tensorflow模型载入失败

载入模型的时候不知道怎么出现这种报错
DataLossError (see above for traceback): Unable to open table file .\eye-model\eye_kaggle.ckpt-192.meta: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

3个回答

你打开模型的地址出错了,试试看绝对路径。

模型的路径,采用绝对路径试一下

.\eye-model\eye_kaggle.ckpt-192.meta 这边改为绝对路径

Csdn user default icon
上传中...
上传图片
插入图片
抄袭、复制答案,以达到刷声望分或其他目的的行为,在CSDN问答是严格禁止的,一经发现立刻封号。是时候展现真正的技术了!
其他相关推荐
在Golang应用服务器中重新加载Tensorflow模型

<div class="post-text" itemprop="text"> <p>I have a Golang app server wherein I keep reloading a saved tensorflow model every 15 minutes. Every api call that uses the tensorflow model, takes a read mutex lock and whenever I reload the model, I take a write lock. Functionality wise, this works fine but during the model load, my API response time increases as the request threads keep waiting for the write lock to be released. Could you please suggest a better approach to keep the loaded model up to date? </p> <p><strong>Edit, Code updated</strong></p> <p>Model Load Code:</p> <pre><code> tags := []string{"serve"} // load from updated saved model var m *tensorflow.SavedModel var err error m, err = tensorflow.LoadSavedModel("/path/to/model", tags, nil) if err != nil { log.Errorf("Exception caught while reloading saved model %v", err) destroyTFModel(m) } if err == nil { ModelLoadMutex.Lock() defer ModelLoadMutex.Unlock() // destroy existing model destroyTFModel(TensorModel) TensorModel = m } </code></pre> <p>Model Use Code(Part of the API request):</p> <pre><code> config.ModelLoadMutex.RLock() defer config.ModelLoadMutex.RUnlock() scoreTensorList, err = TensorModel.Session.Run(map[tensorflow.Output]*tensorflow.Tensor{ UserOp.Output(0): uT, DataOp.Output(0): nT}, []tensorflow.Output{config.SumOp.Output(0)}, nil, ) </code></pre> </div>

iOS OpenCV3.4.2加载TensorFlow已训练好的pb模型失败

各位大哥大姐好! 小白最近在学习OpenCV,使用的是iOS端3.4.2版本:https://opencv.org/releases.html 使用DNN的cv::dnn::readNetFromTensorflow()方法加载TensorFlow网络模型失败,net为empty TensorFlow模型使用的是别人训练好的http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz 这几天尝试了很多模型,也寻了很多中英文的网站论坛。然,未果。 这可急坏了小白,忘大神们不吝赐教!小白愿以身相...额,还是送分吧!感谢!! ![help](https://img-ask.csdn.net/upload/201809/16/1537107723_393719.png)

在jupyter notebook 导入tensorflow_hub失败

**我的tensorflow版本是2.0的gpu版本,然后tensorflow_hub是0.6版本** ![图片说明](https://img-ask.csdn.net/upload/201910/01/1569896067_863194.png) **我在pychram能够成功导入tensorflow_hub,但是在jupyter notebook却导入失败** ![图片说明](https://img-ask.csdn.net/upload/201910/01/1569896118_459889.png) 请问各位大佬,应该如何解决

用java程序调用python,tensorflow模型便不能由python程序读入了

python程序读取tensorflow模型和词向量模型。 我的java程序是一个web,用的spring框架。 没用java程序的调用的时候,python程序可以正常运行 调用过后,python中的saver=tf.train.Saver()报错 显示ValueError: No variables to save java得到的是null 想问如何使得python在被调用的情况下仍然能够正确读取模型。

