def run(config_path, pipeline_config_path=None):
'''Run the convolution module.
Args:
config_path: path to a ConvolutionConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
convolution_config = ConvolutionConfig.from_json(config_path)
etam.setup(convolution_config, pipeline_config_path=pipeline_config_path)
_perform_convolution(convolution_config)
def run(config_path, pipeline_config_path=None):
'''Run the clip_videos module.
Args:
config_path: path to a ClipConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
clip_config = ClipConfig.from_json(config_path)
etam.setup(clip_config, pipeline_config_path=pipeline_config_path)
_clip_videos(clip_config)
def run(config_path, pipeline_config_path=None):
'''Run the video_stream_info module.
Args:
config_path: path to a VideoStreamInfoConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
stream_info_config = VideoStreamInfoConfig.from_json(config_path)
etam.setup(stream_info_config, pipeline_config_path=pipeline_config_path)
_get_stream_info(stream_info_config)
def run(config_path, pipeline_config_path=None):
'''Run the google_drive_download module.
Args:
config_path: path to a GoogleDriveDownloadConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
download_config = GoogleDriveDownloadConfig.from_json(config_path)
etam.setup(download_config, pipeline_config_path=pipeline_config_path)
_download_files(download_config)
def run(config_path, pipeline_config_path=None):
'''Run the canny edge detector module.
Args:
config_path: path to a ConvolutionConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
canny_edge_config = CannyEdgeConfig.from_json(config_path)
etam.setup(canny_edge_config, pipeline_config_path=pipeline_config_path)
_perform_canny_edge_detection(canny_edge_config)
def run(config_path, pipeline_config_path=None):
'''Run the Harris Corner module.
Args:
config_path: path to a HarrisCornerConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
harris_corner_config = HarrisCornerConfig.from_json(config_path)
etam.setup(harris_corner_config, pipeline_config_path=pipeline_config_path)
_find_corners(harris_corner_config)
def run(config_path, pipeline_config_path=None):
'''Run the format_videos module.
Args:
config_path: path to a FormatterConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
config = FormatterConfig.from_json(config_path)
etam.setup(config, pipeline_config_path=pipeline_config_path)
_format_videos(config)
def run(config_path, pipeline_config_path=None):
'''Run the Image Stitching module.
Args:
config_path: path to a ImageStitchingConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
image_stitching_config = ImageStitchingConfig.from_json(config_path)
etam.setup(image_stitching_config,
pipeline_config_path=pipeline_config_path)
_stitch_images(image_stitching_config)
def run(config_path, pipeline_config_path=None):
'''Run the Steerable Filter module.
Args:
config_path: path to a SteerableFilterConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
steerable_filter_config = SteerableFilterConfig.from_json(config_path)
etam.setup(steerable_filter_config,
pipeline_config_path=pipeline_config_path)
_filter_image(steerable_filter_config)
def run(config_path, pipeline_config_path=None):
'''Run this module to find line segments in the image.
Args:
config_path: path to a ConvolutionConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
#print(config_path)
find_segments_config = FindSegmentsConfig.from_json(config_path)
etam.setup(find_segments_config, pipeline_config_path=pipeline_config_path)
_find_line_segments(find_segments_config)
def run(config_path, pipeline_config_path=None):
'''Run the embed_vgg16 module.
Args:
config_path: path to a config file containing the fields to define
both an EmbedVGG16Config and a VGG16FeaturizerConfig
pipeline_config_path: optional path to a PipelineConfig file
'''
d = etas.read_json(config_path)
embed_vgg16_config = EmbedVGG16Config(d)
etam.setup(embed_vgg16_config, pipeline_config_path=pipeline_config_path)
_featurize_driver(embed_vgg16_config, d)
def run(config_path, pipeline_config_path=None):
'''Run the SVHN Classification Module.
Args:
config_path: path to a ConvolutionConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
svhn_config = SVHNClassificationConfig.from_json(config_path)
etam.setup(svhn_config, pipeline_config_path=pipeline_config_path)
for data in svhn_config.data:
# Read all the MNIST data as numpy arrays
mnist_train_images = read_idx(data.mnist_train_images_path)
mnist_train_labels = read_idx(data.mnist_train_labels_path)
mnist_test_images = read_idx(data.mnist_test_images_path)
mnist_test_labels = read_idx(data.mnist_test_labels_path)
# Read the digitStruct.mat from the SVHN test folder
base_svhn_path = data.svhn_test_path
dsf = DigitStructFile(base_svhn_path + "/digitStruct.mat")
# training
PCA_dir_train, PCA_socre_train, mean_train = Get_PCA(
mnist_train_images, svhn_config.parameters.num_PCA)
# testing
svhn_error_rate, _, _ = test_SVHN(PCA_dir_train, mean_train,
PCA_socre_train, mnist_train_labels,
dsf, base_svhn_path,
svhn_config.parameters.num_neighbor,
300)
mnist_error_rate, _, _ = test_MNIST(
PCA_dir_train, mean_train, PCA_socre_train, mnist_train_labels,
mnist_test_images, mnist_test_labels,
svhn_config.parameters.num_neighbor, -1)
'''
# visualize
PCA_vis, _, _ = Get_PCA(mnist_train_images, 10)
visualize_PCA(PCA_vis)
# get example
test_MNIST_sample(PCA_dir_train, mean_train, PCA_socre_train, mnist_train_labels,
mnist_test_images, mnist_test_labels, svhn_config.parameters.num_neighbor)
test_SVHN_sample(PCA_dir_train, mean_train, PCA_socre_train, mnist_train_labels,
dsf, base_svhn_path, svhn_config.parameters.num_neighbor)
'''
error_rate_dic = defaultdict(lambda: defaultdict())
error_rate_dic["error_rates"]["mnist_error_rate"] = mnist_error_rate
error_rate_dic["error_rates"]["svhn_error_rate"] = svhn_error_rate
etas.write_json(error_rate_dic, data.error_rate_file)
def run(config_path, pipeline_config_path=None):
'''Run the Pott's Energy module.
