def variable_summaries(var, name):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.scalar_summary('mean_' + name, mean)
# 计算参数的标准差
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.scalar_summary('stddev_' + name, stddev)
tf.scalar_summary('max_' + name, tf.reduce_max(var))
tf.scalar_summary('min_' + name, tf.reduce_min(var))
# 用直方图记录参数的分布
tf.histogram_summary('histogram_' + name, var)
def tf_xywh_to_grid(all_true_xy: tf.Tensor, all_true_wh: tf.Tensor, layer: int,
h: Helper) -> [tf.Tensor, tf.Tensor]:
"""convert true label xy wh to grid scale
Parameters
----------
all_true_xy : tf.Tensor
all_true_wh : tf.Tensor
layer : int
layer index
h : Helper
Returns
-------
[tf.Tensor, tf.Tensor]
grid_true_xy, grid_true_wh shape = [out h ,out w,anchor num , 2 ]
"""
with tf.name_scope('xywh_to_grid_%d' % layer):
grid_true_xy = (all_true_xy *
h.out_hw[layer][::-1]) - h.xy_offset[layer]
grid_true_wh = tf.log(all_true_wh / h.anchors[layer])
return grid_true_xy, grid_true_wh
def tf_xywh_to_all(grid_pred_xy: tf.Tensor, grid_pred_wh: tf.Tensor,
layer: int, h: Helper) -> [tf.Tensor, tf.Tensor]:
""" rescale the pred raw [grid_pred_xy,grid_pred_wh] to [0~1]
Parameters
----------
grid_pred_xy : tf.Tensor
grid_pred_wh : tf.Tensor
layer : int
the output layer
h : Helper
Returns
-------
tuple
after process, [all_pred_xy, all_pred_wh]
"""
with tf.name_scope('xywh_to_all_%d' % layer):
all_pred_xy = (tf.sigmoid(grid_pred_xy[..., :]) +
h.xy_offset[layer]) / h.out_hw[layer][::-1]
all_pred_wh = tf.exp(grid_pred_wh[..., :]) * h.anchors[layer]
return all_pred_xy, all_pred_wh
def tf_reshape_box(true_xy_A: tf.Tensor, true_wh_A: tf.Tensor,
p_xy_A: tf.Tensor, p_wh_A: tf.Tensor, layer: int,
helper: Helper) -> tuple:
""" reshape the xywh to [?,h,w,anchor_nums,true_box_nums,2]
NOTE must use obj mask in atrue xywh !
Parameters
----------
true_xy_A : tf.Tensor
shape will be [true_box_nums,2]
true_wh_A : tf.Tensor
shape will be [true_box_nums,2]
p_xy_A : tf.Tensor
shape will be [?,h,w,anhor_nums,2]
p_wh_A : tf.Tensor
shape will be [?,h,w,anhor_nums,2]
layer : int
helper : Helper
Returns
-------
tuple
true_cent, true_box_wh, pred_cent, pred_box_wh
"""
with tf.name_scope('reshape_box_%d' % layer):
true_cent = true_xy_A[tf.newaxis, tf.newaxis, tf.newaxis, tf.newaxis,
...]
true_box_wh = true_wh_A[tf.newaxis, tf.newaxis, tf.newaxis, tf.newaxis,
...]