tensorflow模型推理,两个列表串行,输出结果是第一个列表的循环,新手求教

tensorflow模型推理,两个列表串行,输出结果是第一个列表的循环,新手求教 ``` from __future__ import print_function import argparse from datetime import datetime import os import sys import time import scipy.misc import scipy.io as sio import cv2 from glob import glob import multiprocessing os.environ["CUDA_VISIBLE_DEVICES"] = "0" import tensorflow as tf import numpy as np from PIL import Image from utils import * N_CLASSES = 20 DATA_DIR = './datasets/CIHP' LIST_PATH = './datasets/CIHP/list/val2.txt' DATA_ID_LIST = './datasets/CIHP/list/val_id2.txt' with open(DATA_ID_LIST, 'r') as f: NUM_STEPS = len(f.readlines()) RESTORE_FROM = './checkpoint/CIHP_pgn' # Load reader. with tf.name_scope("create_inputs") as scp1: reader = ImageReader(DATA_DIR, LIST_PATH, DATA_ID_LIST, None, False, False, False, None) image, label, edge_gt = reader.image, reader.label, reader.edge image_rev = tf.reverse(image, tf.stack([1])) image_list = reader.image_list image_batch = tf.stack([image, image_rev]) label_batch = tf.expand_dims(label, dim=0) # Add one batch dimension. edge_gt_batch = tf.expand_dims(edge_gt, dim=0) h_orig, w_orig = tf.to_float(tf.shape(image_batch)[1]), tf.to_float(tf.shape(image_batch)[2]) image_batch050 = tf.image.resize_images(image_batch, tf.stack([tf.to_int32(tf.multiply(h_orig, 0.50)), tf.to_int32(tf.multiply(w_orig, 0.50))])) image_batch075 = tf.image.resize_images(image_batch, tf.stack([tf.to_int32(tf.multiply(h_orig, 0.75)), tf.to_int32(tf.multiply(w_orig, 0.75))])) image_batch125 = tf.image.resize_images(image_batch, tf.stack([tf.to_int32(tf.multiply(h_orig, 1.25)), tf.to_int32(tf.multiply(w_orig, 1.25))])) image_batch150 = tf.image.resize_images(image_batch, tf.stack([tf.to_int32(tf.multiply(h_orig, 1.50)), tf.to_int32(tf.multiply(w_orig, 1.50))])) image_batch175 = tf.image.resize_images(image_batch, tf.stack([tf.to_int32(tf.multiply(h_orig, 1.75)), tf.to_int32(tf.multiply(w_orig, 1.75))])) ``` 新建网络 ``` # Create network. with tf.variable_scope('', reuse=False) as scope: net_100 = PGNModel({'data': image_batch}, is_training=False, n_classes=N_CLASSES) with tf.variable_scope('', reuse=True): net_050 = PGNModel({'data': image_batch050}, is_training=False, n_classes=N_CLASSES) with tf.variable_scope('', reuse=True): net_075 = PGNModel({'data': image_batch075}, is_training=False, n_classes=N_CLASSES) with tf.variable_scope('', reuse=True): net_125 = PGNModel({'data': image_batch125}, is_training=False, n_classes=N_CLASSES) with tf.variable_scope('', reuse=True): net_150 = PGNModel({'data': image_batch150}, is_training=False, n_classes=N_CLASSES) with tf.variable_scope('', reuse=True): net_175 = PGNModel({'data': image_batch175}, is_training=False, n_classes=N_CLASSES) # parsing net parsing_out1_050 = net_050.layers['parsing_fc'] parsing_out1_075 = net_075.layers['parsing_fc'] parsing_out1_100 = net_100.layers['parsing_fc'] parsing_out1_125 = net_125.layers['parsing_fc'] parsing_out1_150 = net_150.layers['parsing_fc'] parsing_out1_175 = net_175.layers['parsing_fc'] parsing_out2_050 = net_050.layers['parsing_rf_fc'] parsing_out2_075 = net_075.layers['parsing_rf_fc'] parsing_out2_100 = net_100.layers['parsing_rf_fc'] parsing_out2_125 = net_125.layers['parsing_rf_fc'] parsing_out2_150 = net_150.layers['parsing_rf_fc'] parsing_out2_175 = net_175.layers['parsing_rf_fc'] # edge net edge_out2_100 = net_100.layers['edge_rf_fc'] edge_out2_125 = net_125.layers['edge_rf_fc'] edge_out2_150 = net_150.layers['edge_rf_fc'] edge_out2_175 = net_175.layers['edge_rf_fc'] # combine resize parsing_out1 = tf.reduce_mean(tf.stack([tf.image.resize_images(parsing_out1_050, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out1_075, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out1_100, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out1_125, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out1_150, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out1_175, tf.shape(image_batch)[1:3,])]), axis=0) parsing_out2 = tf.reduce_mean(tf.stack([tf.image.resize_images(parsing_out2_050, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out2_075, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out2_100, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out2_125, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out2_150, tf.shape(image_batch)[1:3,]), tf.image.resize_images(parsing_out2_175, tf.shape(image_batch)[1:3,])]), axis=0) edge_out2_100 = tf.image.resize_images(edge_out2_100, tf.shape(image_batch)[1:3,]) edge_out2_125 = tf.image.resize_images(edge_out2_125, tf.shape(image_batch)[1:3,]) edge_out2_150 = tf.image.resize_images(edge_out2_150, tf.shape(image_batch)[1:3,]) edge_out2_175 = tf.image.resize_images(edge_out2_175, tf.shape(image_batch)[1:3,]) edge_out2 = tf.reduce_mean(tf.stack([edge_out2_100, edge_out2_125, edge_out2_150, edge_out2_175]), axis=0) raw_output = tf.reduce_mean(tf.stack([parsing_out1, parsing_out2]), axis=0) head_output, tail_output = tf.unstack(raw_output, num=2, axis=0) tail_list = tf.unstack(tail_output, num=20, axis=2) tail_list_rev = [None] * 20 for xx in range(14): tail_list_rev[xx] = tail_list[xx] tail_list_rev[14] = tail_list[15] tail_list_rev[15] = tail_list[14] tail_list_rev[16] = tail_list[17] tail_list_rev[17] = tail_list[16] tail_list_rev[18] = tail_list[19] tail_list_rev[19] = tail_list[18] tail_output_rev = tf.stack(tail_list_rev, axis=2) tail_output_rev = tf.reverse(tail_output_rev, tf.stack([1])) raw_output_all = tf.reduce_mean(tf.stack([head_output, tail_output_rev]), axis=0) raw_output_all = tf.expand_dims(raw_output_all, dim=0) pred_scores = tf.reduce_max(raw_output_all, axis=3) raw_output_all = tf.argmax(raw_output_all, axis=3) pred_all = tf.expand_dims(raw_output_all, dim=3) # Create 4-d tensor. raw_edge = tf.reduce_mean(tf.stack([edge_out2]), axis=0) head_output, tail_output = tf.unstack(raw_edge, num=2, axis=0) tail_output_rev = tf.reverse(tail_output, tf.stack([1])) raw_edge_all = tf.reduce_mean(tf.stack([head_output, tail_output_rev]), axis=0) raw_edge_all = tf.expand_dims(raw_edge_all, dim=0) pred_edge = tf.sigmoid(raw_edge_all) res_edge = tf.cast(tf.greater(pred_edge, 0.5), tf.int32) # prepare ground truth preds = tf.reshape(pred_all, [-1,]) gt = tf.reshape(label_batch, [-1,]) weights = tf.cast(tf.less_equal(gt, N_CLASSES - 1), tf.int32) # Ignoring all labels greater than or equal to n_classes. mIoU, update_op_iou = tf.contrib.metrics.streaming_mean_iou(preds, gt, num_classes=N_CLASSES, weights=weights) macc, update_op_acc = tf.contrib.metrics.streaming_accuracy(preds, gt, weights=weights) # # Which variables to load. # restore_var = tf.global_variables() # # Set up tf session and initialize variables. # config = tf.ConfigProto() # config.gpu_options.allow_growth = True # # gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.7) # # config=tf.ConfigProto(gpu_options=gpu_options) # init = tf.global_variables_initializer() # evaluate prosessing parsing_dir = './output' # Set up tf session and initialize variables. config = tf.ConfigProto() config.gpu_options.allow_growth = True ``` 以上是初始化网络和初始化参数载入模型,下面定义两个函数分别处理val1.txt和val2.txt两个列表内部的数据。 ``` # 处理第一个列表函数 def humanParsing1(): # Which variables to load. restore_var = tf.global_variables() init = tf.global_variables_initializer() with tf.Session(config=config) as sess: sess.run(init) sess.run(tf.local_variables_initializer()) # Load weights. loader = tf.train.Saver(var_list=restore_var) if RESTORE_FROM is not None: if load(loader, sess, RESTORE_FROM): print(" [*] Load SUCCESS") else: print(" [!] Load failed...") # Create queue coordinator. coord = tf.train.Coordinator() # Start queue threads. threads = tf.train.start_queue_runners(coord=coord, sess=sess) # Iterate over training steps. for step in range(NUM_STEPS): # parsing_, scores, edge_ = sess.run([pred_all, pred_scores, pred_edge])# , update_op parsing_, scores, edge_ = sess.run([pred_all, pred_scores, pred_edge]) # , update_op print('step {:d}'.format(step)) print(image_list[step]) img_split = image_list[step].split('/') img_id = img_split[-1][:-4] msk = decode_labels(parsing_, num_classes=N_CLASSES) parsing_im = Image.fromarray(msk[0]) parsing_im.save('{}/{}_vis.png'.format(parsing_dir, img_id)) coord.request_stop() coord.join(threads) # 处理第二个列表函数 def humanParsing2(): # Set up tf session and initialize variables. config = tf.ConfigProto() config.gpu_options.allow_growth = True # gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.7) # config=tf.ConfigProto(gpu_options=gpu_options) # Which variables to load. restore_var = tf.global_variables() init = tf.global_variables_initializer() with tf.Session(config=config) as sess: # Create queue coordinator. coord = tf.train.Coordinator() sess.run(init) sess.run(tf.local_variables_initializer()) # Load weights. loader = tf.train.Saver(var_list=restore_var) if RESTORE_FROM is not None: if load(loader, sess, RESTORE_FROM): print(" [*] Load SUCCESS") else: print(" [!] Load failed...") LIST_PATH = './datasets/CIHP/list/val1.txt' DATA_ID_LIST = './datasets/CIHP/list/val_id1.txt' with open(DATA_ID_LIST, 'r') as f: NUM_STEPS = len(f.readlines()) # with tf.name_scope("create_inputs"): with tf.name_scope(scp1): tf.get_variable_scope().reuse_variables() reader = ImageReader(DATA_DIR, LIST_PATH, DATA_ID_LIST, None, False, False, False, coord) image, label, edge_gt = reader.image, reader.label, reader.edge image_rev = tf.reverse(image, tf.stack([1])) image_list = reader.image_list # Start queue threads. threads = tf.train.start_queue_runners(coord=coord, sess=sess) # Load weights. loader = tf.train.Saver(var_list=restore_var) if RESTORE_FROM is not None: if load(loader, sess, RESTORE_FROM): print(" [*] Load SUCCESS") else: print(" [!] Load failed...") # Iterate over training steps. for step in range(NUM_STEPS): # parsing_, scores, edge_ = sess.run([pred_all, pred_scores, pred_edge])# , update_op parsing_, scores, edge_ = sess.run([pred_all, pred_scores, pred_edge]) # , update_op print('step {:d}'.format(step)) print(image_list[step]) img_split = image_list[step].split('/') img_id = img_split[-1][:-4] msk = decode_labels(parsing_, num_classes=N_CLASSES) parsing_im = Image.fromarray(msk[0]) parsing_im.save('{}/{}_vis.png'.format(parsing_dir, img_id)) coord.request_stop() coord.join(threads) if __name__ == '__main__': humanParsing1() humanParsing2() ``` 最终输出结果一直是第一个列表里面的循环,代码上用了 self.queue = tf.train.slice_input_producer([self.images, self.labels, self.edges], shuffle=shuffle),队列的方式进行多线程推理。最终得到的结果一直是第一个列表的循环,求大神告诉问题怎么解决。

tensorflow载入训练好的模型进行预测,同一张图片预测的结果却不一样????

