我是tensorflow的新手。我正在使用cnn训练我的tensorflow模型进行数字识别。虽然，它在训练期间显示99%的准确性。但是在我的图像集上进行测试时，它会继续显示相同的结果，例所有图片有时为8，有时为所有图片2，有时为所有图片3。
请帮忙！
我附上参考代码
档案trainer.py：
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
def layer(input,weight_shape,bias_shape):
w_stddev = (2.0/weight_shape[0])**0.5
w_init = tf.random_normal_initializer(stddev = w_stddev)
b_init = tf.constant_initializer(0)
W = tf.get_variable('W',weight_shape,initializer = w_init)
b = tf.get_variable('B',bias_shape,initializer = b_init)
output = tf.matmul(input,W)+b
return tf.nn.relu(output)
def conv2d(input,weight_shape,bias_shape):
inp = weight_shape[0]*weight_shape[1]*weight_shape[2]
w_init = tf.random_normal_initializer(stddev = (2.0/inp)**0.5)
W = tf.get_variable('W',weight_shape,initializer = w_init)
b_init = tf.constant_initializer(0)
b = tf.get_variable('b',bias_shape,initializer = b_init)
conv_out = tf.nn.conv2d(input,W,strides = [1,1,1,1], padding = 'SAME')
return tf.nn.relu(tf.nn.bias_add(conv_out,b))
def max_pool(input,k=2):
return tf.nn.max_pool(input,ksize = [1,k,k,1], strides = [1,k,k,1],padding = 'SAME')
def inference(x,keep_prob):
x = tf.reshape(x,shape = [-1,28,28,1])
keep_prob = keep_prob[0]
with tf.variable_scope("conv_1"):
conv_1 = conv2d(x,[5,5,1,32],[32])
pool_1 = max_pool(conv_1)
with tf.variable_scope("conv_2"):
conv_2 = conv2d(pool_1,[5,5,32,64],[64])
pool_2 = max_pool(conv_2)
with tf.variable_scope("fc"):
pool_2_flat = tf.reshape(pool_2,[-1,7*7*64])
fc_1 = layer(pool_2_flat,[7*7*64,1024],[1024])
fc_1_drop = tf.nn.dropout(fc_1,keep_prob)
with tf.variable_scope("output"):
output = layer(fc_1_drop,[1024,10],[10])
return output
def evaluate(output,y):
correct_prediction = tf.equal(tf.argmax(output,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
return accuracy
def training(cost,global_step):
tf.summary.scalar("cost",cost)
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
train_op = optimizer.minimize(cost,global_step = global_step)
return train_op
def loss(output,y):
xentropy = tf.nn.softmax_cross_entropy_with_logits(labels = y,logits = output)
loss = tf.reduce_mean(xentropy)
return loss
learning_rate = 0.01
display_step = 1
batch_size = 100
training_epoch = 2
mnist = input_data.read_data_sets('MNIST_data/',one_hot = True)
with tf.Graph().as_default():
x = tf.placeholder('float',[None,784],name="x")
y = tf.placeholder('float',[None,10],name="y")
keep_prob = tf.placeholder('float',[1],name="keep_prob")
global_step = tf.Variable(0,name = 'global_step',trainable = False)
output = inference(x,keep_prob)
#print(output.name)
cost_op = loss(output,y)
eval_op = evaluate(output,y)
print(eval_op.name)
train_op = training(cost_op,global_step)
summary_op = tf.summary.merge_all()
saver = tf.train.Saver()
sess = tf.Session()
writer = tf.summary.FileWriter('logistics_logs/',graph_def = sess.graph_def)
init_op = tf.global_variables_initializer()
sess.run(init_op)
for epoch in range(training_epoch):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
for i in range(total_batch):
mbatch_x,mbatch_y = mnist.train.next_batch(batch_size)
feed_dict = {
x: mbatch_x,
y: mbatch_y,
keep_prob: np.asarray([0.5])
}
sess.run(train_op,feed_dict = feed_dict)
mbatch_cost = sess.run(cost_op,feed_dict = feed_dict)
avg_cost += mbatch_cost/total_batch
if epoch % display_step == 0:
val_feed_dict = {
x: mnist.validation.images,
y: mnist.validation.labels,
keep_prob: np.asarray([1])
}
accuracy = sess.run(eval_op,feed_dict = val_feed_dict)
print(epoch+1,'Validation Accuracy : ',accuracy*100,'%')
summary_str = sess.run(summary_op,feed_dict = val_feed_dict)
writer.add_summary(summary_str,sess.run(global_step))
saver.save(sess,'logistics_logs/model_checkpoint/',global_step)
print('Optimization finished')
test_feed_dict = {
x: mnist.test.images,
y: mnist.test.labels,
keep_prob: np.asarray([1])
}
accuracy = sess.run(eval_op,feed_dict = test_feed_dict)
print('Test Accuracy : ',accuracy*100,'%')
档案model.py：
import tensorflow as tf
import numpy as np
import os
import cv2
from PIL import Image
from scipy import misc
#img = Image.open('character.bmp')
#a = np.asarray(img).flatten()
#test_data = np.subtract(a,0.,dtype=np.float32)
#test_data = np.reshape(test_data,(784))
#test_data = 255*test_data
#print(test_data)
#print(test_data.shape)
image = cv2.imread('character.jpg')
image = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
image = cv2.resize(image,(28,28),cv2.INTER_LINEAR)
images= np.array(image,dtype=np.uint8)
images=images.astype('float32')
images=np.multiply(images,1.0/255.0)
images = np.asarray(images).flatten()
test_data=[images]
#print(test_data)
restore_path = os.path.join(os.path.abspath('./'),"logistics_logs\\model_checkpoint\\")
meta_file_location = os.path.join(restore_path,"-550.meta")
sess = tf.Session()
saver = tf.train.import_meta_graph(meta_file_location)
saver.restore(sess,tf.train.latest_checkpoint(restore_path))
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("x:0")
keep_prob = graph.get_tensor_by_name("keep_prob:0")
feed_dict = {x:test_data,keep_prob:np.asarray([1])}
op = graph.get_tensor_by_name("output/Relu:0")
digit = sess.run(tf.argmax(op,1),feed_dict = feed_dict)
print(int(digit))
答案 0 :(得分：0)
虽然我不能轻易地将您的代码从一个文件跟踪到另一个文件，但我很确定您的问题就在这里：
init_op = tf.global_variables_initializer()
sess.run(init_op)
我怀疑在使用以下代码加载网络后正在运行代码：
saver = tf.train.import_meta_graph(meta_file_location)
saver.restore(sess,tf.train.latest_checkpoint(restore_path))
如果是这样的话，你正在做的就是用随机初始化覆盖你的模型。从磁盘加载模型时，不应运行init操作。
无论输入如何，单个值的输出是随机初始化网络的常见结果，这是我怀疑的原因。