("Epoch %d/%d (batch %d/%d)" %
(i + 1, args.epochs, j + 1, test_batches))
indices = np.random.randint(0, num_samples, args.batch_size)
eddl.eval_batch(net, [x_train], [y_train], indices)
print("All done")
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([784])
layer = in_
layer = eddl.Reshape(layer, [-1])
layer = eddl.ReLu(eddl.Dense(layer, 1024))
layer = eddl.BatchNormalization(layer, True)
layer = eddl.ReLu(eddl.Dense(layer, 1024))
layer = eddl.BatchNormalization(layer, True)
layer = eddl.ReLu(eddl.Dense(layer, 1024))
layer = eddl.BatchNormalization(layer, True)
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net,
eddl.rmsprop(0.01),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem),
True # initialize weights to random values
)
eddl.summary(net)
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
if args.small:
x_train = x_train.select([":6000"])
y_train = y_train.select([":6000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
x_train.div_(255.0)
x_test.div_(255.0)
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
eddl.save_net_to_onnx_file(net, args.output)
print("saved net to", args.output)
print("All done")
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([28])
layer = in_
layer = eddl.LeakyReLu(eddl.Dense(layer, 32))
layer = eddl.L2(eddl.LSTM(layer, 128), 0.001)
ls = layer
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net, eddl.rmsprop(0.001), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
if args.small:
x_train = x_train.select([":6000"])
y_train = y_train.select([":6000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
x_train.reshape_([x_train.shape[0], 28, 28])
x_test.reshape_([x_test.shape[0], 28, 28])
y_train.reshape_([y_train.shape[0], 1, 10])
y_test.reshape_([y_test.shape[0], 1, 10])
x_train.div_(255.0)
x_test.div_(255.0)
for i in range(args.epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
ls_in = eddl.getInput(ls)
ls_in.info()
ls_out = eddl.getOutput(ls)
ls_out.info()
print("All done")
def main(args):
eddl.download_mnist()
in_ = eddl.Input([784])
layer = in_
layer = eddl.Activation(eddl.Dense(layer, 256), "relu")
layer = eddl.Activation(eddl.Dense(layer, 128), "relu")
layer = eddl.Activation(eddl.Dense(layer, 64), "relu")
layer = eddl.Activation(eddl.Dense(layer, 128), "relu")
layer = eddl.Activation(eddl.Dense(layer, 256), "relu")
out = eddl.Dense(layer, 784)
net = eddl.Model([in_], [out])
mse_loss = MSELoss()
mse_metric = MSEMetric()
net.build(
eddl.sgd(0.001, 0.9), [mse_loss], [mse_metric],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
x_train.div_(255.0)
eddl.fit(net, [x_train], [x_train], args.batch_size, args.epochs)
print("All done")
def main(args):
in_channels = 3
in_height = 224
in_width = 224
print("Importing ONNX model")
net = eddl.import_net_from_onnx_file(args.model_fn,
[in_channels, in_height, in_width])
# Add a softmax layer to get probabilities directly from the model
input_ = net.lin[0] # getLayer(net,"input_layer_name")
output = net.lout[0] # getLayer(net,"output_layer_name")
new_output = eddl.Softmax(output)
net = eddl.Model([input_], [new_output])
eddl.build(
net,
eddl.adam(0.001), # not used for prediction
["softmax_cross_entropy"], # not used for prediction
["categorical_accuracy"], # not used for prediction
eddl.CS_GPU() if args.gpu else eddl.CS_CPU(),
False # Disable model initialization, we want to use the ONNX weights
)
eddl.summary(net)
image = Tensor.load(args.img_fn)
image_preprocessed = preprocess_input_resnet34(image,
[in_height, in_width])
outputs = eddl.predict(net, [image_preprocessed])
print("Reading class names...")
