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 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 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 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 main(args):
if not ecvl.ECVL_EDDL:
print("No EDDL support - quitting")
sys.exit(0)
img = ecvl.ImRead(args.in_img)
augs = ecvl.SequentialAugmentationContainer([
ecvl.AugCenterCrop(), # Make image square
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.AugCenterCrop([224, 224]),
ecvl.AugToFloat32(255),
ecvl.AugNormalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
ecvl.AugmentationParam.SetSeed(0)
print("Applying augmentations")
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)
print("Applying augmentations (from text)")
newdeal_augs = ecvl.AugmentationFactory.create(AUG_TXT)
newdeal_augs.Apply(img)
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]),
ecvl.AugToFloat32(255),
ecvl.AugNormalize(0.449, 0.226), # mean of imagenet stats
])
test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim([30, 30]),
ecvl.AugToFloat32(255),
ecvl.AugNormalize(0.449, 0.226), # mean of imagenet stats
])
# number of augmentation containers must match number of dataset splits
ds_augs = ecvl.DatasetAugmentations([training_augs, 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)
# Save some input images
ecvl.ImWrite("mnist_batch.png", ecvl.MakeGrid(x, 8, False))
ecvl.ImWrite("mnist_batch_normalized.png", ecvl.MakeGrid(x, 8, True))
def main(args):
num_classes = 1
size = [512, 512] # size of images
thresh = 0.5
best_dice = -1
if args.out_dir:
os.makedirs(args.out_dir, exist_ok=True)
in_ = eddl.Input([1, size[0], size[1]])
out = SegNetBN(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
eddl.build(net, eddl.adam(0.0001), ["cross_entropy"],
["mean_squared_error"],
eddl.CS_GPU([1], mem='low_mem') if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "pneumothorax_segmentation_training")
if args.ckpts and os.path.exists(args.ckpts):
print("Loading checkpoints '{}'".format(args.ckpts))
eddl.load(net, args.ckpts, 'bin')
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
ecvl.AugMirror(0.5),
ecvl.AugRotate([-10, 10]),
ecvl.AugBrightness([0, 30]),
ecvl.AugGammaContrast([0, 3]),
])
validation_augs = ecvl.SequentialAugmentationContainer(
[ecvl.AugResizeDim(size)])
dataset_augs = ecvl.DatasetAugmentations(
[training_augs, validation_augs, None])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs,
ecvl.ColorType.GRAY)
# Prepare tensors which store batch
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, d.n_channels_gt_, size[0], size[1]])
# Retrieve indices of images with a black ground truth
# which are not include in a split
train_split = d.GetSplit(ecvl.SplitType.training)
val_split = d.GetSplit(ecvl.SplitType.validation)
test_split = d.GetSplit(ecvl.SplitType.test)
all_split = set(train_split + val_split + test_split)
images_list = set(range(len(d.samples_)))
# Obtain images with black ground truth
black_images = images_list - all_split
# Add a 25% of training samples with black ground truth.
num_samples_train = math.floor(len(train_split) * 1.25)
num_batches_train = num_samples_train // args.batch_size
# Add a 25% of validation samples with black ground truth.
num_samples_validation = math.floor(len(val_split) * 1.25)
num_batches_validation = num_samples_validation // args.batch_size
black_images = list(black_images)
black_training = black_images[0:-(num_samples_validation - len(val_split))]
black_validation = black_images[-(num_samples_validation -
len(val_split)):]
indices = list(range(args.batch_size))
evaluator = utils.Evaluator()
print("Starting training")
for e in range(args.epochs):
print("Epoch {:d}/{:d} - Training".format(e + 1, args.epochs),
flush=True)
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(net)
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
random.shuffle(black_training)
d.ResetAllBatches()
# Indices to track mask and black vector in PneumothoraxLoadBatch
m_i = 0
b_i = 0
for i, b in enumerate(range(num_batches_train)):
d, images, labels, _, m_i, b_i = PneumothoraxLoadBatch(
d, black_training, m_i, b_i)
x, y = fill_tensors(images, labels, x, y)
x.div_(255.0)
y.div_(255.0)
eddl.train_batch(net, [x], [y], indices)
if i % args.log_interval == 0:
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, args.epochs, b + 1, num_batches_train),
end="",
flush=True)
eddl.print_loss(net, b)
print()
d.SetSplit(ecvl.SplitType.validation)
evaluator.ResetEval()
print("Epoch %d/%d - Evaluation" % (e + 1, args.epochs), flush=True)
m_i = 0
b_i = 0
for b in range(num_batches_validation):
n = 0
print("Epoch {:d}/{:d} (batch {:d}/{:d}) ".format(
e + 1, args.epochs, b + 1, num_batches_validation),
end="",
flush=True)
d, images, labels, names, m_i, b_i = PneumothoraxLoadBatch(
d, black_validation, m_i, b_i)
x, y = fill_tensors(images, labels, x, y)
x.div_(255.0)
y.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out_sigm)
# Compute Dice metric and optionally save the output images
for k in range(args.batch_size):
pred = output.select([str(k)])
gt = y.select([str(k)])
pred_np = np.array(pred, copy=False)
gt_np = np.array(gt, copy=False)
# DiceCoefficient modifies image as a side effect
dice = evaluator.DiceCoefficient(pred_np, gt_np, thresh=thresh)
print("- Dice: {:.6f} ".format(dice), end="", flush=True)
if args.out_dir:
# Save original image fused together with prediction and
# ground truth
pred_np *= 255
pred_ecvl = ecvl.TensorToImage(pred)
pred_ecvl.colortype_ = ecvl.ColorType.GRAY
pred_ecvl.channels_ = "xyc"
ecvl.ResizeDim(pred_ecvl, pred_ecvl, (1024, 1024),
ecvl.InterpolationType.nearest)
filename_gt = names[n + 1]
gt_ecvl = ecvl.ImRead(filename_gt,
ecvl.ImReadMode.GRAYSCALE)
filename = names[n]
# Image as BGR
img_ecvl = ecvl.ImRead(filename)
ecvl.Stack([img_ecvl, img_ecvl, img_ecvl], img_ecvl)
img_ecvl.channels_ = "xyc"
img_ecvl.colortype_ = ecvl.ColorType.BGR
image_np = np.array(img_ecvl, copy=False)
pred_np = np.array(pred_ecvl, copy=False)
gt_np = np.array(gt_ecvl, copy=False)
pred_np = pred_np.squeeze()
gt_np = gt_np.squeeze()
# Prediction summed in R channel
image_np[:, :, -1] = np.where(pred_np == 255, pred_np,
image_np[:, :, -1])
# Ground truth summed in G channel
image_np[:, :, 1] = np.where(gt_np == 255, gt_np,
image_np[:, :, 1])
n += 2
head, tail = os.path.splitext(os.path.basename(filename))
bname = "{}.png".format(head)
filepath = os.path.join(args.out_dir, bname)
