虐猫人薛定谔
虐猫人薛定谔

使用TensorFlow对电影评论进行文本分类

文章目录

    • 数据来源
    • 数据处理
    • 数据下载
    • 模型的构建
    • 模型的编译与训练
    • 模型的评估
    • 完整代码
    • 最终结果

数据来源

本次使用的数据来源于网络电影数据库的IMDB数据集，其中包含50,000条影评文本。

数据处理

从该数据集切割出的25,000条评论用作训练，另外25,000条用作测试。训练集与测试集是平衡的，意味着它们包含相等数量的积极和消极评论。

数据下载

使用TensorFlow对电影评论进行文本分类_第1张图片

模型的构建

使用TensorFlow对电影评论进行文本分类_第2张图片

模型的编译与训练

使用TensorFlow对电影评论进行文本分类_第3张图片

模型的评估

使用TensorFlow对电影评论进行文本分类_第4张图片

完整代码

# ！/usr/bin/env python
# —*— coding: utf-8 —*—
# @Time:    2020/1/2 7:42
# @Author:  Martin
# @File:    Film_Reviews_Classification.py
# @Software:PyCharm

from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_datasets as tfds
import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = '3'
# 下载IMDB数据集
train_validation_split = tfds.Split.TRAIN.subsplit([6, 4])
(train_data, validation_data), test_data = tfds.load(
    name="imdb_reviews",
    split=(train_validation_split, tfds.Split.TEST),
    as_supervised=True
)
# 构建模型
embedding = "https://hub.tensorflow.google.cn/google/tf2-preview/gnews-swivel-20dim/1"
hub_layer = hub.KerasLayer(embedding, input_shape=[], dtype=tf.string, trainable=True)
model = tf.keras.Sequential()
model.add(hub_layer)
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))
# 编译模型
model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])
# 训练模型
history = model.fit(train_data.shuffle(10000).batch(512),
                    epochs=20,
                    validation_data=validation_data.batch(512),
                    verbose=1)
# 评估模型
results = model.evaluate(test_data.batch(512), verbose=2)
for name, value in zip(model.metrics_names, results):
    print("%s: %.3f" % (name, value))

最终结果

Epoch 1/20

      1/Unknown - 1s 1s/step - loss: 0.8219 - accuracy: 0.4609
      2/Unknown - 2s 782ms/step - loss: 0.8012 - accuracy: 0.4756
      3/Unknown - 2s 563ms/step - loss: 0.7966 - accuracy: 0.4818
      4/Unknown - 2s 450ms/step - loss: 0.7910 - accuracy: 0.4800
      5/Unknown - 2s 381ms/step - loss: 0.7840 - accuracy: 0.4828
      6/Unknown - 2s 334ms/step - loss: 0.7851 - accuracy: 0.4801
      7/Unknown - 2s 299ms/step - loss: 0.7776 - accuracy: 0.4886
      8/Unknown - 2s 274ms/step - loss: 0.7712 - accuracy: 0.4944
      9/Unknown - 2s 255ms/step - loss: 0.7656 - accuracy: 0.4998
     10/Unknown - 2s 240ms/step - loss: 0.7622 - accuracy: 0.5033
     11/Unknown - 2s 227ms/step - loss: 0.7624 - accuracy: 0.5025
     12/Unknown - 3s 215ms/step - loss: 0.7596 - accuracy: 0.5065
     13/Unknown - 3s 206ms/step - loss: 0.7586 - accuracy: 0.5066
     14/Unknown - 3s 197ms/step - loss: 0.7569 - accuracy: 0.5070
     15/Unknown - 3s 190ms/step - loss: 0.7537 - accuracy: 0.5096
     16/Unknown - 3s 184ms/step - loss: 0.7504 - accuracy: 0.5125
     17/Unknown - 3s 178ms/step - loss: 0.7484 - accuracy: 0.5149
     18/Unknown - 3s 174ms/step - loss: 0.7449 - accuracy: 0.5193
     19/Unknown - 3s 170ms/step - loss: 0.7421 - accuracy: 0.5225
     20/Unknown - 3s 166ms/step - loss: 0.7401 - accuracy: 0.5238
     21/Unknown - 3s 162ms/step - loss: 0.7382 - accuracy: 0.5252
     22/Unknown - 3s 159ms/step - loss: 0.7366 - accuracy: 0.5264
     23/Unknown - 4s 156ms/step - loss: 0.7347 - accuracy: 0.5284
     24/Unknown - 4s 153ms/step - loss: 0.7327 - accuracy: 0.5303
     25/Unknown - 4s 151ms/step - loss: 0.7312 - accuracy: 0.5304
     26/Unknown - 4s 149ms/step - loss: 0.7290 - accuracy: 0.5322
     27/Unknown - 4s 147ms/step - loss: 0.7269 - accuracy: 0.5348
     28/Unknown - 4s 144ms/step - loss: 0.7255 - accuracy: 0.5363
     29/Unknown - 4s 142ms/step - loss: 0.7242 - accuracy: 0.5369
     30/Unknown - 4s 139ms/step - loss: 0.7231 - accuracy: 0.5374
30/30 [==============================] - 6s 207ms/step - loss: 0.7231 - accuracy: 0.5374 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 2/20

