def main(model_uri, data_path):
print("Options:")
for k, v in locals().items():
print(f" {k}: {v}")
data = utils.get_prediction_data(data_path)
print("data.type:", type(data))
print("data.shape:", data.shape)
print("\n**** mlflow.keras.load_model\n")
model = mlflow.keras.load_model(model_uri)
print("model:", type(model))
print("\n== model.predict")
predictions = model.predict(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
#print("predictions:", predictions)
utils.display_predictions(predictions)
print("\n== model.predict_classes")
predictions = model.predict_classes(data)
print("predictions.type:", type(predictions))
print("predictions.shape:", predictions.shape)
utils.display_predictions(predictions)
utils.predict_pyfunc(model_uri, data)
for x, y in indices:
if mask[x + PATCH_SIZE // 2, y + PATCH_SIZE // 2] is not 0:
mask[x + PATCH_SIZE // 2,
y + PATCH_SIZE // 2] = gt[x + PATCH_SIZE // 2,
y + PATCH_SIZE // 2]
train_gt = mask
# ----------------------------------------------------------------------------------
test_gt = gt # all of sample to be test sample
# -----------------------------------------------------------------------------------------------------
print("{} samples selected (over {})".format(np.count_nonzero(train_gt),
np.count_nonzero(gt)))
print("Running an experiment with the {} model".format(MODEL),
"run {}/{}".format(run + 1, N_RUNS))
display_predictions(convert_to_color(train_gt),
viz,
caption="Train ground truth")
display_predictions(convert_to_color(test_gt),
viz,
caption="Test ground truth")
if MODEL == 'SGD':
X_train, y_train = build_dataset(img,
train_gt,
ignored_labels=IGNORED_LABELS)
X_train, y_train = sklearn.utils.shuffle(X_train, y_train)
scaler = sklearn.preprocessing.StandardScaler()
X_train = scaler.fit_transform(X_train)
class_weight = 'balanced' if CLASS_BALANCING else None
clf = sklearn.linear_model.SGDClassifier(class_weight=class_weight,
learning_rate='optimal',
# Serve predictions with pyfunc flavor
import sys
import mlflow
import mlflow.pyfunc
import utils
print("MLflow Version:", mlflow.__version__)
if __name__ == "__main__":
if len(sys.argv) < 1:
print("ERROR: Expecting MODEL_URI PREDICTION_FILE")
sys.exit(1)
model_uri = sys.argv[1]
data_path = sys.argv[2] if len(
sys.argv) > 2 else "../../data/wine-quality-white.csv"
print("data_path:", data_path)
print("model_uri:", model_uri)
model = mlflow.pyfunc.load_model(model_uri)
print("model:", type(model))
data = utils.read_prediction_data(data_path)
predictions = model.predict(data)
utils.display_predictions(predictions)
def main(raw_args=None):
parser = argparse.ArgumentParser(
description="Hyperspectral image classification with FixMatch")
parser.add_argument(
'--patch_size',
type=int,
default=5,
help='Size of patch around each pixel taken for classification')
parser.add_argument(
'--center_pixel',
action='store_false',
help=
'use if you only want to consider the label of the center pixel of a patch'
)
parser.add_argument('--batch_size',
type=int,
default=10,
help='Size of each batch for training')
parser.add_argument('--epochs',
type=int,
default=10,
help='number of total epochs of training to run')
parser.add_argument('--dataset',
type=str,
default='Salinas',
help='Name of dataset to run, Salinas or PaviaU')
parser.add_argument('--cuda',
type=int,
default=-1,
help='what CUDA device to run on, -1 defaults to cpu')
parser.add_argument('--warmup',
type=float,
default=0,
help='warmup epochs')
parser.add_argument('--save',
action='store_true',
help='use to save model weights when running')
parser.add_argument(
'--test_stride',
type=int,
default=1,
help='length of stride when sliding patch window over image for testing'
)
parser.add_argument(
'--sampling_percentage',
type=float,
default=0.3,
help=
'percentage of dataset to sample for training (labeled and unlabeled included)'
)
parser.add_argument(
'--sampling_mode',
type=str,
default='nalepa',
help='how to sample data, disjoint, random, nalepa, or fixed')
parser.add_argument('--lr',
type=float,
default=0.001,
help='initial learning rate')
parser.add_argument('--alpha',
type=float,
default=1.0,
help='beta distribution range')
parser.add_argument(
'--class_balancing',
action='store_false',
help='use to balance weights according to ratio in dataset')
parser.add_argument(
'--checkpoint',
type=str,
default=None,
help='use to load model weights from a certain directory')
#Augmentation arguments
parser.add_argument('--flip_augmentation',
action='store_true',
help='use to flip augmentation data for use')
parser.add_argument('--radiation_augmentation',
action='store_true',
help='use to radiation noise data for use')
parser.add_argument('--mixture_augmentation',
action='store_true',
help='use to mixture noise data for use')
parser.add_argument('--pca_augmentation',
action='store_true',
help='use to pca augment data for use')
parser.add_argument(
'--pca_strength',
type=float,
default=1.0,
help='Strength of the PCA augmentation, defaults to 1.')