ecvl.ImWrite(filepath, img_ecvl)
print()
mean_dice = evaluator.MeanMetric()
if mean_dice > best_dice:
print("Saving weights")
eddl.save(
net, "pneumothorax_segnetBN_adam_lr_0.0001_"
"loss_ce_size_512_{}.bin".format(e + 1), "bin")
best_dice = mean_dice
print("Mean Dice Coefficient: {:.6g}".format(mean_dice))
def main(args):
num_classes = 1
size = [512, 512] # size of images
thresh = 0.5
if args.out_dir:
os.makedirs(args.out_dir, exist_ok=True)
in_ = eddl.Input([1, size[0], size[1]])
out = SegNetBN(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
eddl.build(
net,
eddl.adam(0.0001),
["cross_entropy"],
["mean_squared_error"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU()
)
eddl.summary(net)
eddl.setlogfile(net, "pneumothorax_segmentation_inference")
if not os.path.exists(args.ckpts):
raise RuntimeError('Checkpoint "{}" not found'.format(args.ckpts))
eddl.load(net, args.ckpts, "bin")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
dataset_augs = ecvl.DatasetAugmentations([training_augs, None, test_augs])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs,
ecvl.ColorType.GRAY)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
print("Testing")
d.SetSplit(ecvl.SplitType.test)
num_samples_test = len(d.GetSplit())
num_batches_test = num_samples_test // args.batch_size
evaluator = utils.Evaluator()
evaluator.ResetEval()
for b in range(num_batches_test):
n = 0
print("Batch {:d}/{:d} ".format(
b + 1, num_batches_test), end="", flush=True)
d.LoadBatch(x)
x.div_(255.0)
eddl.forward(net, [x])
if args.out_dir:
output = eddl.getOutput(out_sigm)
for k in range(args.batch_size):
img = output.select([str(k)])
img_I = ecvl.TensorToImage(img)
img_I.colortype_ = ecvl.ColorType.GRAY
img_I.channels_ = "xyc"
ecvl.Threshold(img_I, img_I, thresh, 255)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "{}.png".format(head)
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, img_I)
n += 1
print()
def main(args):
num_classes = 8
size = [224, 224] # size of images
in_ = eddl.Input([3, size[0], size[1]])
out = VGG16(in_, num_classes)
net = eddl.Model([in_], [out])
eddl.build(net, eddl.sgd(0.001, 0.9), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "skin_lesion_classification")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
ecvl.AugMirror(.5),
ecvl.AugFlip(.5),
ecvl.AugRotate([-180, 180]),
ecvl.AugAdditivePoissonNoise([0, 10]),
ecvl.AugGammaContrast([0.5, 1.5]),
ecvl.AugGaussianBlur([0, 0.8]),
ecvl.AugCoarseDropout([0, 0.3], [0.02, 0.05], 0.5)
])
validation_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
dataset_augs = ecvl.DatasetAugmentations(
[training_augs, validation_augs, None])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, len(d.classes_)])
num_samples_train = len(d.GetSplit())
num_batches_train = num_samples_train // args.batch_size
d.SetSplit(ecvl.SplitType.validation)
num_samples_val = len(d.GetSplit())
num_batches_val = num_samples_val // args.batch_size
indices = list(range(args.batch_size))
metric = eddl.getMetric("categorical_accuracy")
print("Starting training")
for e in range(args.epochs):
print("Epoch {:d}/{:d} - Training".format(e + 1, args.epochs),
flush=True)
if args.out_dir:
current_path = os.path.join(args.out_dir, "Epoch_%d" % e)
for c in d.classes_:
c_dir = os.path.join(current_path, c)
os.makedirs(c_dir, exist_ok=True)
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(net)
total_metric = []
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetAllBatches()
for b in range(num_batches_train):
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, args.epochs, b + 1, num_batches_train),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
tx, ty = [x], [y]
eddl.train_batch(net, tx, ty, indices)
eddl.print_loss(net, b)
print()
print("Saving weights")
eddl.save(net, "isic_classification_checkpoint_epoch_%s.bin" % e,
"bin")
print("Epoch %d/%d - Evaluation" % (e + 1, args.epochs), flush=True)
d.SetSplit(ecvl.SplitType.validation)
for b in range(num_batches_val):
n = 0
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, args.epochs, b + 1, num_batches_val),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out)
sum_ = 0.0
for k in range(args.batch_size):
result = output.select([str(k)])
target = y.select([str(k)])
ca = metric.value(target, result)
total_metric.append(ca)
sum_ += ca
if args.out_dir:
result_a = np.array(result, copy=False)
target_a = np.array(target, copy=False)
classe = np.argmax(result_a).item()
gt_class = np.argmax(target_a).item()
single_image = x.select([str(k)])
img_t = ecvl.TensorToView(single_image)
img_t.colortype_ = ecvl.ColorType.BGR
single_image.mult_(255.)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s_gt_class_%s.png" % (head, gt_class)
cur_path = os.path.join(current_path, d.classes_[classe],
bname)
ecvl.ImWrite(cur_path, img_t)
n += 1
print("categorical_accuracy:", sum_ / args.batch_size)
total_avg = sum(total_metric) / len(total_metric)
print("Total categorical accuracy:", total_avg)
def main(args):
num_classes = 10
size = [28, 28] # size of images
ctype = ecvl.ColorType.GRAY
in_ = eddl.Input([1, size[0], size[1]])
out = LeNet(in_, num_classes)
net = eddl.Model([in_], [out])
eddl.build(net, eddl.sgd(0.001, 0.9), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "mnist")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugRotate([-5, 5]),
ecvl.AugAdditivePoissonNoise([0, 10]),
ecvl.AugGaussianBlur([0, 0.8]),
ecvl.AugCoarseDropout([0, 0.3], [0.02, 0.05], 0),
])
dataset_augs = ecvl.DatasetAugmentations([training_augs, None, None])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs, ctype)
x_train = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y_train = Tensor([args.batch_size, len(d.classes_)])
num_samples = len(d.GetSplit())
num_batches = num_samples // args.batch_size
indices = list(range(args.batch_size))
print("Training")
for i in range(args.epochs):
eddl.reset_loss(net)
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetCurrentBatch()
for j in range(num_batches):
print("Epoch %d/%d (batch %d/%d) - " %
(i + 1, args.epochs, j + 1, num_batches),
end="",
flush=True)
d.LoadBatch(x_train, y_train)
x_train.div_(255.0)
tx, ty = [x_train], [y_train]
eddl.train_batch(net, tx, ty, indices)
eddl.print_loss(net, j)
print()
print("Saving weights")
eddl.save(net, "mnist_checkpoint.bin", "bin")
print("Evaluation")
d.SetSplit(ecvl.SplitType.test)
num_samples = len(d.GetSplit())
num_batches = num_samples // args.batch_size
for i in range(num_batches):