 1/20 [>.............................] - ETA: 12s - loss: 0.6648 - accuracy: 0.6133
 2/20 [==>...........................] - ETA: 6s - loss: 0.6550 - accuracy: 0.6230 
 3/20 [===>..........................] - ETA: 4s - loss: 0.6492 - accuracy: 0.6243
 4/20 [=====>........................] - ETA: 4s - loss: 0.6570 - accuracy: 0.6211
 5/20 [======>.......................] - ETA: 3s - loss: 0.6621 - accuracy: 0.6133
 6/20 [========>.....................] - ETA: 2s - loss: 0.6596 - accuracy: 0.6159
 7/20 [=========>....................] - ETA: 2s - loss: 0.6600 - accuracy: 0.6158
 8/20 [===========>..................] - ETA: 2s - loss: 0.6589 - accuracy: 0.6187
 9/20 [============>.................] - ETA: 1s - loss: 0.6568 - accuracy: 0.6237
10/20 [==============>...............] - ETA: 1s - loss: 0.6567 - accuracy: 0.6244
11/20 [===============>..............] - ETA: 1s - loss: 0.6574 - accuracy: 0.6223
12/20 [=================>............] - ETA: 1s - loss: 0.6539 - accuracy: 0.6265
13/20 [==================>...........] - ETA: 1s - loss: 0.6535 - accuracy: 0.6259
14/20 [====================>.........] - ETA: 0s - loss: 0.6540 - accuracy: 0.6253
15/20 [=====================>........] - ETA: 0s - loss: 0.6531 - accuracy: 0.6254
16/20 [=======================>......] - ETA: 0s - loss: 0.6520 - accuracy: 0.6263
17/20 [========================>.....] - ETA: 0s - loss: 0.6516 - accuracy: 0.6252
18/20 [==========================>...] - ETA: 0s - loss: 0.6519 - accuracy: 0.6253
19/20 [===========================>..] - ETA: 0s - loss: 0.6504 - accuracy: 0.6278
30/30 [==============================] - 5s 173ms/step - loss: 0.6466 - accuracy: 0.6398 - val_loss: 0.6144 - val_accuracy: 0.6696
Epoch 3/20