parser.add_argument('--cutout_spatial',
action='store_true',
help='use to cutout spatial for data augmentation')
parser.add_argument('--cutout_spectral',
action='store_true',
help='use to cutout spectral for data augmentation')
parser.add_argument(
'--augmentation_magnitude',
type=int,
default=1,
help=
'Magnitude of augmentation (so far only for cutout). Defualts to 1, min 1 and max 10.'
)
parser.add_argument('--spatial_combinations',
action='store_true',
help='use to spatial combine for data augmentation')
parser.add_argument('--spectral_mean',
action='store_true',
help='use to spectal mean for data augmentation')
parser.add_argument(
'--moving_average',
action='store_true',
help='use to sprectral moving average for data augmentation')
parser.add_argument('--results',
type=str,
default='results',
help='where to save results to (default results)')
parser.add_argument('--save_dir',
type=str,
default='/saves/',
help='where to save models to (default /saves/)')
parser.add_argument('--data_dir',
type=str,
default='/data/',
help='where to fetch data from (default /data/)')
parser.add_argument('--load_file',
type=str,
default=None,
help='wihch file to load weights from (default None)')
parser.add_argument(
'--fold',
type=int,
default=0,
help='Which fold to sample from if using Nalepas validation scheme')
parser.add_argument(
'--sampling_fixed',
type=str,
default='True',
help=
'Use to sample a fixed amount of samples for each class from Nalepa sampling'
)
parser.add_argument(
'--samples_per_class',
type=int,
default=10,
help=
'Amount of samples to sample for each class when sampling a fixed amount. Defaults to 10.'
)
parser.add_argument(
'--supervision',
type=str,
default='full',
help=
'check this more, use to make us of all labeled or not, full or semi')
args = parser.parse_args(raw_args)
device = utils.get_device(args.cuda)
args.device = device
#vis = visdom.Visdom()
vis = None
tensorboard_dir = str(args.results + '/' +
datetime.datetime.now().strftime("%m-%d-%X"))
os.makedirs(tensorboard_dir, exist_ok=True)
writer = SummaryWriter(tensorboard_dir)
if args.sampling_mode == 'nalepa':
train_img, train_gt, test_img, test_gt, label_values, ignored_labels, rgb_bands, palette = get_patch_data(
args.dataset,
args.patch_size,
target_folder=args.data_dir,
fold=args.fold)
args.n_bands = train_img.shape[-1]
else:
img, gt, label_values, ignored_labels, rgb_bands, palette = get_dataset(
args.dataset, target_folder=args.data_dir)
args.n_bands = img.shape[-1]
args.n_classes = len(label_values) - len(ignored_labels)
args.ignored_labels = ignored_labels
if palette is None:
# Generate color palette
palette = {0: (0, 0, 0)}
for k, color in enumerate(
sns.color_palette("hls",
len(label_values) - 1)):
palette[k + 1] = tuple(
np.asarray(255 * np.array(color), dtype='uint8'))
invert_palette = {v: k for k, v in palette.items()}
def convert_to_color(x):
return utils.convert_to_color_(x, palette=palette)
def convert_from_color(x):
return utils.convert_from_color_(x, palette=invert_palette)
if args.sampling_mode == 'nalepa':
print("{} samples selected (over {})".format(
np.count_nonzero(train_gt),
np.count_nonzero(train_gt) + np.count_nonzero(test_gt)))
writer.add_text(
'Amount of training samples',
"{} samples selected (over {})".format(np.count_nonzero(train_gt),
np.count_nonzero(test_gt)))
utils.display_predictions(convert_to_color(test_gt),
vis,
writer=writer,
caption="Test ground truth")
else:
train_gt, test_gt = utils.sample_gt(gt,
args.sampling_percentage,
mode=args.sampling_mode)
print("{} samples selected (over {})".format(
np.count_nonzero(train_gt), np.count_nonzero(gt)))
writer.add_text(
'Amount of training samples',
"{} samples selected (over {})".format(np.count_nonzero(train_gt),
np.count_nonzero(gt)))
utils.display_predictions(convert_to_color(train_gt),
vis,
writer=writer,
caption="Train ground truth")
