def test_as_random_patches(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
my_images = ImageTable.load_files(self.s, path=self.data_dir+'giraffe_dolphin_small')
out = my_images.as_random_patches(x=0, y=0, width=200, height=200, step_size=200,
output_width=100, output_height=100, inplace=False)
out = out.image_summary
column_list = ['jpg', 'minWidth', 'maxWidth', 'minHeight', 'maxHeight', 'meanWidth',
'meanHeight', 'mean1stChannel', 'min1stChannel', 'max1stChannel',
'mean2ndChannel', 'min2ndChannel', 'max2ndChannel', 'mean3rdChannel',
'min3rdChannel', 'max3rdChannel']
self.assertTrue(int(out[1]) == 100)
self.assertTrue(int(out[2]) == 100)
self.assertTrue(int(out[3]) == 100)
self.assertTrue(int(out[4]) == 100)
self.assertTrue(int(out[5]) == 100)
self.assertTrue(int(out[6]) == 100)
my_images = ImageTable.load_files(self.s, path=self.data_dir+'giraffe_dolphin_small')
out = my_images.as_random_patches(x=0, y=0, width=None, height=None, step_size=None,
output_width=None, output_height=None, inplace=False)
out = out.image_summary
column_list = ['jpg', 'minWidth', 'maxWidth', 'minHeight', 'maxHeight', 'meanWidth',
'meanHeight', 'mean1stChannel', 'min1stChannel', 'max1stChannel',
'mean2ndChannel', 'min2ndChannel', 'max2ndChannel', 'mean3rdChannel',
'min3rdChannel', 'max3rdChannel']
self.assertTrue(int(out[1]) == 224)
self.assertTrue(int(out[2]) == 224)
self.assertTrue(int(out[3]) == 224)
self.assertTrue(int(out[4]) == 224)
self.assertTrue(int(out[5]) == 224)
self.assertTrue(int(out[6]) == 224)
my_images = ImageTable.load_files(self.s, path=self.data_dir+'giraffe_dolphin_small')
out = my_images.as_random_patches(x=0, y=0, width=None, height=200, step_size=None,
output_width=None, output_height=None, inplace=False)
out = out.image_summary
column_list = ['jpg', 'minWidth', 'maxWidth', 'minHeight', 'maxHeight', 'meanWidth',
'meanHeight', 'mean1stChannel', 'min1stChannel', 'max1stChannel',
'mean2ndChannel', 'min2ndChannel', 'max2ndChannel', 'mean3rdChannel',
'min3rdChannel', 'max3rdChannel']
self.assertTrue(int(out[1]) == 200)
self.assertTrue(int(out[2]) == 200)
self.assertTrue(int(out[3]) == 200)
self.assertTrue(int(out[4]) == 200)
self.assertTrue(int(out[5]) == 200)
self.assertTrue(int(out[6]) == 200)
def test_captioning_table_3(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
if self.data_dir_local is None:
unittest.TestCase.skipTest(
self,
"DLPY_DATA_DIR_LOCAL is not set in the environment variables")
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=224)
captions_file = self.data_dir_local + 'image_captions.txt'
features_model = VGG16(self.s,
width=224,
height=224,
pre_trained_weights=True,
pre_trained_weights_file=self.data_dir +
'VGG_ILSVRC_16_layers.caffemodel.h5')
detection_model = Model(self.s)
detection_model.load(self.data_dir + 'YOLOV2_MULTISIZE.sashdat')
detection_model.load_weights(self.data_dir +
'YoloV2_Multisize_weights.sashdat')
word_embeddings = self.data_dir_local + 'word_embeddings.txt'
self.assertTrue(
create_captioning_table(self.s,
image_table,
features_model,
captions_file,
obj_detect_model=detection_model,
word_embeddings_file=word_embeddings)
is not None)
def test_load_images(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir+'giraffe_dolphin_small'
my_images = ImageTable.load_files(self.s, path=img_path)
self.assertTrue(len(my_images) > 0)
def test_captioning_table_1(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
file_dependency = self.data_dir + 'VGG_ILSVRC_16_layers.caffemodel.h5'
if not file_exist_on_server(self.s, file_dependency):
unittest.TestCase.skipTest(
self, "File, {}, not found.".format(file_dependency))
if self.data_dir_local is None:
unittest.TestCase.skipTest(
self,
"DLPY_DATA_DIR_LOCAL is not set in the environment variables")
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=224)