最近在跑deeplabv1,在测试代码的时候,跑通了训练程序,但是用训练好的模型进行与测试却发现相同的图片预测的结果不一样??请问有大神知道怎么回事吗? 用的是saver.restore()方法载入模型。代码如下: ``` def main(): """Create the model and start the inference process.""" args = get_arguments() # Prepare image. img = tf.image.decode_jpeg(tf.read_file(args.img_path), channels=3) # Convert RGB to BGR. img_r, img_g, img_b = tf.split(value=img, num_or_size_splits=3, axis=2) img = tf.cast(tf.concat(axis=2, values=[img_b, img_g, img_r]), dtype=tf.float32) # Extract mean. img -= IMG_MEAN # Create network. net = DeepLabLFOVModel() # Which variables to load. trainable = tf.trainable_variables() # Predictions. pred = net.preds(tf.expand_dims(img, dim=0)) # Set up TF session and initialize variables. config = tf.ConfigProto() config.gpu_options.allow_growth = True sess = tf.Session(config=config) #init = tf.global_variables_initializer() sess.run(tf.global_variables_initializer()) # Load weights. saver = tf.train.Saver(var_list=trainable) load(saver, sess, args.model_weights) # Perform inference. preds = sess.run([pred]) print(preds) if not os.path.exists(args.save_dir): os.makedirs(args.save_dir) msk = decode_labels(np.array(preds)[0, 0, :, :, 0]) im = Image.fromarray(msk) im.save(args.save_dir + 'mask1.png') print('The output file has been saved to {}'.format( args.save_dir + 'mask.png')) if __name__ == '__main__': main() ``` 其中load是 ``` def load(saver, sess, ckpt_path): '''Load trained weights. Args: saver: TensorFlow saver object. sess: TensorFlow session. ckpt_path: path to checkpoint file with parameters. ''' ckpt = tf.train.get_checkpoint_state(ckpt_path) if ckpt and ckpt.model_checkpoint_path: saver.restore(sess, ckpt.model_checkpoint_path) print("Restored model parameters from {}".format(ckpt_path)) ``` DeepLabLFOVMode类如下: ``` class DeepLabLFOVModel(object): """DeepLab-LargeFOV model with atrous convolution and bilinear upsampling. This class implements a multi-layer convolutional neural network for semantic image segmentation task. This is the same as the model described in this paper: https://arxiv.org/abs/1412.7062 - please look there for details. """ def __init__(self, weights_path=None): """Create the model. Args: weights_path: the path to the cpkt file with dictionary of weights from .caffemodel. """ self.variables = self._create_variables(weights_path) def _create_variables(self, weights_path): """Create all variables used by the network. This allows to share them between multiple calls to the loss function. Args: weights_path: the path to the ckpt file with dictionary of weights from .caffemodel. If none, initialise all variables randomly. Returns: A dictionary with all variables. """ var = list() index = 0 if weights_path is not None: with open(weights_path, "rb") as f: weights = cPickle.load(f) # Load pre-trained weights. for name, shape in net_skeleton: var.append(tf.Variable(weights[name], name=name)) del weights else: # Initialise all weights randomly with the Xavier scheme, # and # all biases to 0's. for name, shape in net_skeleton: if "/w" in name: # Weight filter. w = create_variable(name, list(shape)) var.append(w) else: b = create_bias_variable(name, list(shape)) var.append(b) return var def _create_network(self, input_batch, keep_prob): """Construct DeepLab-LargeFOV network. Args: input_batch: batch of pre-processed images. keep_prob: probability of keeping neurons intact. Returns: A downsampled segmentation mask. """ current = input_batch v_idx = 0 # Index variable. # Last block is the classification layer. for b_idx in xrange(len(dilations) - 1): for l_idx, dilation in enumerate(dilations[b_idx]): w = self.variables[v_idx * 2] b = self.variables[v_idx * 2 + 1] if dilation == 1: conv = tf.nn.conv2d(current, w, strides=[ 1, 1, 1, 1], padding='SAME') else: conv = tf.nn.atrous_conv2d( current, w, dilation, padding='SAME') current = tf.nn.relu(tf.nn.bias_add(conv, b)) v_idx += 1 # Optional pooling and dropout after each block. if b_idx < 3: current = tf.nn.max_pool(current, ksize=[1, ks, ks, 1], strides=[1, 2, 2, 1], padding='SAME') elif b_idx == 3: current = tf.nn.max_pool(current, ksize=[1, ks, ks, 1], strides=[1, 1, 1, 1], padding='SAME') elif b_idx == 4: current = tf.nn.max_pool(current, ksize=[1, ks, ks, 1], strides=[1, 1, 1, 1], padding='SAME') current = tf.nn.avg_pool(current, ksize=[1, ks, ks, 1], strides=[1, 1, 1, 1], padding='SAME') elif b_idx <= 6: current = tf.nn.dropout(current, keep_prob=keep_prob) # Classification layer; no ReLU. # w = self.variables[v_idx * 2] w = create_variable(name='w', shape=[1, 1, 1024, n_classes]) # b = self.variables[v_idx * 2 + 1] b = create_bias_variable(name='b', shape=[n_classes]) conv = tf.nn.conv2d(current, w, strides=[1, 1, 1, 1], padding='SAME') current = tf.nn.bias_add(conv, b) return current def prepare_label(self, input_batch, new_size): """Resize masks and perform one-hot encoding. Args: input_batch: input tensor of shape [batch_size H W 1]. new_size: a tensor with new height and width. Returns: Outputs a tensor of shape [batch_size h w 18] with last dimension comprised of 0's and 1's only. """ with tf.name_scope('label_encode'): # As labels are integer numbers, need to use NN interp. input_batch = tf.image.resize_nearest_neighbor( input_batch, new_size) # Reducing the channel dimension. input_batch = tf.squeeze(input_batch, squeeze_dims=[3]) input_batch = tf.one_hot(input_batch, depth=n_classes) return input_batch def preds(self, input_batch): """Create the network and run inference on the input batch. Args: input_batch: batch of pre-processed images. Returns: Argmax over the predictions of the network of the same shape as the input. """ raw_output = self._create_network( tf.cast(input_batch, tf.float32), keep_prob=tf.constant(1.0)) raw_output = tf.image.resize_bilinear( raw_output, tf.shape(input_batch)[1:3, ]) raw_output = tf.argmax(raw_output, dimension=3) raw_output = tf.expand_dims(raw_output, dim=3) # Create 4D-tensor. return tf.cast(raw_output, tf.uint8) def loss(self, img_batch, label_batch): """Create the network, run inference on the input batch and compute loss. Args: input_batch: batch of pre-processed images. Returns: Pixel-wise softmax loss. """ raw_output = self._create_network( tf.cast(img_batch, tf.float32), keep_prob=tf.constant(0.5)) prediction = tf.reshape(raw_output, [-1, n_classes]) # Need to resize labels and convert using one-hot encoding. label_batch = self.prepare_label( label_batch, tf.stack(raw_output.get_shape()[1:3])) gt = tf.reshape(label_batch, [-1, n_classes]) # Pixel-wise softmax loss. loss = tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=gt) reduced_loss = tf.reduce_mean(loss) return reduced_loss ``` 按理说载入模型应该没有问题,可是不知道为什么结果却不一样? 图片:![图片说明](https://img-ask.csdn.net/upload/201911/15/1573810836_83106.jpg) ![图片说明](https://img-ask.csdn.net/upload/201911/15/1573810850_924663.png) 预测的结果: ![图片说明](https://img-ask.csdn.net/upload/201911/15/1573810884_985680.png) ![图片说明](https://img-ask.csdn.net/upload/201911/15/1573810904_577649.png) 两次结果不一样,与保存的模型算出来的结果也不一样。 我用的是GitHub上这个人的代码: https://github.com/minar09/DeepLab-LFOV-TensorFlow 急急急,请问有大神知道吗???

tensorflow模型ckpt转化为pb后,pb文件1kb

转换后的pb文件也无法调用,不知道是我转换代码问题还是什么问题。 请大神赐教,如果是代码问题也请大神提点一下转换代码

tensorflow重载模型继续训练得到的loss比原模型继续训练得到的loss大,是什么原因??

我使用tensorflow训练了一个模型,在第10个epoch时保存模型,然后在一个新的文件里重载模型继续训练,结果我发现重载的模型在第一个epoch的loss比原模型在epoch=11的loss要大,我感觉既然是重载了原模型,那么重载模型训练的第一个epoch应该是和原模型训练的第11个epoch相等的,一直找不到问题或者自己逻辑的问题,希望大佬能指点迷津。源代码和重载模型的代码如下: ``` 原代码: from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf import os import numpy as np os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' mnist = input_data.read_data_sets("./",one_hot=True) tf.reset_default_graph() ###定义数据和标签 n_inputs = 784 n_classes = 10 X = tf.placeholder(tf.float32,[None,n_inputs],name='X') Y = tf.placeholder(tf.float32,[None,n_classes],name='Y') ###定义网络结构 n_hidden_1 = 256 n_hidden_2 = 256 layer_1 = tf.layers.dense(inputs=X,units=n_hidden_1,activation=tf.nn.relu,kernel_regularizer=tf.contrib.layers.l2_regularizer(0.01)) layer_2 = tf.layers.dense(inputs=layer_1,units=n_hidden_2,activation=tf.nn.relu,kernel_regularizer=tf.contrib.layers.l2_regularizer(0.01)) outputs = tf.layers.dense(inputs=layer_2,units=n_classes,name='outputs') pred = tf.argmax(tf.nn.softmax(outputs,axis=1),axis=1) print(pred.name) err = tf.count_nonzero((pred - tf.argmax(Y,axis=1))) cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=outputs,labels=Y),name='cost') print(cost.name) ###定义优化器 learning_rate = 0.001 optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost,name='OP') saver = tf.train.Saver() checkpoint = 'softmax_model/dense_model.cpkt' ###训练 batch_size = 100 training_epochs = 11 with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for epoch in range(training_epochs): batch_num = int(mnist.train.num_examples / batch_size) epoch_cost = 0 sumerr = 0 for i in range(batch_num): batch_x,batch_y = mnist.train.next_batch(batch_size) c,e = sess.run([cost,err],feed_dict={X:batch_x,Y:batch_y}) _ = sess.run(optimizer,feed_dict={X:batch_x,Y:batch_y}) epoch_cost += c / batch_num sumerr += e / mnist.train.num_examples if epoch == (training_epochs - 1): print('batch_cost = ',c) if epoch == (training_epochs - 2): saver.save(sess, checkpoint) print('test_error = ',sess.run(cost, feed_dict={X: mnist.test.images, Y: mnist.test.labels})) ``` ``` 重载模型的代码: from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' mnist = input_data.read_data_sets("./",one_hot=True) #one_hot=True指对样本标签进行独热编码 file_path = 'softmax_model/dense_model.cpkt' saver = tf.train.import_meta_graph(file_path + '.meta') graph = tf.get_default_graph() X = graph.get_tensor_by_name('X:0') Y = graph.get_tensor_by_name('Y:0') cost = graph.get_operation_by_name('cost').outputs[0] train_op = graph.get_operation_by_name('OP') training_epoch = 10 learning_rate = 0.001 batch_size = 100 with tf.Session() as sess: saver.restore(sess,file_path) print('test_cost = ',sess.run(cost, feed_dict={X: mnist.test.images, Y: mnist.test.labels})) for epoch in range(training_epoch): batch_num = int(mnist.train.num_examples / batch_size) epoch_cost = 0 for i in range(batch_num): batch_x, batch_y = mnist.train.next_batch(batch_size) c = sess.run(cost, feed_dict={X: batch_x, Y: batch_y}) _ = sess.run(train_op, feed_dict={X: batch_x, Y: batch_y}) epoch_cost += c / batch_num print(epoch_cost) ``` 值得注意的是,我在原模型和重载模型里都计算了测试集的cost,两者的结果是一致的。说明参数载入应该是对的