with open(args.classes_fn, "rt") as f:
class_names = [_.strip() for _ in f]
print("Top 5 predictions:")
print(eddl.get_topk_predictions(outputs[0], class_names, 5))
def main(args):
eddl.download_mnist()
in_ = eddl.Input([784])
layer = in_
layer = eddl.Activation(eddl.Dense(layer, 256), "relu")
layer = eddl.Activation(eddl.Dense(layer, 128), "relu")
layer = eddl.Activation(eddl.Dense(layer, 64), "relu")
layer = eddl.Activation(eddl.Dense(layer, 128), "relu")
layer = eddl.Activation(eddl.Dense(layer, 256), "relu")
out = eddl.Dense(layer, 784)
net = eddl.Model([in_], [out])
eddl.build(
net, eddl.sgd(0.001, 0.9), ["mean_squared_error"],
["mean_squared_error"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
if args.small:
x_train = x_train.select([":6000"])
x_train.div_(255.0)
eddl.fit(net, [x_train], [x_train], args.batch_size, args.epochs)
tout = eddl.predict(net, [x_train])
tout[0].info()
print("All done")
def main(args):
if not os.path.isfile(args.input):
raise RuntimeError("input file '%s' not found" % args.input)
eddl.download_mnist()
net = eddl.import_net_from_onnx_file(args.input)
eddl.build(
net,
eddl.rmsprop(0.01),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem),
False # do not initialize weights to random values
)
net.resize(args.batch_size) # resize manually since we don't use "fit"
eddl.summary(net)
x_test = Tensor.load("mnist_tsX.bin")
x_test.div_(255.0)
sys.stderr.write("forward...\n")
eddl.forward(net, [x_test])
sys.stderr.write("forward done\n")
sys.stderr.write("lout: %r\n" % (net.lout, ))
out = eddl.getOut(net)
sys.stderr.write("getOut done\n")
sys.stderr.write("out: %r\n" % (out, ))
print("All done")
def test_py_loss():
shape = [8, 10]
a = np.random.random(shape).astype(np.float32)
b = np.random.random(shape).astype(np.float32)
t, y = Tensor.fromarray(a), Tensor.fromarray(b)
z = Tensor(shape)
exp_z = Tensor(shape)
py_mse_loss = MSELoss()
mse_loss = eddl.getLoss("mse")
mse_loss.delta(t, y, exp_z)
py_mse_loss.delta(t, y, z)
c = np.array(z, copy=False)
exp_c = np.array(exp_z, copy=False)
assert np.array_equal(c, exp_c)
v = py_mse_loss.value(t, y)
exp_v = mse_loss.value(t, y)
assert v == pytest.approx(exp_v)
def preprocess_input_resnet34(input_, target_size):
mean_vec = Tensor.fromarray(
np.array([0.485, 0.456, 0.406], dtype=np.float32), input_.device)
std_vec = Tensor.fromarray(
np.array([0.229, 0.224, 0.225], dtype=np.float32), input_.device)
if input_.ndim not in {3, 4}:
raise RuntimeError("Input tensor must be 3D or 4D")
if input_.ndim == 3:
input_.unsqueeze_(0) # convert to 4D
new_input = input_.scale(target_size) # (height, width)
# Normalization [0..1]
new_input.mult_(1 / 255.0)
# Standardization: (X - mean) / std
mean = Tensor.broadcast(mean_vec, new_input)
std = Tensor.broadcast(std_vec, new_input)
new_input.sub_(mean)
new_input.div_(std)
return new_input
def main(args):
eddl.download_imdb_2000()
epochs = 2 if args.small else 10
length = 250
embdim = 33
vocsize = 2000
in_ = eddl.Input([1]) # 1 word
layer = in_
layer = eddl.RandomUniform(eddl.Embedding(layer, vocsize, 1, embdim),
-0.05, 0.05)
layer = eddl.GRU(layer, 37)
layer = eddl.ReLu(eddl.Dense(layer, 256))
out = eddl.Sigmoid(eddl.Dense(layer, 1))
net = eddl.Model([in_], [out])
eddl.build(
net, eddl.adam(0.001), ["cross_entropy"], ["binary_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
x_train = Tensor.load("imdb_2000_trX.bin")
y_train = Tensor.load("imdb_2000_trY.bin")
x_test = Tensor.load("imdb_2000_tsX.bin")
y_test = Tensor.load("imdb_2000_tsY.bin")
# batch x timesteps x input_dim
x_train.reshape_([x_train.shape[0], length, 1])
x_test.reshape_([x_test.shape[0], length, 1])
y_train.reshape_([y_train.shape[0], 1, 1])
y_test.reshape_([y_test.shape[0], 1, 1])
if args.small:
x_train = x_train.select([":64", ":", ":"])
y_train = y_train.select([":64", ":", ":"])
x_test = x_test.select([":64", ":", ":"])
y_test = y_test.select([":64", ":", ":"])
