2martens/masterthesis
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Moved code into separate functions

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-09-16 11:02:08 +02:00
parent 8230488031
commit 554ccc84f9
1 changed files with 85 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
src/twomartens/masterthesis/debug.py
View File

@ -22,10 +22,12 @@ Functions:
save_ssd_train_images(...):
saves the first batch of SSD train images with overlaid ground truth bounding boxes
"""
import functools
import os
from typing import Dict
from typing import Tuple
from typing import Union, Sequence
import cv2
import math
import numpy as np
from matplotlib import pyplot
@ -68,56 +70,88 @@ def save_ssd_train_images(images: Union[np.ndarray, Sequence[str]], labels: np.n
image = Image.fromarray(train_image)
image.save(f"{output_path}/"
f"{custom_string}train_image{str(i).zfill(nr_digits)}.png")
figure_filename = f"{output_path}/{custom_string}bboxes{str(i).zfill(nr_digits)}.png"
figure = pyplot.figure(figsize=(6.4, 4.8))
pyplot.imshow(image)
_draw_bbox_image(image=image,
filename=figure_filename,
draw_func=functools.partial(_draw_bboxes,
image_size=image_size,
classes_to_names=classes_to_names),
drawables=[
(colors, instances)
])
current_axis = pyplot.gca()
for instance in instances:
if len(instance) == 5: # ground truth
class_id = int(instance[0])
xmin = instance[1]
ymin = instance[2]
xmax = instance[3]
ymax = instance[4]
elif len(instance) == 7: # predictions
class_id = int(instance[0])
xmin = instance[3]
ymin = instance[4]
xmax = instance[5]
ymax = instance[6]
elif len(instance) == 6: # predictions using Caffe method
class_id = int(instance[0])
xmin = instance[2]
ymin = instance[3]
xmax = instance[4]
ymax = instance[5]
elif not len(instance):
continue
else:
instance = np.copy(instance)
class_id = np.argmax(instance[:-12], axis=0)
instance[-12:-8] *= instance[-4:] # multiply with variances
instance[[-11, -9]] *= np.expand_dims(instance[-5] - instance[-7], axis=-1)
instance[[-12, -10]] *= np.expand_dims(instance[-6] - instance[-8], axis=-1)
instance[-12:-8] += instance[-8:-4]
instance[-12:-8] *= image_size
def _draw_bbox_image(image: Image,
filename: str,
draw_func: callable,
drawables: Sequence[Tuple[Sequence, Sequence[np.ndarray]]]):
figure = pyplot.figure(figsize=(6.4, 4.8))
pyplot.imshow(image)
xmin = instance[-12]
ymin = instance[-11]
xmax = instance[-10]
ymax = instance[-9]
current_axis = pyplot.gca()
for colors, instances in drawables:
draw_func(instances=instances,
axis=current_axis,
colors=colors)
if class_id == 0:
continue
pyplot.savefig(filename)
pyplot.close(figure)
color = colors[class_id]
label = f"{classes_to_names[class_id]}"
current_axis.add_patch(
pyplot.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, color=color, fill=False,
linewidth=2))
current_axis.text(xmin, ymin, label, size='x-large', color='white',
bbox={'facecolor': color, 'alpha': 1.0})
pyplot.savefig(f"{output_path}/{custom_string}bboxes{str(i).zfill(nr_digits)}.png")
pyplot.close(figure)
def _draw_bboxes(instances: Sequence[np.ndarray], axis: pyplot.Axes,
image_size: int,
colors: Sequence,
classes_to_names: Dict[int, str]) -> None:
for instance in instances:
if not len(instance):
continue
else:
class_id, xmin, ymin, xmax, ymax = _get_bbox_info(instance, image_size)
if class_id == 0:
continue
color = colors[class_id]
label = f"{classes_to_names[class_id]}"
axis.add_patch(
pyplot.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, color=color, fill=False,
linewidth=2))
axis.text(xmin, ymin, label, size='x-large', color='white',
bbox={'facecolor': color, 'alpha': 1.0})
def _get_bbox_info(instance: np.ndarray, image_size: int) -> Tuple[int, float, float, float, float]:
if len(instance) == 5: # ground truth
class_id = int(instance[0])
xmin = instance[1]
ymin = instance[2]
xmax = instance[3]
ymax = instance[4]
elif len(instance) == 7: # predictions
class_id = int(instance[0])
xmin = instance[3]
ymin = instance[4]
xmax = instance[5]
ymax = instance[6]
elif len(instance) == 6: # predictions using Caffe method
class_id = int(instance[0])
xmin = instance[2]
ymin = instance[3]
xmax = instance[4]
ymax = instance[5]
else:
instance = np.copy(instance)
class_id = np.argmax(instance[:-12], axis=0)
instance[-12:-8] *= instance[-4:] # multiply with variances
instance[[-11, -9]] *= np.expand_dims(instance[-5] - instance[-7], axis=-1)
instance[[-12, -10]] *= np.expand_dims(instance[-6] - instance[-8], axis=-1)
instance[-12:-8] += instance[-8:-4]
instance[-12:-8] *= image_size
xmin = instance[-12]
ymin = instance[-11]
xmax = instance[-10]
ymax = instance[-9]
return class_id, xmin, ymin, xmax, ymax