tensorflow训练完模型直接测试和导入模型进行测试的结果不同,一个很好,一个略差,这是为什么?

在tensorflow训练完模型,我直接采用同一个session进行测试,得到结果较好,但是采用训练完保存的模型,进行重新载入进行测试,结果较差,不懂是为什么会出现这样的结果。注:测试数据是一样的。以下是模型结果: 训练集:loss:0.384,acc:0.931. 验证集:loss:0.212,acc:0.968. 训练完在同一session内的测试集:acc:0.96。导入保存的模型进行测试:acc:0.29 ``` def create_model(hps): global_step = tf.Variable(tf.zeros([], tf.float64), name = 'global_step', trainable = False) scale = 1.0 / math.sqrt(hps.num_embedding_size + hps.num_lstm_nodes[-1]) / 3.0 print(type(scale)) gru_init = tf.random_normal_initializer(-scale, scale) with tf.variable_scope('Bi_GRU_nn', initializer = gru_init): for i in range(hps.num_lstm_layers): cell_bw = tf.contrib.rnn.GRUCell(hps.num_lstm_nodes[i], activation = tf.nn.relu, name = 'cell-bw') cell_bw = tf.contrib.rnn.DropoutWrapper(cell_bw, output_keep_prob = dropout_keep_prob) cell_fw = tf.contrib.rnn.GRUCell(hps.num_lstm_nodes[i], activation = tf.nn.relu, name = 'cell-fw') cell_fw = tf.contrib.rnn.DropoutWrapper(cell_fw, output_keep_prob = dropout_keep_prob) rnn_outputs, _ = tf.nn.bidirectional_dynamic_rnn(cell_bw, cell_fw, inputs, dtype=tf.float32) embeddedWords = tf.concat(rnn_outputs, 2) finalOutput = embeddedWords[:, -1, :] outputSize = hps.num_lstm_nodes[-1] * 2 # 因为是双向LSTM,最终的输出值是fw和bw的拼接,因此要乘以2 last = tf.reshape(finalOutput, [-1, outputSize]) # reshape成全连接层的输入维度 last = tf.layers.batch_normalization(last, training = is_training) fc_init = tf.uniform_unit_scaling_initializer(factor = 1.0) with tf.variable_scope('fc', initializer = fc_init): fc1 = tf.layers.dense(last, hps.num_fc_nodes, name = 'fc1') fc1_batch_normalization = tf.layers.batch_normalization(fc1, training = is_training) fc_activation = tf.nn.relu(fc1_batch_normalization) logits = tf.layers.dense(fc_activation, hps.num_classes, name = 'fc2') with tf.name_scope('metrics'): softmax_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = logits, labels = tf.argmax(outputs, 1)) loss = tf.reduce_mean(softmax_loss) # [0, 1, 5, 4, 2] ->argmax:2 因为在第二个位置上是最大的 y_pred = tf.argmax(tf.nn.softmax(logits), 1, output_type = tf.int64, name = 'y_pred') # 计算准确率,看看算对多少个 correct_pred = tf.equal(tf.argmax(outputs, 1), y_pred) # tf.cast 将数据转换成 tf.float32 类型 accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) with tf.name_scope('train_op'): tvar = tf.trainable_variables() for var in tvar: print('variable name: %s' % (var.name)) grads, _ = tf.clip_by_global_norm(tf.gradients(loss, tvar), hps.clip_lstm_grads) optimizer = tf.train.AdamOptimizer(hps.learning_rate) train_op = optimizer.apply_gradients(zip(grads, tvar), global_step) # return((inputs, outputs, is_training), (loss, accuracy, y_pred), (train_op, global_step)) return((inputs, outputs), (loss, accuracy, y_pred), (train_op, global_step)) placeholders, metrics, others = create_model(hps) content, labels = placeholders loss, accuracy, y_pred = metrics train_op, global_step = others def val_steps(sess, x_batch, y_batch, writer = None): loss_val, accuracy_val = sess.run([loss,accuracy], feed_dict = {inputs: x_batch, outputs: y_batch, is_training: hps.val_is_training, dropout_keep_prob: 1.0}) return loss_val, accuracy_val loss_summary = tf.summary.scalar('loss', loss) accuracy_summary = tf.summary.scalar('accuracy', accuracy) # 将所有的变量都集合起来 merged_summary = tf.summary.merge_all() # 用于test测试的summary merged_summary_test = tf.summary.merge([loss_summary, accuracy_summary]) LOG_DIR = '.' run_label = 'run_Bi-GRU_Dropout_tensorboard' run_dir = os.path.join(LOG_DIR, run_label) if not os.path.exists(run_dir): os.makedirs(run_dir) train_log_dir = os.path.join(run_dir, timestamp, 'train') test_los_dir = os.path.join(run_dir, timestamp, 'test') if not os.path.exists(train_log_dir): os.makedirs(train_log_dir) if not os.path.join(test_los_dir): os.makedirs(test_los_dir) # saver得到的文件句柄,可以将文件训练的快照保存到文件夹中去 saver = tf.train.Saver(tf.global_variables(), max_to_keep = 5) # train 代码 init_op = tf.global_variables_initializer() train_keep_prob_value = 0.2 test_keep_prob_value = 1.0 # 由于如果按照每一步都去计算的话,会很慢,所以我们规定每100次存储一次 output_summary_every_steps = 100 num_train_steps = 1000 # 每隔多少次保存一次 output_model_every_steps = 500 # 测试集测试 test_model_all_steps = 4000 i = 0 session_conf = tf.ConfigProto( gpu_options = tf.GPUOptions(allow_growth=True), allow_soft_placement = True, log_device_placement = False) with tf.Session(config = session_conf) as sess: sess.run(init_op) # 将训练过程中,将loss,accuracy写入文件里,后面是目录和计算图,如果想要在tensorboard中显示计算图,就想sess.graph加上 train_writer = tf.summary.FileWriter(train_log_dir, sess.graph) # 同样将测试的结果保存到tensorboard中,没有计算图 test_writer = tf.summary.FileWriter(test_los_dir) batches = batch_iter(list(zip(x_train, y_train)), hps.batch_size, hps.num_epochs) for batch in batches: train_x, train_y = zip(*batch) eval_ops = [loss, accuracy, train_op, global_step] should_out_summary = ((i + 1) % output_summary_every_steps == 0) if should_out_summary: eval_ops.append(merged_summary) # 那三个占位符输进去 # 计算loss, accuracy, train_op, global_step的图 eval_ops.append(merged_summary) outputs_train = sess.run(eval_ops, feed_dict={ inputs: train_x, outputs: train_y, dropout_keep_prob: train_keep_prob_value, is_training: hps.train_is_training }) loss_train, accuracy_train = outputs_train[0:2] if should_out_summary: # 由于我们想在100steps之后计算summary,所以上面 should_out_summary = ((i + 1) % output_summary_every_steps == 0)成立, # 即为真True,那么我们将训练的内容放入eval_ops的最后面了,因此,我们想获得summary的结果得在eval_ops_results的最后一个 train_summary_str = outputs_train[-1] # 将获得的结果写训练tensorboard文件夹中,由于训练从0开始,所以这里加上1,表示第几步的训练 train_writer.add_summary(train_summary_str, i + 1) test_summary_str = sess.run([merged_summary_test], feed_dict = {inputs: x_dev, outputs: y_dev, dropout_keep_prob: 1.0, is_training: hps.val_is_training })[0] test_writer.add_summary(test_summary_str, i + 1) current_step = tf.train.global_step(sess, global_step) if (i + 1) % 100 == 0: print("Step: %5d, loss: %3.3f, accuracy: %3.3f" % (i + 1, loss_train, accuracy_train)) # 500个batch校验一次 if (i + 1) % 500 == 0: loss_eval, accuracy_eval = val_steps(sess, x_dev, y_dev) print("Step: %5d, val_loss: %3.3f, val_accuracy: %3.3f" % (i + 1, loss_eval, accuracy_eval)) if (i + 1) % output_model_every_steps == 0: path = saver.save(sess,os.path.join(out_dir, 'ckp-%05d' % (i + 1))) print("Saved model checkpoint to {}\n".format(path)) print('model saved to ckp-%05d' % (i + 1)) if (i + 1) % test_model_all_steps == 0: # test_loss, test_acc, all_predictions= sess.run([loss, accuracy, y_pred], feed_dict = {inputs: x_test, outputs: y_test, dropout_keep_prob: 1.0}) test_loss, test_acc, all_predictions= sess.run([loss, accuracy, y_pred], feed_dict = {inputs: x_test, outputs: y_test, is_training: hps.val_is_training, dropout_keep_prob: 1.0}) print("test_loss: %3.3f, test_acc: %3.3d" % (test_loss, test_acc)) batches = batch_iter(list(x_test), 128, 1, shuffle=False) # Collect the predictions here all_predictions = [] for x_test_batch in batches: batch_predictions = sess.run(y_pred, {inputs: x_test_batch, is_training: hps.val_is_training, dropout_keep_prob: 1.0}) all_predictions = np.concatenate([all_predictions, batch_predictions]) correct_predictions = float(sum(all_predictions == y.flatten())) print("Total number of test examples: {}".format(len(y_test))) print("Accuracy: {:g}".format(correct_predictions/float(len(y_test)))) test_y = y_test.argmax(axis = 1) #生成混淆矩阵 conf_mat = confusion_matrix(test_y, all_predictions) fig, ax = plt.subplots(figsize = (4,2)) sns.heatmap(conf_mat, annot=True, fmt = 'd', xticklabels = cat_id_df.category_id.values, yticklabels = cat_id_df.category_id.values) font_set = FontProperties(fname = r"/usr/share/fonts/truetype/wqy/wqy-microhei.ttc", size=15) plt.ylabel(u'实际结果',fontsize = 18,fontproperties = font_set) plt.xlabel(u'预测结果',fontsize = 18,fontproperties = font_set) plt.savefig('./test.png') print('accuracy %s' % accuracy_score(all_predictions, test_y)) print(classification_report(test_y, all_predictions,target_names = cat_id_df['category_name'].values)) print(classification_report(test_y, all_predictions)) i += 1 ``` 以上的模型代码,请求各位大神帮我看看,为什么出现这样的结果?

