def __init__(self):
batch_size = 32
self.image_size = (300, 300, 3)
n_classes = 80
mode = 'inference_fast'
l2_regularization = 0.0005
min_scale = 0.1 # None
max_scale = 0.9 # None
scales = None # [0.07, 0.15, 0.33, 0.51, 0.69, 0.87, 1.05]
aspect_ratios_global = None
aspect_ratios_per_layer = [[1.0, 2.0, 0.5], [1.0, 2.0, 0.5, 3.0, 1.0 / 3.0], [1.0, 2.0, 0.5, 3.0, 1.0 / 3.0],
[1.0, 2.0, 0.5, 3.0, 1.0 / 3.0], [1.0, 2.0, 0.5], [1.0, 2.0, 0.5]]
two_boxes_for_ar1 = True
steps = None # [8, 16, 32, 64, 100, 300]
offsets = None # [0.5, 0.5, 0.5, 0.5, 0.5, 0.5]
clip_boxes = True
variances = [0.1, 0.1, 0.2, 0.2]
coords = 'centroids'
normalize_coords = True
subtract_mean = [123, 117, 104]
divide_by_stddev = 128
swap_channels = None
confidence_thresh = 0.7
iou_threshold = 0.45
top_k = 1
nms_max_output_size = 400
return_predictor_sizes = False
model = mobilenet_v2_ssd(self.image_size, n_classes, mode, l2_regularization, min_scale, max_scale, scales,
aspect_ratios_global, aspect_ratios_per_layer, two_boxes_for_ar1, steps,
offsets, clip_boxes, variances, coords, normalize_coords, subtract_mean,
divide_by_stddev, swap_channels, confidence_thresh, iou_threshold, top_k,
nms_max_output_size, return_predictor_sizes)
# 2: Load the trained weights into the model.
weights_path = os.path.join("pretrained_weights", "ssdlite_coco_loss-4.8205_val_loss-4.1873.h5")
model.load_weights(weights_path, by_name=True)
# 3: Compile the model so that Keras won't complain the next time you load it.
adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)
model.compile(optimizer=adam, loss=ssd_loss.compute_loss)
self.model = model
variances = [0.1, 0.1, 0.2, 0.2]
coords = 'centroids'
normalize_coords = True
subtract_mean = [123, 117, 104]
divide_by_stddev = 128
swap_channels = None
confidence_thresh = 0.01
iou_threshold = 0.45
top_k = 200
nms_max_output_size = 400
return_predictor_sizes = False
model = mobilenet_v2_ssd(image_size, n_classes, mode, l2_regularization,
min_scale, max_scale, scales, aspect_ratios_global,
aspect_ratios_per_layer, two_boxes_for_ar1, steps,
offsets, clip_boxes, variances, coords,
normalize_coords, subtract_mean, divide_by_stddev,
swap_channels, confidence_thresh, iou_threshold,
top_k, nms_max_output_size, return_predictor_sizes)
# 2: Load the trained weights into the model.
# weights_path = '../pretrained_weights/ssdlite_coco_loss-4.8205_val_loss-4.1873.h5'
weights_path = os.path.join("..", "pretrained_weights",
"ssdlite_coco_loss-4.8205_val_loss-4.1873.h5")
model.load_weights(weights_path, by_name=True)