print("batch %d / %d - " % (i, num_batches), end="", flush=True)
d.LoadBatch(x_train, y_train)
x_train.div_(255.0)
eddl.evaluate(net, [x_train], [y_train])
def main(args):
batch_size = args.batch_size
image_size = args.size, args.size
thresh = 0.5
if args.weights:
os.makedirs(args.weights, exist_ok=True)
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(image_size,
ecvl.InterpolationType.cubic,
gt_interp=ecvl.InterpolationType.nearest),
ecvl.AugMirror(.5),
ecvl.AugFlip(.5),
ecvl.AugRotate([-180, 180]),
ecvl.AugAdditivePoissonNoise([0, 10]),
ecvl.AugGammaContrast([0.5, 1.5]),
ecvl.AugGaussianBlur([0, 0.8]),
ecvl.AugCoarseDropout([0, 0.03], [0.02, 0.05], 0.25),
ecvl.AugToFloat32(255, divisor_gt=255),
ecvl.AugNormalize([0.6681, 0.5301, 0.5247],
[0.1337, 0.1480, 0.1595]), # isic stats
])
validation_test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(image_size,
ecvl.InterpolationType.cubic,
gt_interp=ecvl.InterpolationType.nearest),
ecvl.AugToFloat32(255, divisor_gt=255),
ecvl.AugNormalize([0.6681, 0.5301, 0.5247],
[0.1337, 0.1480, 0.1595]), # isic stats
])
dataset_augs = ecvl.DatasetAugmentations(
[training_augs, validation_test_augs, validation_test_augs])
print('Reading dataset')
d = ecvl.DLDataset(args.in_ds,
args.batch_size,
dataset_augs,
ctype=ecvl.ColorType.RGB)
num_classes = len(d.classes_) or d.n_channels_gt_
size = d.n_channels_, args.size, args.size
if args.ckpts:
net = eddl.import_net_from_onnx_file(args.ckpts, size)
else:
in_ = eddl.Input(size)
out = Unet(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
# model_path = utils.DownloadModel(segmentation_zoo[args.model]['url'], f'{args.model}.onnx', 'model_onnx')
# net = eddl.import_net_from_onnx_file(model_path, size)
# eddl.removeLayer(net, segmentation_zoo[args.model]['to_remove'])
# top = eddl.getLayer(net, segmentation_zoo[args.model]['top'])
#
# out = eddl.Sigmoid(eddl.Conv(top, num_classes, [3, 3], name='last_layer'))
# data_input = eddl.getLayer(net, segmentation_zoo[args.model]['input']) # input of the onnx
# net = eddl.Model([data_input], [out])
loss_name = 'binary_cross_entropy'
metric_name = 'mean_squared_error'
eddl.build(
net, eddl.adam(args.learning_rate), [loss_name], [metric_name],
eddl.CS_GPU(args.gpu, mem="low_mem") if args.gpu else eddl.CS_CPU(),
True)
out = eddl.getOut(net)[0]
# if not args.ckpts:
# eddl.initializeLayer(net, "last_layer")
eddl.summary(net)
eddl.setlogfile(net, 'skin_lesion_segmentation')
x = Tensor([args.batch_size, *size])
y = Tensor([args.batch_size, d.n_channels_gt_, size[1], size[2]])
miou = 0.
if args.train:
num_samples_train = len(d.GetSplit())
num_batches_train = num_samples_train // args.batch_size
num_samples_val = len(d.GetSplit(ecvl.SplitType.validation))
num_batches_val = num_samples_val // args.batch_size
evaluator = utils.Evaluator()
print('Starting training')
for e in range(args.epochs):
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(net)
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetAllBatches()
for b in range(num_batches_train):
d.LoadBatch(x, y)
# x_ = x.select(["0"])
# x_.normalize_(0, 1)
# x_.mult_(255.)
# x_.save(f'images/train_{e}_{b}.png')
#
# y_ = y.select(["0"])
# # y_.mult_(255.)
# y_.save(f'images/train_gt_{e}_{b}.png')
eddl.train_batch(net, [x], [y])
losses = eddl.get_losses(net)
metrics = eddl.get_metrics(net)
print(
f'Train - epoch [{e + 1}/{args.epochs}] - batch [{b + 1}/{num_batches_train}]'
f' - {loss_name}={losses[0]:.3f} - {metric_name}={metrics[0]:.3f}',
flush=True)
d.SetSplit(ecvl.SplitType.validation)
evaluator.ResetEval()
eddl.reset_loss(net)
for b in range(num_batches_val):
n = 0
print(
f'Validation - epoch [{e + 1}/{args.epochs}] - batch [{b + 1}/{num_batches_val}]'
)
d.LoadBatch(x, y)
eddl.forward(net, [x])
output = eddl.getOutput(out)
for bs in range(args.batch_size):
img = output.select([str(bs)])
gt = y.select([str(bs)])
img_np = np.array(img, copy=False)
gt_np = np.array(gt, copy=False)
iou = evaluator.BinaryIoU(img_np, gt_np, thresh=thresh)
print(f' - IoU: {iou:.3f}', end="", flush=True)
if args.out_dir:
# C++ BinaryIoU modifies image as a side effect
img_np[img_np >= thresh] = 1
img_np[img_np < thresh] = 0
img_t = ecvl.TensorToView(img)
img_t.colortype_ = ecvl.ColorType.GRAY
img_t.channels_ = "xyc"
img.mult_(255.)
# orig_img
orig_img = x.select([str(bs)])
orig_img.mult_(255.)
orig_img_t = ecvl.TensorToImage(orig_img)
orig_img_t.colortype_ = ecvl.ColorType.BGR
orig_img_t.channels_ = "xyc"
tmp, labels = ecvl.Image.empty(), ecvl.Image.empty()
ecvl.CopyImage(img_t, tmp, ecvl.DataType.uint8)
ecvl.ConnectedComponentsLabeling(tmp, labels)
ecvl.CopyImage(labels, tmp, ecvl.DataType.uint8)
contours = ecvl.FindContours(tmp)
ecvl.CopyImage(orig_img_t, tmp, ecvl.DataType.uint8)
tmp_np = np.array(tmp, copy=False)
for cseq in contours:
for c in cseq:
tmp_np[c[0], c[1], 0] = 0
tmp_np[c[0], c[1], 1] = 0
tmp_np[c[0], c[1], 2] = 255
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(
os.path.basename(filename))
bname = "%s.png" % head
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, tmp)
if e == 0:
gt_t = ecvl.TensorToView(gt)
gt_t.colortype_ = ecvl.ColorType.GRAY
gt_t.channels_ = "xyc"
gt.mult_(255.)
gt_filename = d.samples_[d.GetSplit()
[n]].label_path_
gt_fn = os.path.join(args.out_dir,
os.path.basename(gt_filename))
ecvl.ImWrite(gt_fn, gt_t)
n += 1
print()
last_miou = evaluator.MIoU()
print(
f'Validation - epoch [{e + 1}/{args.epochs}] - Total MIoU: {last_miou:.3f}'
)
if last_miou > miou:
miou = last_miou
eddl.save_net_to_onnx_file(
net,
os.path.join(args.weights,
f'isic_segm_{args.model}_epoch_{e + 1}.onnx'))
print('Weights saved')
elif args.test:
evaluator = utils.Evaluator()
evaluator.ResetEval()
d.SetSplit(ecvl.SplitType.test)
num_samples_test = len(d.GetSplit())
num_batches_test = num_samples_test // batch_size
for b in range(num_batches_test):
n = 0
print(f'Test - batch [{b + 1}/{num_batches_test}]')
d.LoadBatch(x, y)
eddl.forward(net, [x])
output = eddl.getOutput(out)
for bs in range(args.batch_size):
img = output.select([str(bs)])
gt = y.select([str(bs)])
img_np, gt_np = np.array(img, copy=False), np.array(gt,
copy=False)
iou = evaluator.BinaryIoU(img_np, gt_np, thresh=thresh)
print(f' - IoU: {iou:.3f}', end="", flush=True)
if args.out_dir:
# C++ BinaryIoU modifies image as a side effect
img_np[img_np >= thresh] = 1
img_np[img_np < thresh] = 0
img_t = ecvl.TensorToView(img)
img_t.colortype_ = ecvl.ColorType.GRAY
img_t.channels_ = "xyc"
img.mult_(255.)
