我正在使用预先训练好的Alexnet，如下所示。我希望使用该模型进行6个输出的回归（Xcoordinate（范围（0,227），Ycoordinate（范围（0,227），高度（范围（20,50），宽度（范围（20,50），正弦（θ），cos （theta））。（θ的范围是-180到180度） 这些是我改变的以下内容 -
现在，我没有得到正确的正弦和余弦值（它应该在（-1到1）的范围内），我越界了。我该怎么做，我应该如何保持一个受约束的价值观。另外，我是否应该对其他参数保持一致。我该怎么做才能纳入这些变化？ 我应该使用此模型进行回归的其他变化是什么？
import tensorflow as tf
import numpy as np
class AlexNet(object):
def __init__(self, x, keep_prob, num_classes, skip_layer,
weights_path = 'DEFAULT'):
# Parse input arguments into class variables
self.X = x
self.NUM_CLASSES = num_classes
self.KEEP_PROB = keep_prob
self.SKIP_LAYER = skip_layer
if weights_path == 'DEFAULT':
self.WEIGHTS_PATH = 'bvlc_alexnet.npy'
else:
self.WEIGHTS_PATH = weights_path
# Call the create function to build the computational graph of AlexNet
self.create()
def create(self):
# 1st Layer: Conv (w ReLu) -> Pool -> Lrn
conv1 = conv(self.X, 11, 11, 96, 4, 4, padding = 'VALID', name = 'conv1')
pool1 = max_pool(conv1, 3, 3, 2, 2, padding = 'VALID', name = 'pool1')
norm1 = lrn(pool1, 2, 2e-05, 0.75, name = 'norm1')
# 2nd Layer: Conv (w ReLu) -> Pool -> Lrn with 2 groups
conv2 = conv(norm1, 5, 5, 256, 1, 1, groups = 2, name = 'conv2')
pool2 = max_pool(conv2, 3, 3, 2, 2, padding = 'VALID', name ='pool2')
norm2 = lrn(pool2, 2, 2e-05, 0.75, name = 'norm2')
# 3rd Layer: Conv (w ReLu)
conv3 = conv(norm2, 3, 3, 384, 1, 1, name = 'conv3')
# 4th Layer: Conv (w ReLu) splitted into two groups
conv4 = conv(conv3, 3, 3, 384, 1, 1, groups = 2, name = 'conv4')
# 5th Layer: Conv (w ReLu) -> Pool splitted into two groups
conv5 = conv(conv4, 3, 3, 256, 1, 1, groups = 2, name = 'conv5')
pool5 = max_pool(conv5, 3, 3, 2, 2, padding = 'VALID', name = 'pool5')
# 6th Layer: Flatten -> FC (w ReLu) -> Dropout
flattened = tf.reshape(pool5, [-1, 6*6*256])
fc6 = fc(flattened, 6*6*256, 4096, name='fc6',relu =True)
dropout6 = dropout(fc6, self.KEEP_PROB)
# 7th Layer: FC (w ReLu) -> Dropout
fc7 = fc(dropout6, 4096, 4096, name = 'fc7',relu =False)
# dropout7 = dropout(fc7, self.KEEP_PROB)
# 8th Layer: FC and return unscaled activations (for tf.nn.softmax_cross_entropy_with_logits)
self.fc8 = fc(fc7, 4096, self.NUM_CLASSES, name='fc8',relu = False)
def load_initial_weights(self, session):
"""
As the weights from http://www.cs.toronto.edu/~guerzhoy/tf_alexnet/ come
as a dict of lists (e.g. weights['conv1'] is a list) and not as dict of
dicts (e.g. weights['conv1'] is a dict with keys 'weights' & 'biases') we
need a special load function
"""
# Load the weights into memory
weights_dict = np.load(self.WEIGHTS_PATH, encoding = 'bytes').item()
# Loop over all layer names stored in the weights dict
for op_name in weights_dict:
# Check if the layer is one of the layers that should be reinitialized
if op_name not in self.SKIP_LAYER:
with tf.variable_scope(op_name, reuse = True):
# Loop over list of weights/biases and assign them to their corresponding tf variable
for data in weights_dict[op_name]:
# Biases
if len(data.shape) == 1:
var = tf.get_variable('biases', trainable = False)
session.run(var.assign(data))
# Weights
else:
var = tf.get_variable('weights', trainable = False)
session.run(var.assign(data))
"""