utils.display_predictions(convert_to_color(test_gt),
vis,
writer=writer,
caption="Test ground truth")
model = HamidaEtAl(args.n_bands,
args.n_classes,
patch_size=args.patch_size)
optimizer = optim.SGD(model.parameters(),
lr=args.lr,
momentum=0.9,
nesterov=True,
weight_decay=0.0005)
#loss_labeled = nn.CrossEntropyLoss(weight=weights)
#loss_unlabeled = nn.CrossEntropyLoss(weight=weights, reduction='none')
if args.sampling_mode == 'nalepa':
#Get fixed amount of random samples for validation
idx_sup, idx_val, idx_unsup = get_pixel_idx(train_img, train_gt,
args.ignored_labels,
args.patch_size)
if args.sampling_fixed == 'True':
unique_labels = np.zeros(len(label_values))
new_idx_sup = []
index = 0
for p, x, y in idx_sup:
label = train_gt[p, x, y]
if unique_labels[label] < args.samples_per_class:
unique_labels[label] += 1
new_idx_sup.append([p, x, y])
np.delete(idx_sup, index)
index += 1
idx_unsup = np.concatenate((idx_sup, idx_unsup))
idx_sup = np.asarray(new_idx_sup)
writer.add_text(
'Amount of labeled training samples',
"{} samples selected (over {})".format(idx_sup.shape[0],
np.count_nonzero(train_gt)))
train_labeled_gt = [
train_gt[p_l, x_l, y_l] for p_l, x_l, y_l in idx_sup
]
samples_class = np.zeros(args.n_classes)
for c in np.unique(train_labeled_gt):
samples_class[c - 1] = np.count_nonzero(train_labeled_gt == c)
writer.add_text('Labeled samples per class', str(samples_class))
print('Labeled samples per class: ' + str(samples_class))
val_dataset = HyperX_patches(train_img,
train_gt,
idx_val,
labeled='Val',
**vars(args))
val_loader = data.DataLoader(val_dataset, batch_size=args.batch_size)
train_dataset = HyperX_patches(train_img,
train_gt,
idx_sup,
labeled=True,
**vars(args))
train_loader = data.DataLoader(
train_dataset,
batch_size=args.batch_size,
#pin_memory=True, num_workers=5,
shuffle=True,
drop_last=True)
amount_labeled = idx_sup.shape[0]
else:
train_labeled_gt, val_gt = utils.sample_gt(train_gt,
0.95,
mode=args.sampling_mode)
val_dataset = HyperX(img, val_gt, labeled='Val', **vars(args))
val_loader = data.DataLoader(val_dataset, batch_size=args.batch_size)
writer.add_text(
'Amount of labeled training samples',
"{} samples selected (over {})".format(
np.count_nonzero(train_labeled_gt),
np.count_nonzero(train_gt)))
samples_class = np.zeros(args.n_classes)
for c in np.unique(train_labeled_gt):
samples_class[c - 1] = np.count_nonzero(train_labeled_gt == c)
writer.add_text('Labeled samples per class', str(samples_class))
train_dataset = HyperX(img,
train_labeled_gt,
labeled=True,
**vars(args))
train_loader = data.DataLoader(train_dataset,
batch_size=args.batch_size,
pin_memory=True,
num_workers=5,
shuffle=True,
drop_last=True)
utils.display_predictions(convert_to_color(train_labeled_gt),
vis,
writer=writer,
caption="Labeled train ground truth")
utils.display_predictions(convert_to_color(val_gt),
vis,
writer=writer,
caption="Validation ground truth")
amount_labeled = np.count_nonzero(train_labeled_gt)
args.iterations = amount_labeled // args.batch_size
args.total_steps = args.iterations * args.epochs
args.scheduler = get_cosine_schedule_with_warmup(
optimizer, args.warmup * args.iterations, args.total_steps)
if args.class_balancing:
weights_balance = utils.compute_imf_weights(train_gt,
len(label_values),
args.ignored_labels)
args.weights = torch.from_numpy(weights_balance[1:])
args.weights = args.weights.to(torch.float32)
else:
weights = torch.ones(args.n_classes)
#weights[torch.LongTensor(args.ignored_labels)] = 0
args.weights = weights
args.weights = args.weights.to(args.device)
criterion = nn.CrossEntropyLoss(weight=args.weights)
loss_val = nn.CrossEntropyLoss(weight=args.weights)
print(args)
print("Network :")
writer.add_text('Arguments', str(args))
with torch.no_grad():
for input, _ in train_loader:
break
#summary(model.to(device), input.size()[1:])
#writer.add_graph(model.to(device), input)