# orig_img
orig_img = x.select([str(bs)])
orig_img.mult_(255.)
orig_img_t = ecvl.TensorToImage(orig_img)
orig_img_t.colortype_ = ecvl.ColorType.BGR
orig_img_t.channels_ = "xyc"
tmp, labels = ecvl.Image.empty(), ecvl.Image.empty()
ecvl.CopyImage(img_t, tmp, ecvl.DataType.uint8)
ecvl.ConnectedComponentsLabeling(tmp, labels)
ecvl.CopyImage(labels, tmp, ecvl.DataType.uint8)
contours = ecvl.FindContours(tmp)
ecvl.CopyImage(orig_img_t, tmp, ecvl.DataType.uint8)
tmp_np = np.array(tmp, copy=False)
for cseq in contours:
for c in cseq:
tmp_np[c[0], c[1], 0] = 0
tmp_np[c[0], c[1], 1] = 0
tmp_np[c[0], c[1], 2] = 255
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s.png" % head
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, tmp)
gt_t = ecvl.TensorToView(gt)
gt_t.colortype_ = ecvl.ColorType.GRAY
gt_t.channels_ = "xyc"
gt.mult_(255.)
gt_filename = d.samples_[d.GetSplit()[n]].label_path_
gt_fn = os.path.join(args.out_dir,
os.path.basename(gt_filename))
ecvl.ImWrite(gt_fn, gt_t)
n += 1
miou = evaluator.MIoU()
print(f'Test - Total MIoU: {miou:.3f}')
def main(args):
eddl.download_drive()
in_1 = eddl.Input([3, 584, 584])
in_2 = eddl.Input([1, 584, 584])
layer = eddl.Concat([in_1, in_2])
layer = eddl.RandomCropScale(layer, [0.9, 1.0])
layer = eddl.CenteredCrop(layer, [512, 512])
img = eddl.Select(layer, ["0:3"])
mask = eddl.Select(layer, ["3"])
# DA net
danet = eddl.Model([in_1, in_2], [])
eddl.build(danet)
if args.gpu:
eddl.toGPU(danet, mem="low_mem")
eddl.summary(danet)
# SegNet
in_ = eddl.Input([3, 512, 512])
out = eddl.Sigmoid(UNetWithPadding(in_))
segnet = eddl.Model([in_], [out])
eddl.build(
segnet,
eddl.adam(0.00001), # Optimizer
["mse"], # Losses
["mse"], # Metrics
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(segnet)
print("Reading training data")
# x_train_f = Tensor.fromarray(np.load("drive_trX.npy").astype(np.float32))
x_train_f = Tensor.load("drive_trX.bin")
x_train = x_train_f.permute([0, 3, 1, 2])
x_train.info()
x_train.div_(255.0)
print("Reading test data")
# y_train = Tensor.fromarray(np.load("drive_trY.npy").astype(np.float32))
y_train = Tensor.load("drive_trY.bin")
y_train.info()
y_train.reshape_([20, 1, 584, 584])
y_train.div_(255.0)
xbatch = Tensor([args.batch_size, 3, 584, 584])
ybatch = Tensor([args.batch_size, 1, 584, 584])
print("Starting training")
for i in range(args.epochs):
print("\nEpoch %d/%d" % (i + 1, args.epochs))
eddl.reset_loss(segnet)
for j in range(args.num_batches):
eddl.next_batch([x_train, y_train], [xbatch, ybatch])
# DA net
eddl.forward(danet, [xbatch, ybatch])
xbatch_da = eddl.getOutput(img)
ybatch_da = eddl.getOutput(mask)
# SegNet
eddl.train_batch(segnet, [xbatch_da], [ybatch_da])
eddl.print_loss(segnet, j)
if i == args.epochs - 1:
yout = eddl.getOutput(out).select(["0"])
yout.save("./out_%d.jpg" % j)
print()
print("All done")
def main(args):
eddl.download_flickr()
epochs = 2 if args.small else 50
olength = 20
outvs = 2000
embdim = 32
# True: remove last layers and set new top = flatten
# new input_size: [3, 256, 256] (from [224, 224, 3])
net = eddl.download_resnet18(True, [3, 256, 256])
lreshape = eddl.getLayer(net, "top")
# create a new model from input output
image_in = eddl.getLayer(net, "input")
# Decoder
ldecin = eddl.Input([outvs])
ldec = eddl.ReduceArgMax(ldecin, [0])
ldec = eddl.RandomUniform(eddl.Embedding(ldec, outvs, 1, embdim, True),
-0.05, 0.05)
ldec = eddl.Concat([ldec, lreshape])
layer = eddl.LSTM(ldec, 512, True)
out = eddl.Softmax(eddl.Dense(layer, outvs))
eddl.setDecoder(ldecin)
net = eddl.Model([image_in], [out])
# Build model
eddl.build(
net, eddl.adam(0.01), ["softmax_cross_entropy"], ["accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(net)
# Load dataset
x_train = Tensor.load("flickr_trX.bin", "bin")
y_train = Tensor.load("flickr_trY.bin", "bin")
if args.small:
x_train = x_train.select([f"0:{2 * args.batch_size}", ":", ":", ":"])
y_train = y_train.select([f"0:{2 * args.batch_size}", ":"])
xtrain = Tensor.permute(x_train, [0, 3, 1, 2])
y_train = Tensor.onehot(y_train, outvs)
# batch x timesteps x input_dim
y_train.reshape_([y_train.shape[0], olength, outvs])
eddl.fit(net, [xtrain], [y_train], args.batch_size, epochs)
eddl.save(net, "img2text.bin", "bin")
print("\n === INFERENCE ===\n")
# Get all the reshapes of the images. Only use the CNN
timage = Tensor([x_train.shape[0], 512]) # images reshape
cnn = eddl.Model([image_in], [lreshape])
eddl.build(
cnn,
eddl.adam(0.001), # not relevant
["mse"], # not relevant
["mse"], # not relevant
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(cnn)
# forward images
xbatch = Tensor([args.batch_size, 3, 256, 256])
# numbatches = x_train.shape[0] / args.batch_size
j = 0
eddl.next_batch([x_train], [xbatch])
eddl.forward(cnn, [xbatch])
ybatch = eddl.getOutput(lreshape)
sample = str(j * args.batch_size) + ":" + str((j + 1) * args.batch_size)
timage.set_select([sample, ":"], ybatch)
# Create Decoder non recurrent for n-best
ldecin = eddl.Input([outvs])
image = eddl.Input([512])
lstate = eddl.States([2, 512])
ldec = eddl.ReduceArgMax(ldecin, [0])
ldec = eddl.RandomUniform(eddl.Embedding(ldec, outvs, 1, embdim), -0.05,
0.05)
ldec = eddl.Concat([ldec, image])
lstm = eddl.LSTM([ldec, lstate], 512, True)
lstm.isrecurrent = False # Important
out = eddl.Softmax(eddl.Dense(lstm, outvs))
decoder = eddl.Model([ldecin, image, lstate], [out])
eddl.build(
decoder,
eddl.adam(0.001), # not relevant
["softmax_cross_entropy"], # not relevant
["accuracy"], # not relevant
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem))
eddl.summary(decoder)
# Copy params from trained net
eddl.copyParam(eddl.getLayer(net, "LSTM1"),
eddl.getLayer(decoder, "LSTM2"))
eddl.copyParam(eddl.getLayer(net, "dense1"),
eddl.getLayer(decoder, "dense2"))
eddl.copyParam(eddl.getLayer(net, "embedding1"),
eddl.getLayer(decoder, "embedding2"))
# N-best for sample s
s = 1 if args.small else 100 # sample 100
# three input tensors with batch_size = 1 (one sentence)
treshape = timage.select([str(s), ":"])