Args:
config_path: path to a ConvolutionConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
potts_config = PottsEnergyConfig.from_json(config_path)
etam.setup(potts_config, pipeline_config_path=pipeline_config_path)
for data in potts_config.data:
energy = _calculate_potts_energy(data)
potts_energy = defaultdict(lambda: defaultdict())
potts_energy["result"]["energy"] = energy
etas.write_json(potts_energy, data.potts_energy_out)
def run(config_path, pipeline_config_path=None):
'''Run the {{module_name}} module.
Args:
config_path: path to a {{ModuleName}}Config file
pipeline_config_path: optional path to a PipelineConfig file
'''
# Load the module config
config = DarknetConfig.from_json(config_path)
# Perform base module setup via the `eta.core.module.setup()` method
# provided by the ETA library
etam.setup(config, pipeline_config_path=pipeline_config_path)
# Now pass the `config` instance to another private method to perform the
# actual module computations
# ..."
logger.debug("Trying to invoke the darknet code now...")
run_darknet(config)
def run(config_path, pipeline_config_path=None):
'''Run the SVHN Classification Module.
Args:
config_path: path to a ConvolutionConfig file
pipeline_config_path: optional path to a PipelineConfig file
'''
svhn_config = SVHNClassificationConfig.from_json(config_path)
etam.setup(svhn_config, pipeline_config_path=pipeline_config_path)
for data in svhn_config.data:
# Read all the MNIST data as numpy arrays
mnist_train_images = read_idx(data.mnist_train_images_path)
mnist_train_labels = read_idx(data.mnist_train_labels_path)
mnist_test_images = read_idx(data.mnist_test_images_path)
mnist_test_labels = read_idx(data.mnist_test_labels_path)
# Read the digitStruct.mat from the SVHN test folder
base_svhn_path = data.svhn_test_path
dsf = DigitStructFile(base_svhn_path + "/digitStruct.mat")
#reshape mnust_train_data
train_images = np.reshape(mnist_train_images,
(mnist_train_images.shape[0], 784))
test_images = np.reshape(mnist_test_images,
(mnist_test_images.shape[0], 784))
eigen_basis = compute_eigen_basis(mnist_train_images)
mnist_total_num = 0
mnist_wrong = 0
# Apply PCA to the training and test images
train = np.dot(train_images, eigen_basis.T)
test = np.dot(test_images, eigen_basis.T)
'''
plt.imshow(testarray.reshape(28, 28))
plt.show()
pca = PCA(n_components=2)
principal_components = pca.fit_transform(train_images)
'''
# for i in range(500):
# mnist_total_num += 1
# neighbors = getNeighbors(train, test[i], 3, mnist_train_labels)
# res = getResponse(neighbors)
# if res != mnist_test_labels[i]:
# print("wrong", mnist_test_labels[i], res)
# # plt.imshow(mnist_test_images[i])
# # plt.show()
# mnist_wrong += 1
# else:
# print("correct")
# plt.imshow(mnist_test_images[i])
# plt.show()
'''
Format of the bounding box
{
'height': [16.0],
'label': [6.0],
'left': [61.0],
'top': [6.0],
'width': [11.0]
}
'''
svhn_total_num = 0
svhn_correct = 0
for i in range(300):
print(i)
for j in range(len(dsf.getBbox(i)['label'])):
svhn_total_num += 1
img_original = crop_img(base_svhn_path, i + 1,
int(dsf.getBbox(i)['top'][j]),
int(dsf.getBbox(i)['height'][j]),
int(dsf.getBbox(i)['left'][j]),
int(dsf.getBbox(i)['width'][j]))
img_gray = cv2.cvtColor(img_original,
cv2.COLOR_BGR2GRAY).flatten('F')
img = np.dot(img_gray, eigen_basis.T)
# Apply knn
neighbors = getNeighbors(train, img, 1, mnist_train_labels)
res = getResponse(neighbors)
if res == int(dsf.getBbox(i)['label'][j]):
svhn_correct += 1
# else:
# print("wrong")
# plt.imshow(img_original)
# plt.show()
print("correct rate:", svhn_correct,
float(svhn_correct) / float(svhn_total_num))
'''CALL YOUR FUNCTIONS HERE.
Please call of your functions here. For this problem, we ask you to
visualize several things. You need to do this yourself (in any
way you wish).
For the MNIST and SVHN error rates, please store these two error
rates in the variables called "mnist_error_rate" and
"svhn_error_rate", for the MNIST error rate and SVHN error rate,
respectively. These two variables will be used to write
the numbers in a JSON file.
'''
# Make sure you assign values to these two variables
mnist_error_rate = 0.074
svhn_error_rate = (svhn_total_num - svhn_correct) / svhn_total_num
error_rate_dic = defaultdict(lambda: defaultdict())
error_rate_dic["error_rates"]["mnist_error_rate"] = mnist_error_rate
error_rate_dic["error_rates"]["svhn_error_rate"] = svhn_error_rate
etas.write_json(error_rate_dic, data.error_rate_file)