Predefine all necessary layer for the AlexNet
"""
def conv(x, filter_height, filter_width, num_filters, stride_y, stride_x, name,
padding='SAME', groups=1):
"""
Adapted from: https://github.com/ethereon/caffe-tensorflow
"""
# Get number of input channels
input_channels = int(x.get_shape()[-1])
# Create lambda function for the convolution
convolve = lambda i, k: tf.nn.conv2d(i, k,
strides = [1, stride_y, stride_x, 1],
padding = padding)
with tf.variable_scope(name) as scope:
# Create tf variables for the weights and biases of the conv layer
weights = tf.get_variable('weights', shape = [filter_height, filter_width, input_channels/groups, num_filters])
biases = tf.get_variable('biases', shape = [num_filters])
if groups == 1:
conv = convolve(x, weights)
# In the cases of multiple groups, split inputs & weights and
else:
# Split input and weights and convolve them separately
#input_groups = tf.split(value=x, num_split= groups, split_dim=3)
#input_groups = tf.split(split_dim=3, num_split= groups,value=x)
input_groups = tf.split(axis = 3, num_or_size_splits=groups, value=x)
# weight_groups = tf.split(value =weights, num_split=groups, split_dim=3)
weight_groups = tf.split(axis = 3, num_or_size_splits=groups, value=weights)
output_groups = [convolve(i, k) for i,k in zip(input_groups, weight_groups)]
# Concat the convolved output together again
#conv = tf.concat( values = output_groups,concat_dim = 3)
conv = tf.concat(axis = 3, values = output_groups)
# Add biases
bias = tf.reshape(tf.nn.bias_add(conv, biases), conv.get_shape().as_list())
# Apply relu function
relu = tf.nn.relu(bias, name = scope.name)
return relu
#def fc(x, num_in, num_out, name, relu = True):
def fc(x, num_in, num_out, name, relu):
with tf.variable_scope(name) as scope:
# Create tf variables for the weights and biases
weights = tf.get_variable('weights', shape=[num_in, num_out], trainable=True)
biases = tf.get_variable('biases', [num_out], trainable=True)
# Matrix multiply weights and inputs and add bias
act = tf.nn.xw_plus_b(x, weights, biases, name=scope.name)
if relu == True:
# Apply ReLu non linearity
relu = tf.nn.relu(act)
return relu
else:
return act
def max_pool(x, filter_height, filter_width, stride_y, stride_x, name, padding='SAME'):
return tf.nn.max_pool(x, ksize=[1, filter_height, filter_width, 1],
strides = [1, stride_y, stride_x, 1],
padding = padding, name = name)
def lrn(x, radius, alpha, beta, name, bias=1.0):
return tf.nn.local_response_normalization(x, depth_radius = radius, alpha = alpha,
beta = beta, bias = bias, name = name)
def dropout(x, keep_prob):
return tf.nn.dropout(x, keep_prob)
现在，损失功能广告优化工具的代码是
# Op for calculating the loss
with tf.name_scope("cross_ent"):
loss = tf.reduce_mean(tf.squared_difference(score, y))
# Train op
with tf.name_scope("train"):
# Get gradients of all trainable variables
gradients = tf.gradients(loss, var_list)
gradients = list(zip(gradients, var_list))
# Create optimizer and apply gradient descent to the trainable variables
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
train_op = optimizer.apply_gradients(grads_and_vars=gradients)
我应该在这部分改变什么？ 或任何评论，或任何我应该注意将模型从分类更改为回归。 我是张力流和深度学习的新手