text = y_train.select([str(s), ":", ":"]) # 1 x olength x outvs
for j in range(olength):
print(f"Word: {j}")
word = None
if j == 0:
word = Tensor.zeros([1, outvs])
else:
word = text.select(["0", str(j - 1), ":"])
word.reshape_([1, outvs]) # batch = 1
treshape.reshape_([1, 512]) # batch = 1
state = Tensor.zeros([1, 2, 512]) # batch = 1
input_ = [word, treshape, state]
eddl.forward(decoder, input_)
# outword = eddl.getOutput(out)
vstates = eddl.getStates(lstm)
for i in range(len(vstates)):
vstates[i].reshape_([1, 1, 512])
state.set_select([":", str(i), ":"], vstates[i])
print("All done")
def main(args):
eddl.download_eutrans()
epochs = 1 if args.small else 5
ilength = 30
olength = 30
invs = 687
outvs = 514
embedding = 64
# Encoder
in_ = eddl.Input([1]) # 1 word
layer = in_
lE = eddl.RandomUniform(
eddl.Embedding(layer, invs, 1, embedding, True), -0.05, 0.05
)
enc = eddl.LSTM(lE, 128, True)
cps = eddl.GetStates(enc)
# Decoder
ldin = eddl.Input([outvs])
ld = eddl.ReduceArgMax(ldin, [0])
ld = eddl.RandomUniform(
eddl.Embedding(ld, outvs, 1, embedding), -0.05, 0.05
)
layer = eddl.LSTM([ld, cps], 128)
out = eddl.Softmax(eddl.Dense(layer, outvs))
eddl.setDecoder(ldin)
net = eddl.Model([in_], [out])
# Build model
eddl.build(
net,
eddl.adam(0.01),
["softmax_cross_entropy"],
["accuracy"],
eddl.CS_GPU(mem=args.mem) if args.gpu else eddl.CS_CPU(mem=args.mem)
)
eddl.summary(net)
# Load dataset
x_train = Tensor.load("eutrans_trX.bin")
y_train = Tensor.load("eutrans_trY.bin")
y_train = Tensor.onehot(y_train, outvs)
# batch x timesteps x input_dim
x_train.reshape_([x_train.shape[0], ilength, 1])
# batch x timesteps x ouput_dim
y_train.reshape_([y_train.shape[0], olength, outvs])
x_test = Tensor.load("eutrans_tsX.bin")
y_test = Tensor.load("eutrans_tsY.bin")
y_test = Tensor.onehot(y_test, outvs)
# batch x timesteps x input_dim
x_test.reshape_([x_test.shape[0], ilength, 1])
# batch x timesteps x ouput_dim
y_test.reshape_([y_test.shape[0], olength, outvs])
if args.small:
sel = [f":{3 * args.batch_size}", ":", ":"]
x_train = x_train.select(sel)
y_train = y_train.select(sel)
x_test = x_test.select(sel)
y_test = y_test.select(sel)
# Train model
ybatch = Tensor([args.batch_size, olength, outvs])
eddl.next_batch([y_train], [ybatch])
for i in range(epochs):
eddl.fit(net, [x_train], [y_train], args.batch_size, 1)
print("All done")
def eddl_validate_DLDataset(model, out, d):
batch_time = AverageMeter('BatchTime', ':6.3f')
total_time = AverageMeter('TotalTime', ':6.3f')
# Use the image resized dims defined by user or default image size for resnet [224,224]
if hasattr(d, 'resize_dims_'):
size = d.resize_dims_
else:
size = [224, 224]
x = Tensor([d.batch_size_, d.n_channels_, size[0], size[1]])
y = Tensor([d.batch_size_, len(d.classes_)])
d.SetSplit(ecvl.SplitType.validation)
num_samples_val = len(d.GetSplit())
num_batches_val = num_samples_val // d.batch_size_
indices = list(range(d.batch_size_))
metric = eddl.getMetric("categorical_accuracy")
print("Start Evaluation: ", flush=True)
total_metric = []
print("Evaluation (validation set)", flush=True)
d.ResetAllBatches()
d.SetSplit(ecvl.SplitType.validation)
end_total = time.time()
batch_time.reset()
end = time.time()
for b in range(num_batches_val):
n = 0
print("(batch {:d}/{:d}) - ".format(b + 1, num_batches_val),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
eddl.forward(model, [x])
output = eddl.getOutput(out)
sum_ = 0.0
for k in range(d.batch_size_):
result = output.select([str(k)])
target = y.select([str(k)])
ca = metric.value(target, result)
total_metric.append(ca)
sum_ += ca
"""
if args.out_dir:
result_a = np.array(result, copy=False)
target_a = np.array(target, copy=False)
classe = np.argmax(result_a).item()
gt_class = np.argmax(target_a).item()
single_image = eddlT.select(x, k)
img_t = ecvl.TensorToView(single_image)
img_t.colortype_ = ecvl.ColorType.BGR
single_image.mult_(255.)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s_gt_class_%s.png" % (head, gt_class)
cur_path = os.path.join(
current_path, d.classes_[classe], bname
)
ecvl.ImWrite(cur_path, img_t)
"""
n += 1
batch_time.update(time.time() - end)
end = time.time()
print("categorical_accuracy:".format(sum_ / d.batch_size_), flush=True)
print(batch_time)
if (num_batches_val > 0):
total_avg = sum(total_metric) / len(total_metric)
print("Total categorical accuracy:{}".format(total_avg), flush=True)
else:
print(
"Warning! \n "
"Please check your validation set size, it might be smaller than the batch size,\n "
"Validation test didn't execute as batch number is 0")
#total_avg = sum(total_metric) / len(total_metric)
#print("Total categorical accuracy:{}".format(total_avg), flush=True)
total_time.update(time.time() - end_total)
print(total_time, flush=True)
return model
def eddl_train_DLDataset(model,
out,
d,
learning_rate=1e-2,
momentum=0.9,
epochs=10,
dynamic_lr=False):
batch_time = AverageMeter('BatchTime', ':6.3f')
total_time = AverageMeter('TotalTime', ':6.3f')
# Use the image resized dims defined by user or default image size for resnet [224,224]
if hasattr(d, 'resize_dims_'):
size = d.resize_dims_
else:
size = [224, 224]
x = Tensor([d.batch_size_, d.n_channels_, size[0], size[1]])
y = Tensor([d.batch_size_, len(d.classes_)])
d.SetSplit(ecvl.SplitType.training)
num_samples_train = len(d.GetSplit())
num_batches_train = num_samples_train // d.batch_size_
d.SetSplit(ecvl.SplitType.validation)
num_samples_val = len(d.GetSplit())
num_batches_val = num_samples_val // d.batch_size_
indices = list(range(d.batch_size_))
metric = eddl.getMetric("categorical_accuracy")
print("Starting training", flush=True)
end_total = time.time()
for e in range(epochs):
if dynamic_lr and (e % 30 == 0) and e > 0:
# every 30 epochs we want to decrease the learning rate value by 0.1
print(
"every 30 epochs we want to decrease the learning rate value by 0.1"
)
learning_rate = learning_rate * 0.1
eddl.setlr(model, [learning_rate, momentum])
print("Epoch {:d}/{:d} - Training".format(e + 1, epochs), flush=True)