captions_file = self.data_dir_local + 'image_captions.txt'
features_model = VGG16(self.s,
width=224,
height=224,
pre_trained_weights=True,
pre_trained_weights_file=self.data_dir +
'VGG_ILSVRC_16_layers.caffemodel.h5')
self.assertTrue(
create_captioning_table(self.s, image_table, features_model,
captions_file) is not None)
def test_object_table_2(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
file_dependency = self.data_dir + 'YOLOV2_MULTISIZE.sashdat'
if not file_exist_on_server(self.s, file_dependency):
unittest.TestCase.skipTest(
self, "File, {}, not found.".format(file_dependency))
file_dependency = self.data_dir + 'YoloV2_Multisize_weights.sashdat'
if not file_exist_on_server(self.s, file_dependency):
unittest.TestCase.skipTest(
self, "File, {}, not found.".format(file_dependency))
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=416)
word_embeddings = self.data_dir + 'no_file.txt'
detection_model = Model(self.s)
detection_model.load(self.data_dir + 'YOLOV2_MULTISIZE.sashdat')
detection_model.load_weights(self.data_dir +
'YoloV2_Multisize_weights.sashdat')
self.assertRaises(
DLPyError, lambda: create_embeddings_from_object_detection(
self.s, image_table, detection_model, word_embeddings))
def test_filter_by_filename_5(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir+'giraffe_dolphin_small'
table = ImageTable.load_files(self.s, path=img_path)
filename = [1,'text',5.3]
self.assertRaises(ValueError, lambda:filter_by_filename(table, filename, filtered_name=None))
def test_filter_by_image_id_1(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir+'giraffe_dolphin_small'
table = ImageTable.load_files(self.s, path=img_path)
image_id = '1'
self.assertRaises(ValueError, lambda:filter_by_image_id(table, image_id, filtered_name=1))
def test_show(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir+'giraffe_dolphin_small'
my_images = ImageTable.load_files(self.s, path=img_path)
# the test shold be clean, even if selected are less than nimages
my_images.show(nimages=2, where='_id_ eq 57')
def test_filter_by_image_id_2(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir+'giraffe_dolphin_small'
table = ImageTable.load_files(self.s, path=img_path)
image_id = ['1','3','4']
filtered = filter_by_image_id(table, image_id, filtered_name=None)
self.assertTrue(filtered.numrows().numrows == 3)
def test_filter_by_filename_3(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir+'giraffe_dolphin_small'
table = ImageTable.load_files(self.s, path=img_path)
filename = ['giraffe_', 'dolphin_']
filtered = filter_by_filename(table, filename, filtered_name=None)
filtered = ImageTable.from_table(filtered)
self.assertTrue(filtered.label_freq.loc['Giraffe'][1]>0)
self.assertTrue(filtered.label_freq.loc['Dolphin'][1]>0)
def test_get_image_features_1(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=224)
features_model = VGG16(self.s, width=224, height=224)
dense_layer = 'fc10000'
self.assertRaises(
DLPyError, lambda: get_image_features(self.s, features_model,
image_table, dense_layer))
def viyaStartUp():
s= CAS('xx.xxx.xxx.xxx',5570,'viyademo01','demopw')
s.loadactionset('image')
s.loadactionset('deepLearn')
model_load = Model(s)
model_file = '/root/fullModel/Yolov2.sashdat'
model_load.load(path=model_file)
#test = ImageTable.load_files(conn=s, caslib='dnfs', path='/data/Poa/testData/labelled_images')
test = ImageTable.load_files(conn=s, caslib='dnfs', path='/data/Poa/validation')
test.resize(height=416, width=416, inplace=True)
prd = model_load.predict(data=test)
return [s,prd]
def test_get_image_features_3(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=224)
features_model = VGG16(self.s,
width=224,
height=224,
pre_trained_weights=True,
pre_trained_weights_file=self.data_dir +
'VGG_ILSVRC_16_layers.caffemodel.h5')
dense_layer = 'fc7'
self.assertTrue(
get_image_features(self.s, features_model, image_table,