 1/20 [>.............................] - ETA: 12s - loss: 0.6175 - accuracy: 0.6602
 2/20 [==>...........................] - ETA: 6s - loss: 0.6040 - accuracy: 0.6826 
 3/20 [===>..........................] - ETA: 5s - loss: 0.6080 - accuracy: 0.6823
 4/20 [=====>........................] - ETA: 3s - loss: 0.5987 - accuracy: 0.6914
 5/20 [======>.......................] - ETA: 3s - loss: 0.5974 - accuracy: 0.6922
 6/20 [========>.....................] - ETA: 2s - loss: 0.5993 - accuracy: 0.6872
 7/20 [=========>....................] - ETA: 2s - loss: 0.5989 - accuracy: 0.6881
 8/20 [===========>..................] - ETA: 2s - loss: 0.6000 - accuracy: 0.6890
 9/20 [============>.................] - ETA: 1s - loss: 0.5987 - accuracy: 0.6866
10/20 [==============>...............] - ETA: 1s - loss: 0.5985 - accuracy: 0.6867
11/20 [===============>..............] - ETA: 1s - loss: 0.5995 - accuracy: 0.6848
12/20 [=================>............] - ETA: 1s - loss: 0.5986 - accuracy: 0.6857
13/20 [==================>...........] - ETA: 0s - loss: 0.5981 - accuracy: 0.6870
14/20 [====================>.........] - ETA: 0s - loss: 0.5998 - accuracy: 0.6871
15/20 [=====================>........] - ETA: 0s - loss: 0.5991 - accuracy: 0.6880
16/20 [=======================>......] - ETA: 0s - loss: 0.5985 - accuracy: 0.6890
17/20 [========================>.....] - ETA: 0s - loss: 0.5982 - accuracy: 0.6898
18/20 [==========================>...] - ETA: 0s - loss: 0.5972 - accuracy: 0.6900
19/20 [===========================>..] - ETA: 0s - loss: 0.5948 - accuracy: 0.6926
30/30 [==============================] - 5s 171ms/step - loss: 0.5923 - accuracy: 0.6983 - val_loss: 0.5705 - val_accuracy: 0.7160
Epoch 4/20

 1/20 [>.............................] - ETA: 13s - loss: 0.5646 - accuracy: 0.7031
 2/20 [==>...........................] - ETA: 7s - loss: 0.5533 - accuracy: 0.7158 
 3/20 [===>..........................] - ETA: 5s - loss: 0.5497 - accuracy: 0.7240
 4/20 [=====>........................] - ETA: 4s - loss: 0.5535 - accuracy: 0.7168
 5/20 [======>.......................] - ETA: 3s - loss: 0.5614 - accuracy: 0.7094
 6/20 [========>.....................] - ETA: 3s - loss: 0.5617 - accuracy: 0.7113
 7/20 [=========>....................] - ETA: 2s - loss: 0.5603 - accuracy: 0.7132
 8/20 [===========>..................] - ETA: 2s - loss: 0.5576 - accuracy: 0.7161
 9/20 [============>.................] - ETA: 2s - loss: 0.5545 - accuracy: 0.7216
10/20 [==============>...............] - ETA: 1s - loss: 0.5570 - accuracy: 0.7209
11/20 [===============>..............] - ETA: 1s - loss: 0.5560 - accuracy: 0.7227
12/20 [=================>............] - ETA: 1s - loss: 0.5540 - accuracy: 0.7251
13/20 [==================>...........] - ETA: 1s - loss: 0.5549 - accuracy: 0.7258
14/20 [====================>.........] - ETA: 0s - loss: 0.5525 - accuracy: 0.7288
15/20 [=====================>........] - ETA: 0s - loss: 0.5504 - accuracy: 0.7314
16/20 [=======================>......] - ETA: 0s - loss: 0.5510 - accuracy: 0.7311
17/20 [========================>.....] - ETA: 0s - loss: 0.5492 - accuracy: 0.7333
18/20 [==========================>...] - ETA: 0s - loss: 0.5483 - accuracy: 0.7340
19/20 [===========================>..] - ETA: 0s - loss: 0.5470 - accuracy: 0.7366
30/30 [==============================] - 6s 200ms/step - loss: 0.5450 - accuracy: 0.7421 - val_loss: 0.5294 - val_accuracy: 0.7485
Epoch 5/20