# We would like to use device=hyperparams['device'] altough we have
# to wait for torchsummary to be fixed first.
if args.load_file is not None:
model.load_state_dict(torch.load(args.load_file))
model.zero_grad()
try:
train(model,
optimizer,
criterion,
loss_val,
train_loader,
writer,
args,
val_loader=val_loader,
display=vis)
except KeyboardInterrupt:
# Allow the user to stop the training
pass
if args.sampling_mode == 'nalepa':
probabilities = test(model, test_img, args)
else:
probabilities = test(model, img, args)
prediction = np.argmax(probabilities, axis=-1)
run_results = utils.metrics(prediction,
test_gt,
ignored_labels=args.ignored_labels,
n_classes=args.n_classes)
mask = np.zeros(test_gt.shape, dtype='bool')
for l in args.ignored_labels:
mask[test_gt == l] = True
prediction += 1
prediction[mask] = 0
color_prediction = convert_to_color(prediction)
utils.display_predictions(color_prediction,
vis,
gt=convert_to_color(test_gt),
writer=writer,
caption="Prediction vs. test ground truth")
utils.show_results(run_results,
vis,
writer=writer,
label_values=label_values)
writer.close()
return run_results
print("loader.type:", type(loader))
data = utils.prep_data(loader)
print("data.type:", type(data))
print("data.shape:", data.shape)
print("\n**** pytorch.load_model")
model_uri = f"runs:/{args.run_id}/pytorch-model"
model = mlflow.pytorch.load_model(model_uri)
print("model.type:", type(model))
outputs = model(data)
print("outputs.type:", type(outputs))
outputs = outputs.detach().numpy()
print("outputs.shape:", outputs.shape)
utils.display_predictions(outputs)
# TODO: convert tensor to Pyfunc scoring format
if args.score_as_pyfunc:
print("\n**** pyfunc.load_model")
model = mlflow.pyfunc.load_model(model_uri)
print("model.type:", type(model))
data_pd = pd.DataFrame(
data.numpy()) # TODO: ValueError: Must pass 2-d input
outputs = model.predict(data_pd)
print("outputs.type:", type(outputs))
if args.score_as_onnx:
print("\n**** onnx.load_model - onnx\n")
import mlflow.onnx
import onnx
def main(args):
obj=Detector(param)
"""
#detections = obj.run_on_video("samples/test_video.mp4",
# display=True,
# write_annotations=True)
"""
"""
# -------------------------------
# ------ Run on single image ----
# -------------------------------
IMG_PATH="samples/data/data/env1_m30_view/env1_m30_view_01422.png"
img = cv2.imread(IMG_PATH)
predictions = obj.run_on_image(IMG_PATH, display=False, show_mask=False)
disp = display_predictions(img, predictions, min_score_threshold=0.05)
cv2.imwrite("res.jpg", disp)
filtered_predictions = filter_out_predictions(predictions, iou_threshold=0.5, min_score_threshold=0.05)
disp = display_predictions(img, filtered_predictions, min_score_threshold=0.05)
cv2.imwrite("res_filterd.jpg", disp)
# -------------------------------
"""
# -------------------------------
# ------ Run on image folder ----
# -------------------------------
"""
folder_names = ["env1_m30_view",
"env1_m45_view",
"env2_m30_view",
"env2_m45_view",
"env3_m30_view",
"env3_m45_view"]
"""
folder_names = ["/home/ilkerbozcan/repos/uav-indoor-anomaly-detection/test_data/test1",
"/home/ilkerbozcan/repos/uav-indoor-anomaly-detection/test_data/test2",
"/home/ilkerbozcan/repos/uav-indoor-anomaly-detection/test_data/test3",
"/home/ilkerbozcan/repos/uav-indoor-anomaly-detection/test_data/test4"]
for folder_name in folder_names:
os.mkdir(folder_name+"_out")
results = obj.run_on_image_folder(path_to_folder=folder_name,
save_dir="./",
display=False,
show_mask=False)
i=0
filtered_results=[]
for predictions in results:
img = cv2.imread(predictions['img_name'])
filtered_predictions = filter_out_predictions(predictions, iou_threshold=0.5, min_score_threshold=0.5)
disp = display_predictions(img, filtered_predictions, min_score_threshold=0.5)
cv2.imwrite(folder_name+"_out/"+str(i)+".png", disp)
i += 1
print(i)
filtered_results.append(filtered_predictions)
# -------------------------------
print(filtered_results)
with open(folder_name+"/"+"annotations.json", 'w+') as f:
json.dump(filtered_results, f)