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(model)
total_metric = []
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetAllBatches()
batch_time.reset()
end = time.time()
for b in range(num_batches_train):
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, epochs, b + 1, num_batches_train),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
tx, ty = [x], [y]
eddl.train_batch(model, tx, ty, indices)
eddl.print_loss(model, b)
batch_time.update(time.time() - end)
end = time.time()
print(batch_time, flush=True)
print()
#print("Saving weights")
#eddl.save(
# net, "isic_classification_checkpoint_epoch_%s.bin" % e, "bin"
#)
print("Epoch %d/%d - Evaluation (validation set)" % (e + 1, epochs),
flush=True)
d.SetSplit(ecvl.SplitType.validation)
batch_time.reset()
end = time.time()
for b in range(num_batches_val):
n = 0
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, epochs, b + 1, num_batches_val),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
eddl.forward(model, [x])
output = eddl.getOutput(out)
sum_ = 0.0
for k in range(d.batch_size_):
result = output.select([str(k)])
target = y.select([str(k)])
ca = metric.value(target, result)
total_metric.append(ca)
sum_ += ca
"""
if args.out_dir:
result_a = np.array(result, copy=False)
target_a = np.array(target, copy=False)
classe = np.argmax(result_a).item()
gt_class = np.argmax(target_a).item()
single_image = eddlT.select(x, k)
img_t = ecvl.TensorToView(single_image)
img_t.colortype_ = ecvl.ColorType.BGR
single_image.mult_(255.)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s_gt_class_%s.png" % (head, gt_class)
cur_path = os.path.join(
current_path, d.classes_[classe], bname
)
ecvl.ImWrite(cur_path, img_t)
"""
n += 1
batch_time.update(time.time() - end)
end = time.time()
print("batch categorical accuracy:{}".format(sum_ / d.batch_size_),
flush=True)
print(batch_time, flush=True)
if (num_batches_val > 0):
total_avg = sum(total_metric) / len(total_metric)
print("Total categorical accuracy:{}".format(total_avg),
flush=True)
else:
print(
"Warning! \n "
"Please check your validation set size, it might be smaller than the batch size,\n "
"Validation test didn't execute as batch number is 0")
total_time.update(time.time() - end_total)
print(total_time, flush=True)
return model
def main(args):
num_classes = 8
size = [224, 224] # size of images
in_ = eddl.Input([3, size[0], size[1]])
out = VGG16(in_, num_classes)
net = eddl.Model([in_], [out])
eddl.build(net, eddl.sgd(0.001, 0.9), ["soft_cross_entropy"],
["categorical_accuracy"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "skin_lesion_classification_inference")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
dataset_augs = ecvl.DatasetAugmentations([training_augs, None, test_augs])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs)
if args.out_dir:
for c in d.classes_:
os.makedirs(os.path.join(args.out_dir, c), exist_ok=True)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, len(d.classes_)])
d.SetSplit(ecvl.SplitType.test)
num_samples = len(d.GetSplit())
num_batches = num_samples // args.batch_size
metric = eddl.getMetric("categorical_accuracy")
total_metric = []
if not os.path.exists(args.ckpts):
raise RuntimeError('Checkpoint "{}" not found'.format(args.ckpts))
eddl.load(net, args.ckpts, "bin")
print("Testing")
for b in range(num_batches):
n = 0
print("Batch {:d}/{:d}".format(b + 1, num_batches))
d.LoadBatch(x, y)
x.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out)
sum_ = 0.0
for j in range(args.batch_size):
result = output.select([str(j)])
target = y.select([str(j)])
ca = metric.value(target, result)
total_metric.append(ca)
sum_ += ca
if args.out_dir:
result_a = np.array(result, copy=False)
target_a = np.array(target, copy=False)
classe = np.argmax(result_a).item()
gt_class = np.argmax(target_a).item()
single_image = x.select([str(j)])
img_t = ecvl.TensorToView(single_image)
img_t.colortype_ = ecvl.ColorType.BGR
single_image.mult_(255.)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s_gt_class_%s.png" % (head, gt_class)
cur_path = os.path.join(args.out_dir, d.classes_[classe],
bname)
ecvl.ImWrite(cur_path, img_t)
n += 1
print("categorical_accuracy:", sum_ / args.batch_size)
total_avg = sum(total_metric) / len(total_metric)
print("Total categorical accuracy:", total_avg)
def main(args):
num_classes = 1
size = [192, 192] # size of images
thresh = 0.5
if args.out_dir:
os.makedirs(args.out_dir, exist_ok=True)
in_ = eddl.Input([3, size[0], size[1]])
out = SegNet(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
eddl.build(net, eddl.adam(0.0001), ["cross_entropy"],
["mean_squared_error"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "skin_lesion_segmentation_inference")
if not os.path.exists(args.ckpts):
raise RuntimeError('Checkpoint "{}" not found'.format(args.ckpts))
eddl.load(net, args.ckpts, "bin")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
])
dataset_augs = ecvl.DatasetAugmentations([training_augs, None, test_augs])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, d.n_channels_gt_, size[0], size[1]])
print("Testing")
d.SetSplit(ecvl.SplitType.test)
num_samples_test = len(d.GetSplit())
num_batches_test = num_samples_test // args.batch_size
evaluator = utils.Evaluator()
evaluator.ResetEval()
for b in range(num_batches_test):
n = 0
print("Batch {:d}/{:d} ".format(b + 1, num_batches_test),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
y.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out_sigm)
for k in range(args.batch_size):
img = output.select([str(k)])
gt = y.select([str(k)])
img_np, gt_np = np.array(img, copy=False), np.array(gt, copy=False)
iou = evaluator.BinaryIoU(img_np, gt_np, thresh=thresh)
print("- IoU: %.6g " % iou, end="", flush=True)
if args.out_dir:
# C++ BinaryIoU modifies image as a side effect
img_np[img_np >= thresh] = 1
img_np[img_np < thresh] = 0
img_t = ecvl.TensorToView(img)
img_t.colortype_ = ecvl.ColorType.GRAY
img_t.channels_ = "xyc"
img.mult_(255.)