 1/20 [>.............................] - ETA: 15s - loss: 0.5316 - accuracy: 0.7480
 2/20 [==>...........................] - ETA: 8s - loss: 0.5228 - accuracy: 0.7588 
 3/20 [===>..........................] - ETA: 6s - loss: 0.5195 - accuracy: 0.7572
 4/20 [=====>........................] - ETA: 4s - loss: 0.5217 - accuracy: 0.7515
 5/20 [======>.......................] - ETA: 4s - loss: 0.5153 - accuracy: 0.7598
 6/20 [========>.....................] - ETA: 3s - loss: 0.5170 - accuracy: 0.7552
 7/20 [=========>....................] - ETA: 2s - loss: 0.5178 - accuracy: 0.7567
 8/20 [===========>..................] - ETA: 2s - loss: 0.5125 - accuracy: 0.7603
 9/20 [============>.................] - ETA: 2s - loss: 0.5108 - accuracy: 0.7628
10/20 [==============>...............] - ETA: 1s - loss: 0.5105 - accuracy: 0.7627
11/20 [===============>..............] - ETA: 1s - loss: 0.5089 - accuracy: 0.7630
12/20 [=================>............] - ETA: 1s - loss: 0.5065 - accuracy: 0.7660
13/20 [==================>...........] - ETA: 1s - loss: 0.5063 - accuracy: 0.7670
14/20 [====================>.........] - ETA: 1s - loss: 0.5075 - accuracy: 0.7662
15/20 [=====================>........] - ETA: 0s - loss: 0.5076 - accuracy: 0.7669
16/20 [=======================>......] - ETA: 0s - loss: 0.5064 - accuracy: 0.7683
17/20 [========================>.....] - ETA: 0s - loss: 0.5059 - accuracy: 0.7687
18/20 [==========================>...] - ETA: 0s - loss: 0.5062 - accuracy: 0.7688
19/20 [===========================>..] - ETA: 0s - loss: 0.5057 - accuracy: 0.7701
30/30 [==============================] - 6s 203ms/step - loss: 0.5024 - accuracy: 0.7791 - val_loss: 0.4901 - val_accuracy: 0.7749
Epoch 6/20

 1/20 [>.............................] - ETA: 15s - loss: 0.4646 - accuracy: 0.8047
 2/20 [==>...........................] - ETA: 8s - loss: 0.4698 - accuracy: 0.8037 
 3/20 [===>..........................] - ETA: 5s - loss: 0.4678 - accuracy: 0.8073
 4/20 [=====>........................] - ETA: 4s - loss: 0.4634 - accuracy: 0.8105
 5/20 [======>.......................] - ETA: 4s - loss: 0.4670 - accuracy: 0.8051
 6/20 [========>.....................] - ETA: 3s - loss: 0.4673 - accuracy: 0.8031
 7/20 [=========>....................] - ETA: 2s - loss: 0.4622 - accuracy: 0.8041
 8/20 [===========>..................] - ETA: 2s - loss: 0.4659 - accuracy: 0.7981
 9/20 [============>.................] - ETA: 2s - loss: 0.4643 - accuracy: 0.7993
10/20 [==============>...............] - ETA: 1s - loss: 0.4649 - accuracy: 0.8010
11/20 [===============>..............] - ETA: 1s - loss: 0.4656 - accuracy: 0.8008
12/20 [=================>............] - ETA: 1s - loss: 0.4649 - accuracy: 0.8016
13/20 [==================>...........] - ETA: 1s - loss: 0.4630 - accuracy: 0.8026
14/20 [====================>.........] - ETA: 1s - loss: 0.4635 - accuracy: 0.8022
15/20 [=====================>........] - ETA: 0s - loss: 0.4632 - accuracy: 0.8016
16/20 [=======================>......] - ETA: 0s - loss: 0.4617 - accuracy: 0.8038
17/20 [========================>.....] - ETA: 0s - loss: 0.4607 - accuracy: 0.8037
18/20 [==========================>...] - ETA: 0s - loss: 0.4590 - accuracy: 0.8051
19/20 [===========================>..] - ETA: 0s - loss: 0.4603 - accuracy: 0.8041
30/30 [==============================] - 6s 199ms/step - loss: 0.4571 - accuracy: 0.8093 - val_loss: 0.4511 - val_accuracy: 0.7988
Epoch 7/20

