finetune_alexnet_with_tensorflow
finetune_alexnet_with_tensorflow copied to clipboard
How to improve accuracy
2019-05-28 10:45:45.833285 Validation Accuracy = 0.2188 2019-05-28 10:45:45.833390 Saving checkpoint of model... 2019-05-28 10:45:47.135384 Model checkpoint saved at checkpoints/model_epoch1.ckpt 2019-05-28 10:45:47.464044 Start validation 2019-05-28 10:45:50.295000 Validation Accuracy = 0.2188 2019-05-28 10:45:50.295116 Saving checkpoint of model... 2019-05-28 10:45:51.710815 Model checkpoint saved at checkpoints/model_epoch1.ckpt 2019-05-28 10:45:52.035434 Start validation 2019-05-28 10:45:54.884074 Validation Accuracy = 0.2188 2019-05-28 10:45:54.884180 Saving checkpoint of model... 2019-05-28 10:45:56.231970 Model checkpoint saved at checkpoints/model_epoch1.ckpt 2019-05-28 10:45:56.560833 Start validation 2019-05-28 10:45:59.407273 Validation Accuracy = 0.2188 2019-05-28 10:45:59.407380 Saving checkpoint of model... 2019-05-28 10:46:01.239952 Model checkpoint saved at checkpoints/model_epoch1.ckpt 2019-05-28 10:46:01.566239 Start validation 2019-05-28 10:46:04.391418 Validation Accuracy = 0.2188 2019-05-28 10:46:04.391538 Saving checkpoint of model... 2019-05-28 10:46:05.695854 Model checkpoint saved at checkpoints/model_epoch1.ckpt 2019-05-28 10:46:06.340697 Start validation 2019-05-28 10:46:09.281800 Validation Accuracy = 0.2188 2019-05-28 10:46:09.281909 Saving checkpoint of model... 2019-05-28 10:46:10.555316 Model checkpoint saved at checkpoints/model_epoch1.ckpt 2019-05-28 10:46:10.904200 Start validation 2019-05-28 10:46:13.926193 Validation Accuracy = 0.2188 2019-05-28 10:46:13.926291 Saving checkpoint of model...
As you see,accuracy is 0.2188 and not change.What can I do to fit this condition
I discard this function 'load_initial_weights', because i think w and b in net have init ,such as code:
def conv(self,x, filter_height, filter_width, num_filters, stride_y, stride_x, name,padding='SAME', groups=1):
# 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
w=tf.random_normal_initializer(mean=0.0, stddev=0.001, seed=None, dtype=tf.float32)
#b=tf.tf.constant_initializer(value)
weights = tf.get_variable('weights', shape=[filter_height,
filter_width,
input_channels/groups,
num_filters],
initializer=w,
trainable=True)
biases = tf.get_variable('biases', shape=[num_filters],initializer=tf.ones_initializer(),trainable=True)
if groups == 1:
conv = convolve(x, weights)
else:
# Split input and weights and convolve them separately
input_groups = tf.split(axis=3, num_or_size_splits=groups, value=x)
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(axis=3, values=output_groups)#拼接张量
# Add biases
bias = tf.reshape(tf.nn.bias_add(conv, biases), tf.shape(conv))
# Apply relu function
relu = tf.nn.relu(bias, name=scope.name)
return relu
if i delete function 'load_initial_weights', Have any influence on net?