c++内如何导入tensorflow中训练好的模型

我现在用tensorflow训练了一个自己搭建的卷积神经网络,现在需要再用c++实现该网络,不知道如何将这个模型保存成文本文件,然后再导入c++

Tensorflow可视化问题

用Tensorboard可视化时,logs文件生成格式不对,请问是什么问题?![图片说明](https://img-ask.csdn.net/upload/201805/02/1525260071_324541.png)

Tensorflow 多GPU并行训练,模型收敛su'du'ma

在使用多GPU并行训练深度学习神经网络时,以TFrecords 形式读取MNIST数据的训练数据进行训练,发现比直接用MNIST训练数据训练相同模型时,发现前者收敛速度慢和运行时间长,已知模型没有问题,想请大神帮忙看看是什么原因导致运行速度慢,运行时间长 ``` import os import time import numpy as np import tensorflow as tf from datetime import datetime import tensorflow.compat.v1 as v1 from tensorflow.examples.tutorials.mnist import input_data BATCH_SIZE = 100 LEARNING_RATE = 1e-4 LEARNING_RATE_DECAY = 0.99 REGULARZTION_RATE = 1e-4 EPOCHS = 10000 MOVING_AVERAGE_DECAY = 0.99 N_GPU = 2 MODEL_SAVE_PATH = r'F:\model\log_dir' MODEL_NAME = 'model.ckpt' TRAIN_PATH = r'F:\model\threads_file\MNIST_data_tfrecords\train.tfrecords' TEST_PATH = r'F:\model\threads_file\MNIST_data_tfrecords\test.tfrecords' def __int64_feature(value): return v1.train.Feature(int64_list=v1.train.Int64List(value=[value])) def __bytes_feature(value): return v1.train.Feature(bytes_list=v1.train.BytesList(value=[value])) def creat_tfrecords(path, data, labels): writer = tf.io.TFRecordWriter(path) for i in range(len(data)): image = data[i].tostring() label = labels[i] examples = v1.train.Example(features=v1.train.Features(feature={ 'image': __bytes_feature(image), 'label': __int64_feature(label) })) writer.write(examples.SerializeToString()) writer.close() def parser(record): features = v1.parse_single_example(record, features={ 'image': v1.FixedLenFeature([], tf.string), 'label': v1.FixedLenFeature([], tf.int64) }) image = tf.decode_raw(features['image'], tf.uint8) image = tf.reshape(image, [28, 28, 1]) image = tf.cast(image, tf.float32) label = tf.cast(features['label'], tf.int32) label = tf.one_hot(label, 10, on_value=1, off_value=0) return image, label def get_input(batch_size, path): dataset = tf.data.TFRecordDataset([path]) dataset = dataset.map(parser) dataset = dataset.shuffle(10000) dataset = dataset.repeat(100) dataset = dataset.batch(batch_size) iterator = dataset.make_one_shot_iterator() image, label = iterator.get_next() return image, label def model_inference(images, labels, rate, regularzer=None, reuse_variables=None): with v1.variable_scope(v1.get_variable_scope(), reuse=reuse_variables): with tf.compat.v1.variable_scope('First_conv'): w1 = tf.compat.v1.get_variable('weights', [3, 3, 1, 32], tf.float32, initializer=tf.compat.v1.truncated_normal_initializer(stddev=0.1)) if regularzer: tf.add_to_collection('losses', regularzer(w1)) b1 = tf.compat.v1.get_variable('biases', [32], tf.float32, initializer=tf.compat.v1.constant_initializer(0.1)) activation1 = tf.nn.relu(tf.nn.conv2d(images, w1, strides=[1, 1, 1, 1], padding='SAME') + b1) out1 = tf.nn.max_pool2d(activation1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') with tf.compat.v1.variable_scope('Second_conv'): w2 = tf.compat.v1.get_variable('weight', [3, 3, 32, 64], tf.float32, initializer=tf.compat.v1.truncated_normal_initializer(stddev=0.1)) if regularzer: tf.add_to_collection('losses', regularzer(w2)) b2 = tf.compat.v1.get_variable('biases', [64], tf.float32, initializer=tf.compat.v1.constant_initializer(0.1)) activation2 = tf.nn.relu(tf.nn.conv2d(out1, w2, strides=[1, 1, 1, 1], padding='SAME') + b2) out2 = tf.nn.max_pool2d(activation2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') out3 = tf.reshape(out2, [-1, 7*7*64], name='flatten') with tf.compat.v1.variable_scope('FC_1'): w3 = tf.compat.v1.get_variable('weight', [7*7*64, 1024], tf.float32, initializer=tf.compat.v1.truncated_normal_initializer(stddev=0.1)) if regularzer: tf.add_to_collection('losses', regularzer(w3)) b3 = tf.compat.v1.get_variable('biases', [1024], tf.float32, initializer=tf.compat.v1.constant_initializer(0.1)) activation3 = tf.nn.relu(tf.matmul(out3, w3) + b3) out4 = tf.nn.dropout(activation3, keep_prob=rate) with tf.compat.v1.variable_scope('FC_2'): w4 = tf.compat.v1.get_variable('weight', [1024, 10], tf.float32, initializer=tf.compat.v1.truncated_normal_initializer(stddev=0.1)) if regularzer: tf.add_to_collection('losses', regularzer(w4)) b4 = tf.compat.v1.get_variable('biases', [10], tf.float32, initializer=tf.compat.v1.constant_initializer(0.1)) output = tf.nn.softmax(tf.matmul(out4, w4) + b4) with tf.compat.v1.variable_scope('Loss_entropy'): if regularzer: loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(labels, 1), logits=output)) \ + tf.add_n(tf.get_collection('losses')) else: loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(labels, 1), logits=output)) with tf.compat.v1.variable_scope('Accuracy'): correct_data = tf.equal(tf.math.argmax(labels, 1), tf.math.argmax(output, 1)) accuracy = tf.reduce_mean(tf.cast(correct_data, tf.float32, name='accuracy')) return output, loss, accuracy def average_gradients(tower_grads): average_grads = [] for grad_and_vars in zip(*tower_grads): grads = [] for g, v2 in grad_and_vars: expanded_g = tf.expand_dims(g, 0) grads.append(expanded_g) grad = tf.concat(grads, 0) grad = tf.reduce_mean(grad, 0) v = grad_and_vars[0][1] grad_and_var = (grad, v) average_grads.append(grad_and_var) return average_grads def main(argv=None): with tf.Graph().as_default(), tf.device('/cpu:0'): x, y = get_input(batch_size=BATCH_SIZE, path=TRAIN_PATH) regularizer = tf.contrib.layers.l2_regularizer(REGULARZTION_RATE) global_step = v1.get_variable('global_step', [], initializer=v1.constant_initializer(0), trainable=False) lr = v1.train.exponential_decay(LEARNING_RATE, global_step, 55000/BATCH_SIZE, LEARNING_RATE_DECAY) opt = v1.train.AdamOptimizer(lr) tower_grads = [] reuse_variables = False device = ['/gpu:0', '/cpu:0'] for i in range(len(device)): with tf.device(device[i]): with v1.name_scope(device[i][1:4] + '_0') as scope: out, cur_loss, acc = model_inference(x, y, 0.3, regularizer, reuse_variables) reuse_variables = True grads = opt.compute_gradients(cur_loss) tower_grads.append(grads) grads = average_gradients(tower_grads) for grad, var in grads: if grad is not None: v1.summary.histogram('gradients_on_average/%s' % var.op.name, grad) apply_gradient_op = opt.apply_gradients(grads, global_step) for var in v1.trainable_variables(): tf.summary.histogram(var.op.name, var) variable_averages = v1.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step) variable_to_average = (v1.trainable_variables() + v1.moving_average_variables()) variable_averages_op = variable_averages.apply(variable_to_average) train_op = tf.group(apply_gradient_op, variable_averages_op) saver = v1.train.Saver(max_to_keep=1) summary_op = v1.summary.merge_all() # merge_all 可以将所有summary全部保存到磁盘 init = v1.global_variables_initializer() with v1.Session(config=v1.ConfigProto(allow_soft_placement=True, log_device_placement=True)) as sess: init.run() summary_writer = v1.summary.FileWriter(MODEL_SAVE_PATH, sess.graph) # 指定一个文件用来保存图 for step in range(EPOCHS): try: start_time = time.time() _, loss_value, out_value, acc_value = sess.run([train_op, cur_loss, out, acc]) duration = time.time() - start_time if step != 0 and step % 100 == 0: num_examples_per_step = BATCH_SIZE * N_GPU examples_per_sec = num_examples_per_step / duration sec_per_batch = duration / N_GPU format_str = '%s: step %d, loss = %.2f(%.1f examples/sec; %.3f sec/batch), accuracy = %.2f' print(format_str % (datetime.now(), step, loss_value, examples_per_sec, sec_per_batch, acc_value)) summary = sess.run(summary_op) summary_writer.add_summary(summary, step) if step % 100 == 0 or (step + 1) == EPOCHS: checkpoint_path = os.path.join(MODEL_SAVE_PATH, MODEL_NAME) saver.save(sess, checkpoint_path, global_step=step) except tf.errors.OutOfRangeError: break if __name__ == '__main__': tf.app.run() ```

