我训练了Tensorflow Cifar10模型，我想用自己的单张图片（32 * 32，jpg / png）来喂它。
我希望看到每个标签的标签和概率作为输出，但我对此有些麻烦..
搜索堆栈溢出后，我发现了一些this的帖子，我修改了cifar10_eval.py。
但它根本不起作用。
错误信息是：
InvalidArgumentErrorTraceback（最近一次调用最后一次） in（） ----＆GT; 1评估（）
在evaluate（）中 86＃从检查站恢复 87打印（＆＃34; ckpt.model_checkpoint_path＆＃34;，ckpt.model_checkpoint_path） ---＆GT; 88 saver.restore（sess，ckpt.model_checkpoint_path） 89＃假设model_checkpoint_path看起来像： 90＃/my-favorite-path/cifar10_train/model.ckpt-0,
/home/huray/anaconda2/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/training/saver.pyc 在恢复（self，sess，save_path）1127加注 ValueError（＆＃34;使用无效的保存路径％s＆＃34;％save_path调用还原）
1128 sess.run（self.saver_def.restore_op_name， - ＆GT; 1129 {self.saver_def.filename_tensor_name：save_path}）1130 1131 @staticmethod/home/huray/anaconda2/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.pyc 在运行中（self，fetches，feed_dict，options，run_metadata） 380尝试： 381 result = self._run（None，fetches，feed_dict，options_ptr， - ＆GT; 382 run_metadata_ptr） 383如果run_metadata： 384 proto_data = tf_session.TF_GetBuffer（run_metadata_ptr）
/home/huray/anaconda2/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.pyc 在_run中（self，handle，fetches，feed_dict，options，run_metadata） 653个movers = self._update_with_movers（feed_dict_string，feed_map） 654 results = self._do_run（handle，target_list，unique_fetches， - ＆GT; 655 feed_dict_string，options，run_metadata） 656 657＃用户可能多次获取相同的张量，但我们
/home/huray/anaconda2/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.pyc 在_do_run中（self，handle，target_list，fetch_list，feed_dict，options， run_metadata） 721如果句柄为无： 722返回self._do_call（_ run_fn，self._session，feed_dict，fetch_list， - ＆GT; 723 target_list，options，run_metadata） 724其他： 725返回self._do_call（_prun_fn，self._session，handle，feed_dict，
/home/huray/anaconda2/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.pyc 在_do_call中（self，fn，* args） 741除了KeyError： 742通过 - ＆GT; 743引发类型（e）（node_def，op，message） 744 745 def _extend_graph（self）：
InvalidArgumentError：Assign要求两个张量的形状匹配。 lhs shape = [18,384] rhs shape = [2304,384] [[节点：save / Assign_5 = 分配[T = DT_FLOAT，_class = [＆＃34; loc：@ local3 / weights＆＃34;]，use_locking = true， validate_shape = TRUE， _device =＆＃34; / job：localhost / replica：0 / task：0 / cpu：0＆＃34;]（local3 / weights，save / restore_slice_5）]]
对Cifar10的任何帮助都将不胜感激。
到目前为止，这是编译问题的实现代码：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import math
import time
import numpy as np
import tensorflow as tf
import cifar10
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('eval_dir', '/tmp/cifar10_eval',
"""Directory where to write event logs.""")
tf.app.flags.DEFINE_string('eval_data', 'test',
"""Either 'test' or 'train_eval'.""")
tf.app.flags.DEFINE_string('checkpoint_dir', '/tmp/cifar10_train',
"""Directory where to read model checkpoints.""")
tf.app.flags.DEFINE_integer('eval_interval_secs', 5,
"""How often to run the eval.""")
tf.app.flags.DEFINE_integer('num_examples', 1,
"""Number of examples to run.""")
tf.app.flags.DEFINE_boolean('run_once', False,
"""Whether to run eval only once.""")
def eval_once(saver, summary_writer, top_k_op, summary_op):
"""Run Eval once.
