class Solver:
def __init__(self, dirname=DEFAULT_MODEL_DIR, gpu=-1,
nms_thresh=DEFAULT_NMS_THRESH, score_thresh=DEFAULT_SCORE_THRESH):
with open(os.path.join(dirname, "model.json"), 'r') as fp:
metadata = json.load(fp)
n_class = metadata['n_class']
n_channel = metadata['n_channel']
npz_file = metadata['file']
self.class_labels = metadata['class_labels']
self.model = SSD(n_class=n_class, n_channel=n_channel,
nms_thresh=nms_thresh, score_thresh=score_thresh,
grids=DEFAULT_GRIDS, aspect_ratios=DEFAULT_ASPECT_RATIOS,
variance=DEFAULT_VARIANCE)
chainer.serializers.load_npz(os.path.join(dirname, npz_file), self.model)
if gpu >= 0:
chainer.backends.cuda.get_device_from_id(gpu).use()
self.model.to_gpu(gpu)
@property
def xp(self):
return self.model.xp
def solve(self, filename):
xp = self.xp
gif = cv2.VideoCapture(filename)
_, color_image = gif.read(0)
gray_image = cv2.cvtColor(color_image, cv2.COLOR_BGR2GRAY)
h, w = gray_image.shape[:2]
img = xp.array(gray_image / 255.0, dtype=xp.float32).reshape(1, 1, h, w)
output = self.model.predict(img)
bbox, label, score = output[0][0], output[1][0], output[2][0]
bbox = chainer.dataset.to_device(-1, bbox)
label = chainer.dataset.to_device(-1, label)
score = chainer.dataset.to_device(-1, score)
if len(label) > NCHARS:
indices = np.argsort(score)[-1:-NCHARS-1:-1]
bbox = bbox[indices]
label = label[indices]
score = score[indices]
bbox = np.vectorize(lambda v: int(v + 0.5), otypes=[int])(bbox)
indices = np.argsort(bbox[:, 1])
text = ''.join([ self.class_labels[label[i]] for i in indices ])
return text, bbox[indices], score[indices]
# 予測結果のbbox
print("予測結果")
##################
# 画像を選択
index =
image_path = os.path.join(image_dir, image_files[index])
img = cv2.imread(image_path)
gt = annotation[index]
answer =
# 予測
confidence_threshold =
out = ssd.predict(image_path)
out = [pred for pred in out if pred["score"]>=confidence_threshold]
out = sorted(out, key=lambda x:x["score"], reverse=True)
# 評価
pred =
evaluation =
print('f1score:', evaluation)
#表示
plot_bbox(img, gt, out)
print()
##################
# 画像を選択
print(os.listdir(models_dir))
model_path = os.path.join(models_dir, "ssd7.h5")
ssd.load_weights(model_path)
##################################################################
# 画像を1枚選択
index = 4
image_path = os.path.join(image_dir, image_files[index])
img = cv2.imread(image_path)
gt = annotation[index]
# 選択した画像に対してbboxの予測を行う
output = ssd.predict(image_path)
#print(output)
# 確信度の閾値
confidence_threshold = 0.25
# スコアが閾値以上のものだけに絞る
output_thresh = [prediction for prediction in output if prediction["score"]>= confidence_threshold]
# スコア順にソート
output_thresh = sorted(output_thresh, key=lambda x:x["score"], reverse=True)
print(output_thresh)
def plot_bbox(img, gt, out):
# グラフサイズの指定
plt.figure(figsize=(11,11))
net = SSD(cuda=args.cuda,
architecture='300_VGG16',
num_classes=len(LogoDataset.CLASSES))
has_cuda = args.cuda and torch.cuda.is_available()
if has_cuda:
weights = torch.load(args.weights)['model']
else:
weights = torch.load(args.weights, map_location='cpu')['model']
net = SSD.load(weights=weights)
COLORMAP = [(255, 0, 0), (0, 255, 0), (0, 0, 255)]
images = []
images = [cv2.imread(filename) for filename in glob.glob(args.test_filenames)]
results = net.predict(images)
for im, result_image in zip(images, results):
for i, result in enumerate(result_image):
print(LogoDataset.CLASSES[result['class']])
class_ = LogoDataset.CLASSES[result['class']]
position = result['position']
confidence = int(100 * result['confidence'])
cv2.rectangle(im, (int(position[0]), int(position[1])),
(int(position[2]), int(position[3])),
COLORMAP[i % len(COLORMAP)])
cv2.putText(im, '%s (%d%%)' % (class_, confidence),
(int(position[0]), int(position[1])),
cv2.FONT_HERSHEY_SIMPLEX, 2, COLORMAP[i % len(COLORMAP)],
2, cv2.LINE_AA)
#print(ssd.model.summary())
models_dir = os.path.join(".", "trained_models")
#print(os.listdir(models_dir))
model_path = os.path.join(models_dir, "ssd7.h5")
ssd.load_weights(model_path)
# 画像を1枚選択
index = 4
image_path = os.path.join(image_dir, image_files[index])
img = cv2.imread(image_path)
gt = annotation[index]
# 選択した画像に対してbboxの予測を行う
output = ssd.predict(image_path)
#print(output)
# 確信度の閾値
confidence_threshold = 0.25
# スコアが閾値以上のものだけに絞る
output_thresh = [prediction for prediction in output if prediction["score"]>= confidence_threshold]
# スコア順にソート
output_thresh = sorted(output_thresh, key=lambda x:x["score"], reverse=True)
print(output_thresh)
def plot_bbox(img, gt, out):
# グラフサイズの指定
plt.figure(figsize=(11,11))