for i in range(epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
eddl.evaluate(net, [x_test], [y_test])
print("All done")
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([784])
layer = in_
layer = eddl.BatchNormalization(
eddl.Activation(eddl.L2(eddl.Dense(layer, 1024), 0.0001), "relu"), True
)
layer = eddl.BatchNormalization(
eddl.Activation(eddl.L2(eddl.Dense(layer, 1024), 0.0001), "relu"), True
)
layer = eddl.BatchNormalization(
eddl.Activation(eddl.L2(eddl.Dense(layer, 1024), 0.0001), "relu"), True
)
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
acc = CategoricalAccuracy()
net.build(
eddl.sgd(0.01, 0.9),
[eddl.getLoss("soft_cross_entropy")],
[acc],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
x_train.div_(255.0)
x_test.div_(255.0)
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def main(args):
eddl.download_mnist()
num_classes = 10
in_ = eddl.Input([784])
layer = in_
layer = eddl.ReLu(eddl.L2(eddl.Dense(layer, 1024), 0.0001))
layer = eddl.ReLu(eddl.L1(eddl.Dense(layer, 1024), 0.0001))
layer = eddl.ReLu(eddl.L1L2(eddl.Dense(layer, 1024), 0.00001, 0.0001))
out = eddl.Softmax(eddl.Dense(layer, num_classes))
net = eddl.Model([in_], [out])
eddl.build(
net,
eddl.sgd(0.01, 0.9),
["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
eddl.plot(net, "model.pdf")
x_train = Tensor.load("mnist_trX.bin")
y_train = Tensor.load("mnist_trY.bin")
x_test = Tensor.load("mnist_tsX.bin")
y_test = Tensor.load("mnist_tsY.bin")
if args.small:
x_train = x_train.select([":6000"])
y_train = y_train.select([":6000"])
x_test = x_test.select([":1000"])
y_test = y_test.select([":1000"])
x_train.div_(255.0)
x_test.div_(255.0)
eddl.fit(net, [x_train], [y_train], args.batch_size, args.epochs)
eddl.evaluate(net, [x_test], [y_test], bs=args.batch_size)
print("All done")
def read_slide(slide_fn, level=4):
levels = ecvl.OpenSlideGetLevels(slide_fn)
dims = [0, 0] + levels[level]
img = ecvl.OpenSlideRead(slide_fn, level, dims)
t = ecvl.ImageToTensor(img)
t_np = t.getdata()
s = t_np.shape
t_np = t_np.transpose((1, 2, 0)).reshape(
(s[1] * s[2], 3)) # Channel last and reshape
t_eval = Tensor.fromarray(t_np)
print(t_eval.getShape())
return t_eval, s
def fun(rows):
assert (len(rows) == 1)
item = rows[0]
feat, lab = self._get_img(item)
with self.lock:
self.feats.append(feat)
self.labels.append(lab)
self.perm.append(idx)
self.cow += 1
self.onair -= 1
if (self.cow == self.tot): # last patch
# recover original order of images
sh = []
for (i, x) in enumerate(self.perm):
sh.append([x, i])
sh = np.array(sorted(sh))[:, 1]
# reorder data and conclude
feats = np.array(self.feats)[sh]
labels = np.array(self.labels)[sh]
self.bb = (Tensor(feats.transpose(0, 3, 1,
2)), Tensor(labels))
self.finished_event.set()
def read_input(filename, split_ratio=0.7):
data = np.load(filename)['d']
# shuffle data
sel_index = np.arange(data.shape[0])
np.random.shuffle(sel_index)
shuffled_data = data[sel_index]
shuffled_data = np.c_[shuffled_data, np.zeros(shuffled_data.shape[0])] # Add column for two class labels
shuffled_data[:,4][shuffled_data[:,3] == 0] = 1. ## [1] -> [1 0], [0]-->[0 1]
shuffled_data[:,[3,4]] = shuffled_data[:,[4,3]] ## Swap last two columns [1] --> [0 1], [0] --> [1 0]
# Split train test
n_train = int (shuffled_data.shape[0] * split_ratio )
train = shuffled_data[0:n_train]
test = shuffled_data[n_train:]
x_trn = train[:,:3]
y_trn = train[:,3:]
# Class balancing of validation set
test_0 = test[test[:, 3] == 1]
test_1 = test[test[:, 4] == 1]
c0_size = test_0.shape[0]
c1_size = test_1.shape[0]
c_size = min(c0_size, c1_size)
test_bal = np.concatenate((test_0[:c_size], test_1[:c_size]),axis=0)
x_test = test_bal[:,:3]
y_test = test_bal[:,3:]
# Tensor creation
x_train_t = Tensor.fromarray(x_trn.astype(np.float32))
y_train_t = Tensor.fromarray(y_trn.astype(np.int32))
x_test_t = Tensor.fromarray(x_test.astype(np.float32))
y_test_t = Tensor.fromarray(y_test.astype(np.int32))
return x_train_t, y_train_t, x_test_t, y_test_t
