def segmentation(model, input_path, output_path):
if model == "scene_parsing":
model = pretrained.pspnet_50_ADE_20K()
elif model == "cityscapes":
model = pretrained.pspnet_101_cityscapes()
else:
model == pretrained.pspnet_101_voc12()
model.predict_segmentation(inp=input_path, out_fname=output_path)
def get_segmentation_model(model_type, freeze=True):
x = None
segmentation_model = None
if model_type == "three_class_trained":
segmentation_model = model_from_checkpoint_path(
three_class_checkpoints_path)
elif model_type == "seven_class_trained":
segmentation_model = model_from_checkpoint_path(
seven_class_checkpoints_path)
x = segmentation_model.get_layer("conv2d_6").output
elif model_type == "pretrained":
segmentation_model = pspnet_101_cityscapes()
x = segmentation_model.get_layer("activation_107").output
elif model_type == "seven_class_vanilla_psp":
segmentation_model = model_from_checkpoint_path(
seven_class_vanilla_psp_path)
x = segmentation_model.get_layer("activation_10").output
elif model_type == "seven_class_vanilla_psp_depth":
from utils.pspnet import model_from_checkpoint_path as custom_model_from_checkpoint_path
segmentation_model = custom_model_from_checkpoint_path(
seven_class_vanilla_psp_depth_path)
x = segmentation_model.get_layer("activation_10").output
elif model_type == "seven_class_mobile":
segmentation_model = model_from_checkpoint_path(
seven_class_mobile_checkpoints_path)
output_layer = get_layer_with_name(segmentation_model,
"conv_dw_6_relu")
x = output_layer.output
elif model_type == "resnet50_pspnet_8_classes":
segmentation_model = model_from_checkpoint_path(
resnet50_pspnet_8_classes)
output_layer = segmentation_model.get_layer(name="conv2d_6")
x = output_layer.output
plot_model(segmentation_model, "segmentation_model.png", show_shapes=True)
# Explicitly define new model input and output by slicing out old model layers
model_new = Model(inputs=segmentation_model.layers[0].input, outputs=x)
if freeze:
for layer in model_new.layers:
layer.trainable = False
return model_new
def main(opt):
model = pspnet_101_cityscapes()
files = sorted(os.listdir(opt.src_rgb))
print(f"Total: {len(files)}")
if 500 * (opt.part + 1) < len(files):
partial = files[500 * opt.part:500 * (opt.part + 1)]
print(f"Processing from {500*opt.part} to {500*(opt.part+1)} ...")
else:
partial = files[500 * opt.part:]
print(f"Processing from {500*opt.part} to {len(files)} ...")
for f in tqdm(partial):
out = model.predict_segmentation(inp=os.path.join(opt.src_rgb, f),
out_fname=os.path.join(
opt.out_dir, f))
def predict(images, predictions, pretrained, entire_image, checkpoint_dir):
if pretrained:
model = pspnet_101_cityscapes(
) # load the pretrained model trained on Cityscapes dataset
else:
model = model_from_checkpoint_path(normpath(checkpoint_dir))
files = [f for f in listdir(images) if isfile(join(images, f))]
for file in files:
name, ext = splitext(file)
if entire_image:
predict_standard(model,
inp=f'{images}{file}',
out_fname=f'{predictions}{name}.png')
else:
predict_split(model,
inp=f'{images}{file}',
out_fname=f'{predictions}{name}.png')
# -*- coding: utf-8 -*-
import os
################ CPU only ##############
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
########################################
from keras_segmentation.models.model_utils import transfer_weights
from keras_segmentation.pretrained import resnet_pspnet_VOC12_v0_1, pspnet_101_cityscapes
from keras_segmentation.models.pspnet import resnet50_pspnet, pspnet_101
n_classes = 2
#model = vgg_unet(n_classes=n_classes , input_height=512, input_width=512)
pred_dir = '/home/GDDC-CV1/Desktop/data_1024/pred_x_presentation/'
out_dir = '/home/GDDC-CV1/Desktop/pred_out_pred-function'
checkpoints_path = '/home/GDDC-CV1/Desktop/CV-Semantic-Segmentation/model_transfer_learning/checkpoint/'
pretrained_model = pspnet_101_cityscapes()
new_model = pspnet_101(n_classes=n_classes)
transfer_weights(pretrained_model, new_model)
model = pspnet_101(n_classes=n_classes)
out = model.predict_multiple(inp_dir=pred_dir,
out_dir=out_dir,
checkpoints_path=checkpoints_path)
'''
model=None, inps=None, inp_dir=None, out_dir=None,
checkpoints_path=None, overlay_img=False,
class_names=None, show_legends=False, colors=class_colors,
prediction_width=None, prediction_height=None)
'''
from keras_segmentation.pretrained import pspnet_101_cityscapes
model = pspnet_101_cityscapes() # load the pretrained model trained on Cityscapes dataset
out = model.predict_segmentation(
inp="cam6_eletric_0005.jpg",
out_fname="out.png"
)