# orig_img
orig_img = x.select([str(k)])
orig_img.mult_(255.)
orig_img_t = ecvl.TensorToImage(orig_img)
orig_img_t.colortype_ = ecvl.ColorType.BGR
orig_img_t.channels_ = "xyc"
tmp, labels = ecvl.Image.empty(), ecvl.Image.empty()
ecvl.CopyImage(img_t, tmp, ecvl.DataType.uint8)
ecvl.ConnectedComponentsLabeling(tmp, labels)
ecvl.CopyImage(labels, tmp, ecvl.DataType.uint8)
contours = ecvl.FindContours(tmp)
ecvl.CopyImage(orig_img_t, tmp, ecvl.DataType.uint8)
tmp_np = np.array(tmp, copy=False)
for cseq in contours:
for c in cseq:
tmp_np[c[0], c[1], 0] = 0
tmp_np[c[0], c[1], 1] = 0
tmp_np[c[0], c[1], 2] = 255
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s.png" % head
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, tmp)
gt_t = ecvl.TensorToView(gt)
gt_t.colortype_ = ecvl.ColorType.GRAY
gt_t.channels_ = "xyc"
gt.mult_(255.)
gt_filename = d.samples_[d.GetSplit()[n]].label_path_
gt_fn = os.path.join(args.out_dir,
os.path.basename(gt_filename))
ecvl.ImWrite(gt_fn, gt_t)
n += 1
print()
print("MIoU: %.6g" % evaluator.MeanMetric())
def main(args):
num_classes = 1
size = [192, 192] # size of images
thresh = 0.5
if args.out_dir:
os.makedirs(args.out_dir, exist_ok=True)
in_ = eddl.Input([3, size[0], size[1]])
out = SegNet(in_, num_classes)
out_sigm = eddl.Sigmoid(out)
net = eddl.Model([in_], [out_sigm])
eddl.build(net, eddl.adam(0.0001), ["cross_entropy"],
["mean_squared_error"],
eddl.CS_GPU([1]) if args.gpu else eddl.CS_CPU())
eddl.summary(net)
eddl.setlogfile(net, "skin_lesion_segmentation")
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(size),
ecvl.AugMirror(0.5),
ecvl.AugFlip(0.5),
ecvl.AugRotate([-180, 180]),
ecvl.AugAdditivePoissonNoise([0, 10]),
ecvl.AugGammaContrast([0.5, 1.5]),
ecvl.AugGaussianBlur([0, 0.8]),
ecvl.AugCoarseDropout([0, 0.3], [0.02, 0.05], 0.5)
])
validation_augs = ecvl.SequentialAugmentationContainer(
[ecvl.AugResizeDim(size)])
dataset_augs = ecvl.DatasetAugmentations(
[training_augs, validation_augs, None])
print("Reading dataset")
d = ecvl.DLDataset(args.in_ds, args.batch_size, dataset_augs)
x = Tensor([args.batch_size, d.n_channels_, size[0], size[1]])
y = Tensor([args.batch_size, d.n_channels_gt_, size[0], size[1]])
num_samples_train = len(d.GetSplit())
num_batches_train = num_samples_train // args.batch_size
d.SetSplit(ecvl.SplitType.validation)
num_samples_validation = len(d.GetSplit())
num_batches_validation = num_samples_validation // args.batch_size
indices = list(range(args.batch_size))
evaluator = utils.Evaluator()
print("Starting training")
for e in range(args.epochs):
print("Epoch {:d}/{:d} - Training".format(e + 1, args.epochs),
flush=True)
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(net)
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetAllBatches()
for b in range(num_batches_train):
print("Epoch {:d}/{:d} (batch {:d}/{:d}) - ".format(
e + 1, args.epochs, b + 1, num_batches_train),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
y.div_(255.0)
tx, ty = [x], [y]
eddl.train_batch(net, tx, ty, indices)
eddl.print_loss(net, b)
print()
print("Saving weights")
eddl.save(net, "isic_segmentation_checkpoint_epoch_%s.bin" % e, "bin")
d.SetSplit(ecvl.SplitType.validation)
evaluator.ResetEval()
print("Epoch %d/%d - Evaluation" % (e + 1, args.epochs), flush=True)
for b in range(num_batches_validation):
n = 0
print("Epoch {:d}/{:d} (batch {:d}/{:d}) ".format(
e + 1, args.epochs, b + 1, num_batches_validation),
end="",
flush=True)
d.LoadBatch(x, y)
x.div_(255.0)
y.div_(255.0)
eddl.forward(net, [x])
output = eddl.getOutput(out_sigm)
for k in range(args.batch_size):
img = output.select([str(k)])
gt = y.select([str(k)])
img_np = np.array(img, copy=False)
gt_np = np.array(gt, copy=False)
iou = evaluator.BinaryIoU(img_np, gt_np, thresh=thresh)
print("- IoU: %.6g " % iou, end="", flush=True)
if args.out_dir:
# C++ BinaryIoU modifies image as a side effect
img_np[img_np >= thresh] = 1
img_np[img_np < thresh] = 0
img_t = ecvl.TensorToView(img)
img_t.colortype_ = ecvl.ColorType.GRAY
img_t.channels_ = "xyc"
img.mult_(255.)
# orig_img
orig_img = x.select([str(k)])
orig_img.mult_(255.)
orig_img_t = ecvl.TensorToImage(orig_img)
orig_img_t.colortype_ = ecvl.ColorType.BGR
orig_img_t.channels_ = "xyc"
tmp, labels = ecvl.Image.empty(), ecvl.Image.empty()
ecvl.CopyImage(img_t, tmp, ecvl.DataType.uint8)
ecvl.ConnectedComponentsLabeling(tmp, labels)
ecvl.CopyImage(labels, tmp, ecvl.DataType.uint8)
contours = ecvl.FindContours(tmp)
ecvl.CopyImage(orig_img_t, tmp, ecvl.DataType.uint8)
tmp_np = np.array(tmp, copy=False)
for cseq in contours:
for c in cseq:
tmp_np[c[0], c[1], 0] = 0
tmp_np[c[0], c[1], 1] = 0
tmp_np[c[0], c[1], 2] = 255
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s.png" % head
output_fn = os.path.join(args.out_dir, bname)
ecvl.ImWrite(output_fn, tmp)
if e == 0:
gt_t = ecvl.TensorToView(gt)
gt_t.colortype_ = ecvl.ColorType.GRAY
gt_t.channels_ = "xyc"
gt.mult_(255.)