# 3: Compile the model so that Keras won't complain the next time you load it.
adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)
model.compile(optimizer=adam, loss=ssd_loss.compute_loss)
def train(self):
# build model
model = mobilenet_v2_ssd(self.training_config)
# load weights
model.load_weights(self.weights_path, by_name=True)
# compile the model
adam = Adam(lr=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=0.0)
ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)
# set_trainable(r"(ssd\_[cls|box].*)", model)
model.compile(optimizer=adam, loss=ssd_loss.compute_loss)
print(model.summary())
# load data
train_dataset = DataGenerator(load_images_into_memory=False,
hdf5_dataset_path=None)
val_dataset = DataGenerator(load_images_into_memory=False,
hdf5_dataset_path=None)
train_dataset.parse_json(
images_dirs=[self.train_dir],
annotations_filenames=[self.train_annotations],
ground_truth_available=True,
include_classes='all',
ret=False)
val_dataset.parse_json(images_dirs=[self.val_dir],
annotations_filenames=[self.val_annotations],
ground_truth_available=True,
include_classes='all',
ret=False)
# We need the `classes_to_cats` dictionary. Read the documentation of this function to understand why.
cats_to_classes, classes_to_cats, cats_to_names, classes_to_names = get_coco_category_maps(
train_annotations_filename)
# set the image transformations for pre-processing and data augmentation options.
# For the training generator:
ssd_data_augmentation = SSDDataAugmentation(img_height=image_size[0],
img_width=image_size[1],
background=subtract_mean)
# For the validation generator:
convert_to_3_channels = ConvertTo3Channels()
resize = Resize(height=image_size[0], width=image_size[1])
# instantiate an encoder that can encode ground truth labels into the format needed by the SSD loss function.
# The encoder constructor needs the spatial dimensions of the model's predictor layers to create the anchor boxes.
predictor_sizes = [
model.get_layer('ssd_cls1conv2_bn').output_shape[1:3],
model.get_layer('ssd_cls2conv2_bn').output_shape[1:3],
model.get_layer('ssd_cls3conv2_bn').output_shape[1:3],
model.get_layer('ssd_cls4conv2_bn').output_shape[1:3],
model.get_layer('ssd_cls5conv2_bn').output_shape[1:3],
model.get_layer('ssd_cls6conv2_bn').output_shape[1:3]
]
ssd_input_encoder = SSDInputEncoder(
img_height=image_size[0],
img_width=image_size[1],
n_classes=n_classes,
predictor_sizes=predictor_sizes,
scales=scales,
aspect_ratios_per_layer=aspect_ratios_per_layer,
two_boxes_for_ar1=two_boxes_for_ar1,
steps=steps,
offsets=offsets,
clip_boxes=clip_boxes,
variances=variances,
matching_type='multi',
pos_iou_threshold=0.5,
neg_iou_limit=0.3,
normalize_coords=normalize_coords)
# create the generator handles that will be passed to Keras' `fit_generator()` function.
train_generator = train_dataset.generate(
batch_size=batch_size,
shuffle=True,
transformations=[ssd_data_augmentation],
label_encoder=ssd_input_encoder,
returns={'processed_images', 'encoded_labels'},
keep_images_without_gt=False)
val_generator = val_dataset.generate(
batch_size=batch_size,
shuffle=False,
transformations=[convert_to_3_channels, resize],
label_encoder=ssd_input_encoder,
returns={'processed_images', 'encoded_labels'},
keep_images_without_gt=False)
# Get the number of samples in the training and validations datasets.
train_dataset_size = train_dataset.get_dataset_size()
val_dataset_size = val_dataset.get_dataset_size()
print("Number of images in the training dataset:\t{:>6}".format(
train_dataset_size))
print("Number of images in the validation dataset:\t{:>6}".format(
val_dataset_size))
callbacks = [
LearningRateScheduler(schedule=lr_schedule, verbose=1),
TensorBoard(log_dir=log_dir,
histogram_freq=0,
write_graph=True,
write_images=False),
ModelCheckpoint(os.path.join(
log_dir,
"ssdseg_coco_{epoch:02d}_loss-{loss:.4f}_val_loss-{val_loss:.4f}.h5"
),
monitor='val_loss',
verbose=1,
save_best_only=True,
save_weights_only=True)
]
model.fit_generator(train_generator,
epochs=1000,
steps_per_epoch=1000,
callbacks=callbacks,
validation_data=val_generator,
validation_steps=100,
initial_epoch=0)