true_cent = tf.tile(true_cent, [
helper.batch_size, helper.out_hw[layer][0],
helper.out_hw[layer][1], helper.anchor_number, 1, 1
])
true_box_wh = tf.tile(true_box_wh, [
helper.batch_size, helper.out_hw[layer][0],
helper.out_hw[layer][1], helper.anchor_number, 1, 1
])
pred_cent = p_xy_A[..., tf.newaxis, :]
pred_box_wh = p_wh_A[..., tf.newaxis, :]
pred_cent = tf.tile(pred_cent, [1, 1, 1, 1, tf.shape(true_xy_A)[0], 1])
pred_box_wh = tf.tile(
pred_box_wh, [1, 1, 1, 1, tf.shape(true_wh_A)[0], 1])
return true_cent, true_box_wh, pred_cent, pred_box_wh
def calc_ignore_mask(t_xy_A: tf.Tensor, t_wh_A: tf.Tensor, p_xy: tf.Tensor,
p_wh: tf.Tensor, obj_mask: tf.Tensor, iou_thresh: float,
layer: int, helper: Helper) -> tf.Tensor:
"""clac the ignore mask
Parameters
----------
t_xy_A : tf.Tensor
raw ture xy,shape = [batch size,h,w,anchors,2]
t_wh_A : tf.Tensor
raw true wh,shape = [batch size,h,w,anchors,2]
p_xy : tf.Tensor
raw pred xy,shape = [batch size,h,w,anchors,2]
p_wh : tf.Tensor
raw pred wh,shape = [batch size,h,w,anchors,2]
obj_mask : tf.Tensor
old obj mask,shape = [batch size,h,w,anchors]
iou_thresh : float
iou thresh
helper : Helper
Helper obj
Returns
-------
tf.Tensor
ignore_mask :
ignore_mask, shape = [batch size, h, w, anchors, 1]
"""
with tf.name_scope('calc_mask_%d' % layer):
pred_xy, pred_wh = tf_xywh_to_all(p_xy, p_wh, layer, helper)
# def lmba(bc):
# vaild_xy = tf.boolean_mask(t_xy_A[bc], obj_mask[bc])
# vaild_wh = tf.boolean_mask(t_wh_A[bc], obj_mask[bc])
# iou_score = tf_iou(pred_xy[bc], pred_wh[bc], vaild_xy, vaild_wh)
# best_iou = tf.reduce_max(iou_score, axis=-1, keepdims=True)
# return tf.cast(best_iou < iou_thresh, tf.float32)
# return map_fn(lmba, tf.range(helper.batch_size), dtype=tf.float32)
ignore_mask = []
for bc in range(helper.batch_size):
vaild_xy = tf.boolean_mask(t_xy_A[bc], obj_mask[bc])
vaild_wh = tf.boolean_mask(t_wh_A[bc], obj_mask[bc])
iou_score = tf_iou(pred_xy[bc], pred_wh[bc], vaild_xy, vaild_wh)
best_iou = tf.reduce_max(iou_score, axis=-1, keepdims=True)
ignore_mask.append(tf.cast(best_iou < iou_thresh, tf.float32))
return tf.stack(ignore_mask)
import matplotlib.pyplot as plt
train_times = 50000
base_path = "/Users/coorchice/Desktop/ML/model/ml/BreadBasket/"
save_path = base_path + str(train_times) + "/"
BBDATA = read_datas('data/')
x_data = tf.placeholder(tf.float32, [None, 135])
y_data = tf.placeholder(tf.float32, [None])
W = tf.Variable(tf.truncated_normal([135, 1], stddev=0.1))
b = tf.Variable(tf.constant(0.1, shape=[1]))
y = tf.nn.relu(tf.matmul(x_data, W) + b)
# 按照交叉熵公式计算交叉熵
with tf.name_scope('loss'):
# cross_entropy = -tf.reduce_sum(y_data * tf.log(y))
cross_entropy = tf.reduce_mean((tf.square((y - y_data))))
tf.scalar_summary('loss', cross_entropy)
# init_lr = 0.00001
lr = tf.Variable(0.00005, trainable=False)
# global_step = tf.Variable(0., trainable=False)
# lr = tf.train.exponential_decay(init_lr, global_step=global_step, decay_steps=10000, decay_rate=0.5, staircase=True)
# 使用梯度下降法不断的调整变量，寻求最小的交叉熵
# 此处使用梯度下降法以0.01的学习速率最小化交叉熵
train_step = tf.train.GradientDescentOptimizer(lr).minimize(cross_entropy)
# train_step = tf.train.GradientDescentOptimizer(0.00001).minimize(cross_entropy)
# correct_prediction = tf.equal(y, y_data)