gt_filename = d.samples_[d.GetSplit()[n]].label_path_
gt_fn = os.path.join(args.out_dir,
os.path.basename(gt_filename))
ecvl.ImWrite(gt_fn, gt_t)
n += 1
print()
print("MIoU: %.6g" % evaluator.MeanMetric())
def main(args):
batch_size = args.batch_size
image_size = args.size, args.size
if args.weights:
os.makedirs(args.weights, exist_ok=True)
training_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(image_size, ecvl.InterpolationType.cubic),
ecvl.AugMirror(.5),
ecvl.AugFlip(.5),
ecvl.AugRotate([-180, 180]),
ecvl.AugAdditivePoissonNoise([0, 10]),
ecvl.AugGammaContrast([0.5, 1.5]),
ecvl.AugGaussianBlur([0, 0.8]),
ecvl.AugCoarseDropout([0, 0.03], [0.02, 0.05], 0.25),
ecvl.AugToFloat32(255),
])
validation_test_augs = ecvl.SequentialAugmentationContainer([
ecvl.AugResizeDim(image_size),
ecvl.AugToFloat32(255),
])
dataset_augs = ecvl.DatasetAugmentations(
[training_augs, validation_test_augs, validation_test_augs])
print('Reading dataset')
d = ecvl.DLDataset(args.in_ds,
args.batch_size,
dataset_augs,
ctype=ecvl.ColorType.RGB)
num_classes = len(d.classes_)
size = d.n_channels_, args.size, args.size
if args.ckpts:
net = eddl.import_net_from_onnx_file(args.ckpts, size)
else:
model_path = utils.DownloadModel(classification_zoo[args.model]['url'],
f'{args.model}.onnx', 'model_onnx')
net = eddl.import_net_from_onnx_file(model_path, size)
eddl.removeLayer(net, classification_zoo[args.model]
['to_remove']) # remove last Linear of resnet
top = eddl.getLayer(
net,
classification_zoo[args.model]['top']) # get flatten of resnet
out = eddl.Softmax(eddl.Dense(top, num_classes, True,
'classifier')) # true is for the bias
data_input = eddl.getLayer(
net, classification_zoo[args.model]['input']) # input of the onnx
net = eddl.Model([data_input], [out])
eddl.build(
net, eddl.adam(args.learning_rate), ['softmax_cross_entropy'],
['accuracy'],
eddl.CS_GPU(args.gpu, mem="low_mem") if args.gpu else eddl.CS_CPU(),
False)
out = eddl.getOut(net)[0]
if not args.ckpts:
eddl.initializeLayer(net, "classifier")
eddl.summary(net)
eddl.setlogfile(net, 'skin_lesion_classification')
x = Tensor([batch_size, *size])
y = Tensor([batch_size, num_classes])
metric_fn = eddl.getMetric('accuracy')
best_accuracy = 0.
if args.train:
num_samples_train = len(d.GetSplit())
num_batches_train = num_samples_train // args.batch_size
num_samples_val = len(d.GetSplit(ecvl.SplitType.validation))
num_batches_val = num_samples_val // args.batch_size
print('Starting training')
for e in range(args.epochs):
if args.out_dir:
current_path = os.path.join(args.out_dir, f'Epoch_{e}')
for c in d.classes_:
c_dir = os.path.join(current_path, c)
os.makedirs(c_dir, exist_ok=True)
d.SetSplit(ecvl.SplitType.training)
eddl.reset_loss(net)
s = d.GetSplit()
random.shuffle(s)
d.split_.training_ = s
d.ResetAllBatches()
for b in range(num_batches_train):
d.LoadBatch(x, y)
eddl.train_batch(net, [x], [y])
losses = eddl.get_losses(net)
metrics = eddl.get_metrics(net)
print(
f'Train - epoch [{e + 1}/{args.epochs}] - batch [{b + 1}/{num_batches_train}]'
f' - loss={losses[0]:.3f} - accuracy={metrics[0]:.3f}',
flush=True)
d.SetSplit(ecvl.SplitType.validation)
values = np.zeros(num_batches_val)
eddl.reset_loss(net)
for b in range(num_batches_val):
n = 0
d.LoadBatch(x, y)
eddl.forward(net, [x])
output = eddl.getOutput(out)
value = metric_fn.value(y, output)
values[b] = value
if args.out_dir:
for k in range(args.batch_size):
result = output.select([str(k)])
target = y.select([str(k)])
result_a = np.array(result, copy=False)
target_a = np.array(target, copy=False)
classe = np.argmax(result_a).item()
gt_class = np.argmax(target_a).item()
single_image = x.select([str(k)])
img_t = ecvl.TensorToView(single_image)
img_t.colortype_ = ecvl.ColorType.BGR
single_image.mult_(255.)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(
os.path.basename(filename))
bname = '{}_gt_class_{}.png'.format(head, gt_class)
cur_path = os.path.join(current_path,
d.classes_[classe], bname)
ecvl.ImWrite(cur_path, img_t)
n += 1
print(
f'Validation - epoch [{e + 1}/{args.epochs}] - batch [{b + 1}/{num_batches_val}] -'
f' accuracy={np.mean(values[:b + 1] / batch_size):.3f}')
last_accuracy = np.mean(values / batch_size)
print(
f'Validation - epoch [{e + 1}/{args.epochs}] - total accuracy={last_accuracy:.3f}'
)
if last_accuracy > best_accuracy:
best_accuracy = last_accuracy
print('Saving weights')
eddl.save_net_to_onnx_file(
net,
f'isic_classification_{args.model}_epoch_{e + 1}.onnx')
elif args.test:
d.SetSplit(ecvl.SplitType.test)
num_samples_test = len(d.GetSplit())
num_batches_test = num_samples_test // batch_size
values = np.zeros(num_batches_test)
eddl.reset_loss(net)
for b in range(num_batches_test):
d.LoadBatch(x, y)
eddl.forward(net, [x])
output = eddl.getOutput(out)
value = metric_fn.value(y, output)
values[b] = value
if args.out_dir:
n = 0
for k in range(args.batch_size):
result = output.select([str(k)])
target = y.select([str(k)])
result_a = np.array(result, copy=False)
target_a = np.array(target, copy=False)
classe = np.argmax(result_a).item()
gt_class = np.argmax(target_a).item()
single_image = x.select([str(k)])
img_t = ecvl.TensorToView(single_image)
img_t.colortype_ = ecvl.ColorType.BGR
single_image.mult_(255.)
filename = d.samples_[d.GetSplit()[n]].location_[0]
head, tail = os.path.splitext(os.path.basename(filename))
bname = "%s_gt_class_%s.png" % (head, gt_class)
cur_path = os.path.join(args.out_dir, d.classes_[classe],
bname)
ecvl.ImWrite(cur_path, img_t)
n += 1
print(
f'Test - batch [{b + 1}/{num_batches_test}] - accuracy={np.mean(values[:b + 1] / batch_size):.3f}'
)
print(f'Test - total accuracy={np.mean(values / batch_size):.3f}')