def _pixel_selector_grad(op, grad):
"""The gradients for 'pixel_selector'.
Args:
op: The 'pixel_selector' operation we want to differentiate.
grad: Gradient with respect to the output of the 'pixel_selector' op.
Returns:
Gradients with respect to the coordinates of points of interest for 'pixel_selector'.
"""
input = op.inputs[0]
coord = op.inputs[1]
strides = op.inputs[2]
coord_grad = ops.zeros_like((NUM_POINTS, 3), tf.float32)
back_grad = ops.reshape(grad, [-1])
coord_grad_tmp = np.zeros((NUM_POINTS, 3), np.float32)
for i in range(0, NUM_POINTS):
for j in range(0, 3):
coord_tmp = np.zeros((NUM_POINTS, 3), np.float32)
coord_tmp[i, j] = 1.0
coord_tmp = coord + coord_tmp
tmp_1 = ops.reshape(
select_module.pixel_selector(input, coord_tmp, strides), [-1])
coord_tmp = np.zeros((NUM_POINTS, 3), np.float32)
coord_tmp[i, j] = -1.0
coord_tmp = coord + coord_tmp
tmp_2 = ops.reshape(
select_module.pixel_selector(input, coord_tmp, strides), [-1])
tmp = ops.subtract(tmp_1, tmp_2)
tmp = ops.divide(tmp, 2)
tmp = ops.multiply(tmp, back_grad)
tmp_3 = np.zeros((NUM_POINTS, 3), np.float32)
tmp_3[i, j] = 1.0
coord_grad_tmp = coord_grad_tmp + tmp_3 * ops.reduce_sum(tmp)
coord_grad = coord_grad_tmp
return [None, coord_grad, None]
def calc_loss(logits: tf.Tensor, caps_out: tf.Tensor, x: tf.Tensor, y: tf.Tensor, decoded: tf.Tensor):
with tf.variable_scope('calc_loss'):
# margin loss 中调节上margin和下margind的权重
lambda_val = 0.5
# 上margin与下margin的参数值
m_plus = 0.95
m_minus = 0.05
max_l = tf.square(tf.maximum(0., m_plus-logits))
max_r = tf.square(tf.maximum(0., logits-m_minus))
margin_loss = tf.reduce_mean(tf.reduce_sum(y * max_l + lambda_val * (1. - y) * max_r, axis=-1))
orgin = tf.reshape(x, (x.shape[0], -1))
reconstruct_loss = 0.0005*tf.reduce_mean(tf.square(orgin-decoded))
total_loss = margin_loss+reconstruct_loss
return total_loss
def main(ckpt_weights, image_size, output_size, model_def, class_num,
depth_multiplier, obj_thresh, iou_thresh, train_set, test_image):
h = Helper(None, class_num, f'data/{train_set}_anchor.npy',
np.reshape(np.array(image_size), (-1, 2)),
np.reshape(np.array(output_size), (-1, 2)))
network = eval(model_def) # type :yolo_mobilev2
yolo_model, yolo_model_warpper = network([image_size[0], image_size[1], 3],
len(h.anchors[0]),
class_num,
alpha=depth_multiplier)
yolo_model_warpper.load_weights(str(ckpt_weights))
print(INFO, f' Load CKPT {str(ckpt_weights)}')
orig_img = h._read_img(str(test_image))
image_shape = orig_img.shape[0:2]
img, _ = h._process_img(orig_img,
true_box=None,
is_training=False,
is_resize=True)
""" load images """
img = tf.expand_dims(img, 0)
y_pred = yolo_model_warpper.predict(img)
""" box list """
_yxyx_box = []
_yxyx_box_scores = []
""" preprocess label """
for l, pred_label in enumerate(y_pred):
""" split the label """
pred_xy = pred_label[..., 0:2]
pred_wh = pred_label[..., 2:4]
pred_confidence = pred_label[..., 4:5]
pred_cls = pred_label[..., 5:]
# box_scores = obj_score * class_score
box_scores = tf.sigmoid(pred_cls) * tf.sigmoid(pred_confidence)
# obj_mask = pred_confidence_score[..., 0] > obj_thresh
""" reshape box """
# NOTE tf_xywh_to_all will auto use sigmoid function
pred_xy_A, pred_wh_A = tf_xywh_to_all(pred_xy, pred_wh, l, h)
boxes = correct_box(pred_xy_A, pred_wh_A, image_size, image_shape)
boxes = tf.reshape(boxes, (-1, 4))
box_scores = tf.reshape(box_scores, (-1, class_num))
""" append box and scores to global list """
_yxyx_box.append(boxes)
_yxyx_box_scores.append(box_scores)
yxyx_box = tf.concat(_yxyx_box, axis=0)
yxyx_box_scores = tf.concat(_yxyx_box_scores, axis=0)
