#'mean_categorical_crossentropy': mean_categorical_crossentropy})
'flatten_categorical_crossentropy':
flatten_categorical_crossentropy(classes=21)
})
print(model.summary())
for fn in dataload.filenames[:10]:
x = dataload.load_img(fn)
x = datagen.standardize(x)
print(x.min(), x.max())
X = x[np.newaxis, ...]
label = dataload.load_seg(fn)
label = np.squeeze(label, axis=-1).astype('int')
y_enc = np.eye(21)[label]
y_true = y_enc[np.newaxis, ...]
result = model.evaluate(X, y_true)
y_pred = model.predict(X)
print(np.unique(y_true), np.unique(y_pred))
loss = mean_categorical_crossentropy(K.variable(y_true),
K.variable(y_pred))
print(y_true.shape, y_pred.shape)
print(result, K.eval(loss))
pred = np.argmax(y_pred, axis=-1)
pred = pred[..., np.newaxis]
pred = np.squeeze(pred, axis=0)
print(np.unique(label), np.unique(pred))
print(np.size(label), np.sum(label != 0))
dataload.save(x, pred, fn)
import datetime
import numpy as np
from keras.models import load_model
from voc_generator import PascalVocGenerator, ImageSetLoader
import yaml
with open("init_args.yml", 'r') as stream:
try:
init_args = yaml.load(stream)
except yaml.YAMLError as exc:
print(exc)
datagen = PascalVocGenerator(**init_args['pascal_voc_generator']['test'])
dataload = ImageSetLoader(**init_args['image_set_loader']['test'])
weights = 'weights.h5'
model = load_model(weights)
for fn in dataload.filenames:
x = dataload.load_img(fn)
x = datagen.standardize(x)
y = model.predict(x)
dataload.save(x, y, fn)