def training_patches(imnames,
npatches,
psize,
maxdim=None,
colour=False,
verbose=False):
""" Extract patches from images for dictionary training
Arguments:
imnames: A list of image names from which to extract training patches.
npatches: The number (int) of patches to extract from the images
maxdim: The maximum dimension of the image in pixels. The image is
rescaled if it is larger than this. By default there is no scaling.
psize: A int of the size of the square patches to extract
verbose: bool, print progress bar
Returns:
An np.array (npatches, psize**2*3) for RGB or (npatches, psize**2) for
grey of flattened image patches. NOTE, the actual npatches found may be
less than that requested.
"""
nimg = len(imnames)
ppeimg = int(round(float(npatches) / nimg))
plist = []
# Set up progess updates
progbar = Progress(nimg, title='Extracting patches', verbose=verbose)
for i, ims in enumerate(imnames):
img = imread_resize(ims, maxdim) # read in and resize the image
spaceing = max(int(round(img.shape[1] * ppeimg**(-0.5))), 1)
# Extract patches and map to grayscale if necessary
if (colour == False) and (img.ndim == 3):
imgg = rgb2gray(img)
plist.append(grid_patches(imgg, psize, spaceing)[0])
else:
plist.append(grid_patches(img, psize, spaceing)[0])
progbar.update(i)
progbar.finished()
patches = np.concatenate(plist, axis=0)
return np.reshape(patches, (patches.shape[0], np.prod(patches.shape[1:])))
def training_patches (imnames, npatches, psize, maxdim=None, colour=False,
verbose=False):
""" Extract patches from images for dictionary training
Arguments:
imnames: A list of image names from which to extract training patches.
npatches: The number (int) of patches to extract from the images
maxdim: The maximum dimension of the image in pixels. The image is
rescaled if it is larger than this. By default there is no scaling.
psize: A int of the size of the square patches to extract
verbose: bool, print progress bar
Returns:
An np.array (npatches, psize**2*3) for RGB or (npatches, psize**2) for
grey of flattened image patches. NOTE, the actual npatches found may be
less than that requested.
"""
nimg = len(imnames)
ppeimg = int(round(float(npatches)/nimg))
plist = []
# Set up progess updates
progbar = Progress(nimg, title='Extracting patches', verbose=verbose)
for i, ims in enumerate(imnames):
img = imread_resize(ims, maxdim) # read in and resize the image
spaceing = max(int(round(img.shape[1] * ppeimg**(-0.5))), 1)
# Extract patches and map to grayscale if necessary
if (colour == False) and (img.ndim == 3):
imgg = rgb2gray(img)
plist.append(grid_patches(imgg, psize, spaceing)[0])
else:
plist.append(grid_patches(img, psize, spaceing)[0])
progbar.update(i)
progbar.finished()
patches = np.concatenate(plist, axis=0)
return np.reshape(patches, (patches.shape[0], np.prod(patches.shape[1:])))
data = csv.DictReader(fd, delimiter="\t", quotechar='"', escapechar='')
for r in data:
raw_id = r['raw_id']
# Check if valid with regex
match = re.match(r"^(tt)*(?P<id>\d{7,10}).*", raw_id)
if not match:
progress.count()
wrongs.append(raw_id)
continue
imdb_id = match.group(2)
film_node = n['Movie/tt' + imdb_id]
# Create a node for dbpedia
uri = r['uri']
wiki_node = URIRef(uri)
g.add((film_node, n['has' + source + 'Node'], wiki_node))
progress.count()
if progress.finished():
break
g.serialize(destination=outfile, format='turtle')
end = time.time()
print('Wrong formatted IMDB IDs found: ', len(wrongs))
print(wrongs)
print("Total Items Processed: ", progress.total)
print("Total Time: ", end - start)
g.close()