mask = yxyx_box_scores >= obj_thresh
""" do nms for every classes"""
_boxes = []
_scores = []
_classes = []
for c in range(class_num):
class_boxes = tf.boolean_mask(yxyx_box, mask[:, c])
class_box_scores = tf.boolean_mask(yxyx_box_scores[:, c], mask[:, c])
select = tf.image.non_max_suppression(class_boxes,
scores=class_box_scores,
max_output_size=30,
iou_threshold=iou_thresh)
class_boxes = tf.gather(class_boxes, select)
class_box_scores = tf.gather(class_box_scores, select)
_boxes.append(class_boxes)
_scores.append(class_box_scores)
_classes.append(tf.ones_like(class_box_scores) * c)
boxes = tf.concat(_boxes, axis=0)
classes = tf.concat(_classes, axis=0)
scores = tf.concat(_scores, axis=0)
""" draw box """
font = ImageFont.truetype(font='asset/FiraMono-Medium.otf',
size=tf.cast(
tf.floor(3e-2 * image_shape[0] + 0.5),
tf.int32).numpy())
thickness = (image_shape[0] + image_shape[1]) // 300
""" show result """
if len(classes) > 0:
pil_img = Image.fromarray(orig_img)
print(f'[top\tleft\tbottom\tright\tscore\tclass]')
for i, c in enumerate(classes):
box = boxes[i]
score = scores[i]
label = '{:2d} {:.2f}'.format(int(c.numpy()), score.numpy())
draw = ImageDraw.Draw(pil_img)
label_size = draw.textsize(label, font)
top, left, bottom, right = box
print(
f'[{top:.1f}\t{left:.1f}\t{bottom:.1f}\t{right:.1f}\t{score:.2f}\t{int(c):2d}]'
)
top = max(0, tf.cast(tf.floor(top + 0.5), tf.int32))
left = max(0, tf.cast(tf.floor(left + 0.5), tf.int32))
bottom = min(image_shape[0],
tf.cast(tf.floor(bottom + 0.5), tf.int32))
right = min(image_shape[1], tf.cast(tf.floor(right + 0.5),
tf.int32))
if top - image_shape[0] >= 0:
text_origin = tf.convert_to_tensor([left, top - label_size[1]])
else:
text_origin = tf.convert_to_tensor([left, top + 1])
for j in range(thickness):
draw.rectangle([left + j, top + j, right - j, bottom - j],
outline=h.colormap[c])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=h.colormap[c])
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
pil_img.show()
else:
print(NOTE, ' no boxes detected')
if __name__ == "__main__":
g = tf.get_default_graph()
ds, ds_val = mnist_dataset()
iterator = ds.make_one_shot_iterator()
next_x, next_y = iterator.get_next()
batch_x = tf.placeholder_with_default(next_x, shape=[100, 28, 28, 1])
batch_y = tf.placeholder_with_default(next_y, shape=[100, 10])
logits, caps_out = capsnet(batch_x)
decoded = decoder(caps_out, batch_y)
""" define loss """
loss = calc_loss(logits, caps_out, batch_x, batch_y, decoded)
""" define summary """
acc_op, acc = tf.metrics.accuracy(tf.argmax(batch_y, -1), tf.argmax(logits, -1))
tf.summary.scalar('loss', loss)
tf.summary.scalar('acc', acc)
tf.summary.image('reconstruction_img', tf.reshape(decoded, (100, 28, 28, 1)))
summ = tf.summary.merge_all()
""" define train op """
steps = tf.train.get_or_create_global_step(g)
train_op = tf.train.AdamOptimizer().minimize(loss, global_step=steps)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
writer = tf.summary.FileWriter('log', g)
sess.run([tf.global_variables_initializer(), tf.local_variables_initializer()])
for i in range(10):
with tqdm(total=60000//100, bar_format='{n_fmt}/{total_fmt} |{bar}| {rate_fmt}{postfix}', unit=' batch', dynamic_ncols=True) as t:
for j in range(60000//100):
_, summ_, steps_, loss_, acc_ = sess.run([train_op, summ, steps, loss, acc])
t.set_postfix(loss='{:<5.3f}'.format(loss_), acc='{:<4.2f}%'.format(acc_*100))
def flatten(previous_layer):
return tf.reshape(previous_layer, shape=[-1, (previous_layer.get_shape()[1] * previous_layer.get_shape()[2] * previous_layer.get_shape()[3])])