Tensorflow pb文件加载后还能继续训练吗?

Tensorflow 的pb 和ckpt文件加载恢复之后还能继续训练吗?

请问tensorflow保存模型后,为什么变量根据名称提取不了?

![图片说明](https://img-ask.csdn.net/upload/202004/22/1587517421_807638.png)![图片说明](https://img-ask.csdn.net/upload/202004/22/1587517434_623782.png) 已经用get_Variable 中的name了

opencv3.4 加载tensorflow模型 net.forward()总是报错?

OpenCV Error: Assertion failed (!_aspectRatios.empty(), _minSize > 0) in cv::dnn::PriorBoxLayerImpl::PriorBoxLayerImpl, file C:\build\master_winpack-build-win64-vc14\opencv\modules\dnn\src\layers\prior_box_layer.cpp, line 207 C:\build\master_winpack-build-win64-vc14\opencv\modules\dnn\src\layers\prior_box_layer.cpp:207: error: (-215) !_aspectRatios.empty(), _minSize > 0 in function cv::dnn::PriorBoxLayerImpl::PriorBoxLayerImpl

神经网络模型加载后测试效果不对

tensorflow框架训练好的神经网络模型,加载之后再去测试准确率特别低 图中是我的加载方法 麻烦大神帮忙指正,是不是网络加载出现问题 首先手动重新构建了模型:以下代码省略了权值、偏置和网络搭建 ``` # 构建模型 pred = alex_net(x, weights, biases, keep_prob) # 定义损失函数和优化器 cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,logits=pred))#softmax和交叉熵结合 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # 评估函数 correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # 3.训练模型和评估模型 # 初始化变量 init = tf.global_variables_initializer() saver = tf.train.Saver() with tf.Session() as sess: # 初始化变量 sess.run(init) saver.restore(sess, tf.train.latest_checkpoint(model_dir)) pred_test=sess.run(pred,{x:test_x, keep_prob:1.0}) result=sess.run(tf.argmax(pred_test, 1)) ```

Pycharm每次都要加载tensorflow

如题。我安装的是Win10+CUDA9.0+cuDNN9.0+tensorflow1.7+Pycharm tensorflow已经是通过pip安装了。在CMD界面写import tensorflow是没有问题的。 在Pycharm里面新建一个工程都要重新在setting->project interpreter加载tensorflow,很慢! 而且,我在Python安装路径下面,D:\Program Files (x86)\Python\Lib\site-packages,里面有tensorflow和tensorflow_gpu-1.7.0.dist-info两个文件夹。我需要的是GPU版的,这两个文件夹有什么区别呢?这里面都没有python.exe! 我在网上查到的不少都是用Anaconda的,直接在Pycharm里面把设置改为tensorflow里面的python.exe就行了。 请问我如果不装Anaconda有没有一劳永逸的让Pycharm自己加载的方法呢?还是说用Pycharm只能是用Anaconda最方便? 谢谢!

Tensorflow实现手写数字识别,使用训练模型进行预测时,为什么精确度远不如训练精确度??

用BP神经网络算法,基于Tensorflow训练了mnist数据集,在训练的python脚本中可以得到test上的精确度为96%,然后在另一个python脚本中,恢复出这个模型,输入手写数字的图片进行预测,100张图片识别的精确度只有70%多,请教各路大神帮忙解决一下,预测脚本的代码如下: ``` import sys import tensorflow as tf import os from PIL import Image, ImageFilter from pylab import * def predictint(imvalue): with tf.Graph().as_default(): def addlayer(input_data,insize,outsize,act_function=None): W=tf.Variable(tf.random_normal([insize,outsize])) b=tf.Variable(tf.zeros([outsize]))+0.1 out_data=tf.matmul(input_data,W)+b if act_function==None: return out_data elif act_function=="relu": return tf.nn.relu(out_data) elif act_function=="softmax": #result=tf.nn.softmax(out_data) return tf.nn.softmax(out_data) else: return tf.nn.sigmoid(out_data) x_input=tf.placeholder(tf.float32,[None,784]) #y_input=tf.placeholder(tf.float32,[None,10]) l1=addlayer(x_input,784,64,act_function="relu") l2=addlayer(l1,64,10,act_function="softmax") init_op = tf.initialize_all_variables() saver = tf.train.Saver() with tf.Session() as sess: sess.run(init_op) saver.restore(sess, "./model.ckpt") prediction=tf.argmax(l2,1) return prediction.eval(feed_dict={x_input: [imvalue]}, session=sess) def imageprepare(argv): im = Image.open(argv).convert('L') width = float(im.size[0]) height = float(im.size[1]) newImage = Image.new('L', (28, 28), (255)) #creates white canvas of 28x28 pixels if width > height: #check which dimension is bigger #Width is bigger. Width becomes 20 pixels. nheight = int(round((20.0/width*height),0)) #resize height according to ratio width if (nheigth == 0): #rare case but minimum is 1 pixel nheigth = 1 # resize and sharpen img = im.resize((20,nheight), Image.ANTIALIAS).filter(ImageFilter.SHARPEN) wtop = int(round(((28 - nheight)/2),0)) #caculate horizontal pozition newImage.paste(img, (4, wtop)) #paste resized image on white canvas else: #Height is bigger. Heigth becomes 20 pixels. nwidth = int(round((20.0/height*width),0)) #resize width according to ratio height if (nwidth == 0): #rare case but minimum is 1 pixel nwidth = 1 # resize and sharpen img = im.resize((nwidth,20), Image.ANTIALIAS).filter(ImageFilter.SHARPEN) wleft = int(round(((28 - nwidth)/2),0)) #caculate vertical pozition newImage.paste(img, (wleft, 4)) #paste resized image on white canvas newImage.show() tv = list(newImage.getdata()) #get pixel values #normalize pixels to 0 and 1. 0 is pure white, 1 is pure black. tva = [ (255-x)*1.0/255.0 for x in tv] return tva #print(tva) def main(argv): imvalue = imageprepare(argv) predint = predictint(imvalue) print (predint[0]) #first value in list f1 = open('/home/wch/MNIST_data/traindata_predict.txt','a') f1.writelines('%d ' % predint[0]) f1.close() def VisitDir(path): for root,dirs,files in os.walk(path): for filepath in files: print(os.path.join(root,filepath)) main(os.path.join(root,filepath)) if __name__ == "__main__": path = r"/home/wch/MNIST_data/data_convert2" VisitDir(path) ```