Args:
saver: Saver.
summary_writer: Summary writer.
top_k_op: Top K op.
summary_op: Summary op.
"""
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
# Assuming model_checkpoint_path looks something like:
# /my-favorite-path/cifar10_train/model.ckpt-0,
# extract global_step from it.
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
else:
print('No checkpoint file found')
return
print("Check point : %s" % ckpt.model_checkpoint_path)
# Start the queue runners.
coord = tf.train.Coordinator()
try:
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(qr.create_threads(sess, coord=coord, daemon=True,
start=True))
num_iter = int(math.ceil(FLAGS.num_examples / FLAGS.batch_size))
true_count = 0 # Counts the number of correct predictions.
total_sample_count = num_iter * FLAGS.batch_size
step = 0
while step < num_iter and not coord.should_stop():
predictions = sess.run([top_k_op])
true_count += np.sum(predictions)
step += 1
# Compute precision @ 1.
precision = true_count / total_sample_count
print('%s: precision @ 1 = %.3f' % (datetime.now(), precision))
summary = tf.Summary()
summary.ParseFromString(sess.run(summary_op))
summary.value.add(tag='Precision @ 1', simple_value=precision)
summary_writer.add_summary(summary, global_step)
except Exception as e: # pylint: disable=broad-except
coord.request_stop(e)
coord.request_stop()
coord.join(threads, stop_grace_period_secs=10)
def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default() as g:
# Get images and labels for CIFAR-10.
eval_data = FLAGS.eval_data == 'test'
# images, labels = cifar10.inputs(eval_data=eval_data)
# TEST CODE
img_path = "/TEST_IMAGEPATH/image.png"
input_img = tf.image.decode_png(tf.read_file(img_path), channels=3)
casted_image = tf.cast(input_img, tf.float32)
reshaped_image = tf.image.resize_image_with_crop_or_pad(casted_image, 24, 24)
float_image = tf.image.per_image_withening(reshaped_image)
images = tf.expand_dims(reshaped_image, 0)
logits = cifar10.inference(images)
_, top_k_pred = tf.nn.top_k(logits, k=1)
with tf.Session() as sess:
saver = tf.train.Saver()
ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
print("ckpt.model_checkpoint_path ", ckpt.model_checkpoint_path)
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
else:
print('No checkpoint file found')
return
print("Check point : %s" % ckpt.model_checkpoint_path)
top_indices = sess.run([top_k_pred])
print ("Predicted ", top_indices[0], " for your input image.")
evaluate()
答案 0 :(得分：2)
视频https://youtu.be/d9mSWqfo0Xw显示了对单个图片进行分类的示例。
在网络已经通过python cifar10_train.py训练之后，我们评估了CIFAR-10数据库的单个图像deer6.png和火柴盒的自己的照片。 TF教程原始源代码的最重要修改如下：
首先，有必要将这些图像转换为cifar10_input.py可以读取的二进制形式。使用可在How to create dataset similar to cifar-10
找到的代码段，可以轻松完成此操作然后为了读取转换后的图像（称为input.bin），我们需要修改cifar10_input.py中的函数input（）：
else:
#filenames = [os.path.join(data_dir, 'test_batch.bin')]
filenames = [os.path.join(data_dir, 'input.bin')]
（data_dir等于'./')
最后为了得到标签，我们修改了源cifar10_eval.py中的函数eval_once（）：
#while step < num_iter and not coord.should_stop():
# predictions = sess.run([top_k_op])
print(sess.run(logits[0]))
classification = sess.run(tf.argmax(logits[0], 0))
cifar10classes = ["airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck"]
print(cifar10classes[classification])
#true_count += np.sum(predictions)
step += 1
# Compute precision @ 1.
precision = true_count / total_sample_count
# print('%s: precision @ 1 = %.3f' % (datetime.now(), precision))
当然，您需要进行一些小修改。