dense_layer) is not None)
def test_captioning_table_2(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
file_dependency = self.data_dir + 'VGG_ILSVRC_16_layers.caffemodel.h5'
if not file_exist_on_server(self.s, file_dependency):
unittest.TestCase.skipTest(
self, "File, {}, not found.".format(file_dependency))
file_dependency = self.data_dir + 'YOLOV2_MULTISIZE.sashdat'
if not file_exist_on_server(self.s, file_dependency):
unittest.TestCase.skipTest(
self, "File, {}, not found.".format(file_dependency))
file_dependency = self.data_dir + 'YoloV2_Multisize_weights.sashdat'
if not file_exist_on_server(self.s, file_dependency):
unittest.TestCase.skipTest(
self, "File, {}, not found.".format(file_dependency))
if self.data_dir_local is None:
unittest.TestCase.skipTest(
self,
"DLPY_DATA_DIR_LOCAL is not set in the environment variables")
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=224)
captions_file = self.data_dir_local + 'image_captions.txt'
features_model = VGG16(self.s,
width=224,
height=224,
pre_trained_weights=True,
pre_trained_weights_file=self.data_dir +
'VGG_ILSVRC_16_layers.caffemodel.h5')
detection_model = Model(self.s)
detection_model.load(self.data_dir + 'YOLOV2_MULTISIZE.sashdat')
detection_model.load_weights(self.data_dir +
'YoloV2_Multisize_weights.sashdat')
self.assertRaises(
DLPyError,
lambda: create_captioning_table(self.s,
image_table,
features_model,
captions_file,
obj_detect_model=detection_model))
def test_object_table_1(self):
if self.data_dir is None:
unittest.TestCase.skipTest(
self, "DLPY_DATA_DIR is not set in the environment variables")
if self.data_dir_local is None:
unittest.TestCase.skipTest(
self,
"DLPY_DATA_DIR_LOCAL is not set in the environment variables")
img_path = self.data_dir + 'imageCaptioning_images'
image_table = ImageTable.load_files(self.s, path=img_path)
image_table.resize(width=416)
word_embeddings = self.data_dir_local + 'word_embeddings.txt'
detection_model = Model(self.s)
detection_model.load(self.data_dir + 'YOLOV2_MULTISIZE.sashdat')
detection_model.load_weights(self.data_dir +
'YoloV2_Multisize_weights.sashdat')
tbl = create_embeddings_from_object_detection(self.s, image_table,
detection_model,
word_embeddings)
self.assertTrue(tbl is not None)
def test_heat_map_analysis(self):
if self.data_dir is None:
unittest.TestCase.skipTest(self, 'DLPY_DATA_DIR is not set in the environment variables')
if not file_exist_on_server(self.s, self.data_dir + 'ResNet-50-model.caffemodel.h5'):
unittest.TestCase.skipTest(self, "File, {}, not found.".format(self.data_dir
+ 'ResNet-50-model.caffemodel.h5'))
from dlpy.applications import ResNet50_Caffe
from dlpy.images import ImageTable
pre_train_weight_file = os.path.join(self.data_dir, 'ResNet-50-model.caffemodel.h5')
my_im = ImageTable.load_files(self.s, self.data_dir+'giraffe_dolphin_small')
my_im_r = my_im.resize(width=224, inplace=False)
model = ResNet50_Caffe(self.s, model_table='ResNet50_Caffe',
n_classes=2, n_channels=3, width=224, height=224, scale=1,
random_flip='none', random_crop='none',
offsets=my_im_r.channel_means, pre_trained_weights=True,
pre_trained_weights_file=pre_train_weight_file,
include_top=False)
model.fit(data=my_im_r, mini_batch_size=1, max_epochs=1)
model.heat_map_analysis(data=my_im_r, mask_width=None, mask_height=None, step_size=None,
max_display=1)
self.assertRaises(ValueError, lambda:model.heat_map_analysis(mask_width=56, mask_height=56,
step_size=8, display=False))
self.assertRaises(ValueError, lambda:model.heat_map_analysis(data=my_im, mask_width=56,
mask_height=56, step_size=8, display=False))
try:
from numpy import array
except:
unittest.TestCase.skipTest(self, 'numpy is not installed')
self.assertRaises(ValueError, lambda:model.heat_map_analysis(data=array([]), mask_width=56,
mask_height=56, step_size=8, display=False))