加载resnet网络 训练好PB模型加载的时候遇到如下错误? 如何解决? 求助

``` 2019-11-27 02:18:29 UTC [MainThread ] - /home/mind/app.py[line:121] - INFO: args: Namespace(model_name='serve', model_path='/home/mind/model/1', service_file='/home/mind/model/1/customize_service.py', tf_server_name='127.0.0.1') 2019-11-27 02:18:36.823910: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA Using TensorFlow backend. [2019-11-27 02:18:37 +0000] [68] [ERROR] Exception in worker process Traceback (most recent call last): File "/usr/local/lib/python3.6/site-packages/gunicorn/arbiter.py", line 583, in spawn_worker worker.init_process() File "/usr/local/lib/python3.6/site-packages/gunicorn/workers/base.py", line 129, in init_process self.load_wsgi() File "/usr/local/lib/python3.6/site-packages/gunicorn/workers/base.py", line 138, in load_wsgi self.wsgi = self.app.wsgi() File "/usr/local/lib/python3.6/site-packages/gunicorn/app/base.py", line 67, in wsgi self.callable = self.load() File "/usr/local/lib/python3.6/site-packages/gunicorn/app/wsgiapp.py", line 52, in load return self.load_wsgiapp() File "/usr/local/lib/python3.6/site-packages/gunicorn/app/wsgiapp.py", line 41, in load_wsgiapp return util.import_app(self.app_uri) File "/usr/local/lib/python3.6/site-packages/gunicorn/util.py", line 350, in import_app __import__(module) File "/home/mind/app.py", line 145, in model_service = class_defs[0](model_name, model_path) File "/home/mind/model/1/customize_service.py", line 39, in __init__ meta_graph_def = tf.saved_model.loader.load(self.sess, [tag_constants.SERVING], self.model_path) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/saved_model/loader_impl.py", line 219, in load saver = tf_saver.import_meta_graph(meta_graph_def_to_load, **saver_kwargs) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1955, in import_meta_graph **kwargs) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/meta_graph.py", line 743, in import_scoped_meta_graph producer_op_list=producer_op_list) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 432, in new_func return func(*args, **kwargs) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 460, in import_graph_def _RemoveDefaultAttrs(op_dict, producer_op_list, graph_def) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 227, in _RemoveDefaultAttrs op_def = op_dict[node.op] KeyError: 'DivNoNan' ```

大学四年自学走来,这些私藏的实用工具/学习网站我贡献出来了

大学四年,看课本是不可能一直看课本的了,对于学习,特别是自学,善于搜索网上的一些资源来辅助,还是非常有必要的,下面我就把这几年私藏的各种资源,网站贡献出来给你们。主要有:电子书搜索、实用工具、在线视频学习网站、非视频学习网站、软件下载、面试/求职必备网站。 注意:文中提到的所有资源,文末我都给你整理好了,你们只管拿去,如果觉得不错,转发、分享就是最大的支持了。 一、电子书搜索 对于大部分程序员...

在中国程序员是青春饭吗?

今年,我也32了 ,为了不给大家误导,咨询了猎头、圈内好友,以及年过35岁的几位老程序员……舍了老脸去揭人家伤疤……希望能给大家以帮助,记得帮我点赞哦。 目录: 你以为的人生 一次又一次的伤害 猎头界的真相 如何应对互联网行业的「中年危机」 一、你以为的人生 刚入行时,拿着傲人的工资,想着好好干,以为我们的人生是这样的: 等真到了那一天,你会发现,你的人生很可能是这样的: ...

程序员请照顾好自己,周末病魔差点一套带走我。

程序员在一个周末的时间,得了重病,差点当场去世,还好及时挽救回来了。

技术大佬:我去,你写的 switch 语句也太老土了吧

昨天早上通过远程的方式 review 了两名新来同事的代码,大部分代码都写得很漂亮,严谨的同时注释也很到位,这令我非常满意。但当我看到他们当中有一个人写的 switch 语句时,还是忍不住破口大骂:“我擦,小王,你丫写的 switch 语句也太老土了吧!” 来看看小王写的代码吧,看完不要骂我装逼啊。 private static String createPlayer(PlayerTypes p...

上班一个月,后悔当初着急入职的选择了

最近有个老铁,告诉我说,上班一个月,后悔当初着急入职现在公司了。他之前在美图做手机研发,今年美图那边今年也有一波组织优化调整,他是其中一个,在协商离职后,当时捉急找工作上班,因为有房贷供着,不能没有收入来源。所以匆忙选了一家公司,实际上是一个大型外包公司,主要派遣给其他手机厂商做外包项目。**当时承诺待遇还不错,所以就立马入职去上班了。但是后面入职后,发现薪酬待遇这块并不是HR所说那样,那个HR自...

女程序员,为什么比男程序员少???

昨天看到一档综艺节目,讨论了两个话题:(1)中国学生的数学成绩,平均下来看,会比国外好?为什么?(2)男生的数学成绩,平均下来看,会比女生好?为什么?同时,我又联想到了一个技术圈经常讨...

为什么本科以上学历的人只占中国人口的5%,但感觉遍地都是大学生?

中国大学生占总人口不到5% 2017年,中国整体的本科率仅有5.9%;如果算上研究生,这一比例可以进一步上升到6.5% 为什么在国家统计局推出的这份年鉴中,学历的最高一阶就是到研究生,而没有进一步再统计博士生的数量的。 原因其实并不难理解,相比全国和各省整体人口体量,博士生的占比非常之低,属于绝对意义上的小概率样本。 这一点,我们从上表中的各省研究生占比情况也可以看出端倪。除北京、天津、上海三...

副业收入是我做程序媛的3倍,工作外的B面人生是怎样的?

提到“程序员”,多数人脑海里首先想到的大约是:为人木讷、薪水超高、工作枯燥…… 然而,当离开工作岗位,撕去层层标签,脱下“程序员”这身外套,有的人生动又有趣,马上展现出了完全不同的A/B面人生! 不论是简单的爱好,还是正经的副业,他们都干得同样出色。偶尔,还能和程序员的特质结合,产生奇妙的“化学反应”。 @Charlotte:平日素颜示人,周末美妆博主 大家都以为程序媛也个个不修边幅,但我们也许...

MySQL数据库面试题(2020最新版)

文章目录数据库基础知识为什么要使用数据库什么是SQL?什么是MySQL?数据库三大范式是什么mysql有关权限的表都有哪几个MySQL的binlog有有几种录入格式?分别有什么区别?数据类型mysql有哪些数据类型引擎MySQL存储引擎MyISAM与InnoDB区别MyISAM索引与InnoDB索引的区别?InnoDB引擎的4大特性存储引擎选择索引什么是索引?索引有哪些优缺点?索引使用场景(重点)...

如果你是老板,你会不会踢了这样的员工?

有个好朋友ZS,是技术总监,昨天问我:“有一个老下属,跟了我很多年,做事勤勤恳恳,主动性也很好。但随着公司的发展,他的进步速度,跟不上团队的步伐了,有点...

我入职阿里后,才知道原来简历这么写

私下里,有不少读者问我:“二哥,如何才能写出一份专业的技术简历呢?我总感觉自己写的简历太烂了,所以投了无数份,都石沉大海了。”说实话,我自己好多年没有写过简历了,但我认识的一个同行,他在阿里,给我说了一些他当年写简历的方法论,我感觉太牛逼了,实在是忍不住,就分享了出来,希望能够帮助到你。 01、简历的本质 作为简历的撰写者,你必须要搞清楚一点,简历的本质是什么,它就是为了来销售你的价值主张的。往深...

程序员写出这样的代码,能不挨骂吗?

当你换槽填坑时,面对一个新的环境。能够快速熟练,上手实现业务需求是关键。但是,哪些因素会影响你快速上手呢?是原有代码写的不够好?还是注释写的不够好?昨夜...

外包程序员的幸福生活

今天给你们讲述一个外包程序员的幸福生活。男主是Z哥,不是在外包公司上班的那种,是一名自由职业者,接外包项目自己干。接下来讲的都是真人真事。 先给大家介绍一下男主,Z哥,老程序员,是我十多年前的老同事,技术大牛,当过CTO,也创过业。因为我俩都爱好喝酒、踢球,再加上住的距离不算远,所以一直也断断续续的联系着,我对Z哥的状况也有大概了解。 Z哥几年前创业失败,后来他开始干起了外包,利用自己的技术能...

带了6个月的徒弟当了面试官,而身为高级工程师的我天天修Bug......

即将毕业的应届毕业生一枚,现在只拿到了两家offer,但最近听到一些消息,其中一个offer,我这个组据说客户很少,很有可能整组被裁掉。 想问大家: 如果我刚入职这个组就被裁了怎么办呢? 大家都是什么时候知道自己要被裁了的? 面试软技能指导: BQ/Project/Resume 试听内容: 除了刷题,还有哪些技能是拿到offer不可或缺的要素 如何提升面试软实力:简历, 行为面试,沟通能...

优雅的替换if-else语句

场景 日常开发,if-else语句写的不少吧??当逻辑分支非常多的时候,if-else套了一层又一层,虽然业务功能倒是实现了,但是看起来是真的很不优雅,尤其是对于我这种有强迫症的程序"猿",看到这么多if-else,脑袋瓜子就嗡嗡的,总想着解锁新姿势:干掉过多的if-else!!!本文将介绍三板斧手段: 优先判断条件,条件不满足的,逻辑及时中断返回; 采用策略模式+工厂模式; 结合注解,锦...

离职半年了,老东家又发 offer,回不回?

有小伙伴问松哥这个问题,他在上海某公司,在离职了几个月后,前公司的领导联系到他,希望他能够返聘回去,他很纠结要不要回去? 俗话说好马不吃回头草,但是这个小伙伴既然感到纠结了,我觉得至少说明了两个问题:1.曾经的公司还不错;2.现在的日子也不是很如意。否则应该就不会纠结了。 老实说,松哥之前也有过类似的经历,今天就来和小伙伴们聊聊回头草到底吃不吃。 首先一个基本观点,就是离职了也没必要和老东家弄的苦...

记录下入职中软一个月(外包华为)

我在年前从上一家公司离职,没想到过年期间疫情爆发,我也被困在家里,在家呆着的日子让人很焦躁,于是我疯狂的投简历,看面试题,希望可以进大公司去看看。 我也有幸面试了我觉得还挺大的公司的(虽然不是bat之类的大厂,但是作为一名二本计算机专业刚毕业的大学生bat那些大厂我连投简历的勇气都没有),最后选择了中软,我知道这是一家外包公司,待遇各方面甚至不如我的上一家公司,但是对我而言这可是外包华为,能...

为什么程序员做外包会被瞧不起?

二哥,有个事想询问下您的意见,您觉得应届生值得去外包吗?公司虽然挺大的,中xx,但待遇感觉挺低,马上要报到,挺纠结的。

当HR压你价,说你只值7K,你该怎么回答?

当HR压你价,说你只值7K时,你可以流畅地回答,记住,是流畅,不能犹豫。 礼貌地说:“7K是吗?了解了。嗯~其实我对贵司的面试官印象很好。只不过,现在我的手头上已经有一份11K的offer。来面试,主要也是自己对贵司挺有兴趣的,所以过来看看……”(未完) 这段话主要是陪HR互诈的同时,从公司兴趣,公司职员印象上,都给予对方正面的肯定,既能提升HR的好感度,又能让谈判气氛融洽,为后面的发挥留足空间。...

面试:第十六章:Java中级开发

HashMap底层实现原理,红黑树,B+树,B树的结构原理 Spring的AOP和IOC是什么?它们常见的使用场景有哪些?Spring事务,事务的属性,传播行为,数据库隔离级别 Spring和SpringMVC,MyBatis以及SpringBoot的注解分别有哪些?SpringMVC的工作原理,SpringBoot框架的优点,MyBatis框架的优点 SpringCould组件有哪些,他们...

面试阿里p7,被按在地上摩擦,鬼知道我经历了什么?

面试阿里p7被问到的问题(当时我只知道第一个):@Conditional是做什么的?@Conditional多个条件是什么逻辑关系?条件判断在什么时候执...

Python爬虫,高清美图我全都要(彼岸桌面壁纸)

爬取彼岸桌面网站较为简单,用到了requests、lxml、Beautiful Soup4

无代码时代来临,程序员如何保住饭碗?

编程语言层出不穷,从最初的机器语言到如今2500种以上的高级语言,程序员们大呼“学到头秃”。程序员一边面临编程语言不断推陈出新,一边面临由于许多代码已存在,程序员编写新应用程序时存在重复“搬砖”的现象。 无代码/低代码编程应运而生。无代码/低代码是一种创建应用的方法,它可以让开发者使用最少的编码知识来快速开发应用程序。开发者通过图形界面中,可视化建模来组装和配置应用程序。这样一来,开发者直...

面试了一个 31 岁程序员,让我有所触动,30岁以上的程序员该何去何从?

最近面试了一个31岁8年经验的程序猿,让我有点感慨,大龄程序猿该何去何从。

6年开发经验女程序员,面试京东Java岗要求薪资28K

写在开头: 上周面试了一位女程序员,上午10::30来我们部门面试,2B哥接待了她.来看看她的简历: 个人简历 个人技能: ● 熟悉spring mvc 、spring、mybatis 等框架 ● 熟悉 redis 、rocketmq、dubbo、zookeeper、netty 、nginx、tomcat、mysql。 ● 阅读过juc 中的线程池、锁的源...

大三实习生,字节跳动面经分享,已拿Offer

说实话,自己的算法,我一个不会,太难了吧

程序员垃圾简历长什么样?

已经连续五年参加大厂校招、社招的技术面试工作,简历看的不下于万份 这篇文章会用实例告诉你,什么是差的程序员简历! 疫情快要结束了,各个公司也都开始春招了,作为即将红遍大江南北的新晋UP主,那当然要为小伙伴们做点事(手动狗头)。 就在公众号里公开征简历,义务帮大家看,并一一点评。《启舰:春招在即,义务帮大家看看简历吧》 一石激起千层浪,三天收到两百多封简历。 花光了两个星期的所有空闲时...

Java岗开发3年,公司临时抽查算法,离职后这几题我记一辈子

前几天我们公司做了一件蠢事,非常非常愚蠢的事情。我原以为从学校出来之后,除了找工作有测试外,不会有任何与考试有关的事儿。 但是,天有不测风云,公司技术总监、人事总监两位大佬突然降临到我们事业线,叫上我老大,给我们组织了一场别开生面的“考试”。 那是一个风和日丽的下午,我翘着二郎腿,左手端着一杯卡布奇诺,右手抓着我的罗技鼠标,滚动着轮轴,穿梭在头条热点之间。 “淡黄的长裙~蓬松的头发...

大牛都会用的IDEA调试技巧!!!

导读 前天面试了一个985高校的实习生,问了他平时用什么开发工具,他想也没想的说IDEA,于是我抛砖引玉的问了一下IDEA的调试用过吧,你说说怎么设置断点...

都前后端分离了,咱就别做页面跳转了!统统 JSON 交互

文章目录1. 无状态登录1.1 什么是有状态1.2 什么是无状态1.3 如何实现无状态1.4 各自优缺点2. 登录交互2.1 前后端分离的数据交互2.2 登录成功2.3 登录失败3. 未认证处理方案4. 注销登录 这是本系列的第四篇,有小伙伴找不到之前文章,松哥给大家列一个索引出来: 挖一个大坑,Spring Security 开搞! 松哥手把手带你入门 Spring Security,别再问密...

立即提问
相关内容推荐