 1/20 [>.............................] - ETA: 14s - loss: 0.4428 - accuracy: 0.8164
 2/20 [==>...........................] - ETA: 8s - loss: 0.4384 - accuracy: 0.8281 
 3/20 [===>..........................] - ETA: 6s - loss: 0.4481 - accuracy: 0.8125
 4/20 [=====>........................] - ETA: 4s - loss: 0.4415 - accuracy: 0.8169
 5/20 [======>.......................] - ETA: 4s - loss: 0.4384 - accuracy: 0.8164
 6/20 [========>.....................] - ETA: 3s - loss: 0.4372 - accuracy: 0.8164
 7/20 [=========>....................] - ETA: 2s - loss: 0.4333 - accuracy: 0.8172
 8/20 [===========>..................] - ETA: 2s - loss: 0.4311 - accuracy: 0.8193
 9/20 [============>.................] - ETA: 2s - loss: 0.4309 - accuracy: 0.8181
10/20 [==============>...............] - ETA: 1s - loss: 0.4285 - accuracy: 0.8215
11/20 [===============>..............] - ETA: 1s - loss: 0.4265 - accuracy: 0.8233
12/20 [=================>............] - ETA: 1s - loss: 0.4278 - accuracy: 0.8223
13/20 [==================>...........] - ETA: 1s - loss: 0.4277 - accuracy: 0.8209
14/20 [====================>.........] - ETA: 1s - loss: 0.4268 - accuracy: 0.8220
15/20 [=====================>........] - ETA: 0s - loss: 0.4249 - accuracy: 0.8225
16/20 [=======================>......] - ETA: 0s - loss: 0.4257 - accuracy: 0.8213
17/20 [========================>.....] - ETA: 0s - loss: 0.4243 - accuracy: 0.8218
18/20 [==========================>...] - ETA: 0s - loss: 0.4229 - accuracy: 0.8230
19/20 [===========================>..] - ETA: 0s - loss: 0.4215 - accuracy: 0.8240
30/30 [==============================] - 6s 202ms/step - loss: 0.4168 - accuracy: 0.8331 - val_loss: 0.4177 - val_accuracy: 0.8153
Epoch 8/20

 1/20 [>.............................] - ETA: 15s - loss: 0.3927 - accuracy: 0.8301
 2/20 [==>...........................] - ETA: 8s - loss: 0.3845 - accuracy: 0.8408 
 3/20 [===>..........................] - ETA: 6s - loss: 0.3938 - accuracy: 0.8353
 4/20 [=====>........................] - ETA: 4s - loss: 0.3910 - accuracy: 0.8403
 5/20 [======>.......................] - ETA: 4s - loss: 0.3894 - accuracy: 0.8422
 6/20 [========>.....................] - ETA: 3s - loss: 0.3856 - accuracy: 0.8424
 7/20 [=========>....................] - ETA: 2s - loss: 0.3878 - accuracy: 0.8418
 8/20 [===========>..................] - ETA: 2s - loss: 0.3879 - accuracy: 0.8403
 9/20 [============>.................] - ETA: 2s - loss: 0.3848 - accuracy: 0.8418
10/20 [==============>...............] - ETA: 1s - loss: 0.3860 - accuracy: 0.8418
11/20 [===============>..............] - ETA: 1s - loss: 0.3863 - accuracy: 0.8436
12/20 [=================>............] - ETA: 1s - loss: 0.3855 - accuracy: 0.8438
13/20 [==================>...........] - ETA: 1s - loss: 0.3837 - accuracy: 0.8444
14/20 [====================>.........] - ETA: 1s - loss: 0.3828 - accuracy: 0.8453
15/20 [=====================>........] - ETA: 0s - loss: 0.3827 - accuracy: 0.8454
16/20 [=======================>......] - ETA: 0s - loss: 0.3807 - accuracy: 0.8466
17/20 [========================>.....] - ETA: 0s - loss: 0.3814 - accuracy: 0.8471
18/20 [==========================>...] - ETA: 0s - loss: 0.3782 - accuracy: 0.8492
19/20 [===========================>..] - ETA: 0s - loss: 0.3763 - accuracy: 0.8503
30/30 [==============================] - 6s 202ms/step - loss: 0.3743 - accuracy: 0.8511 - val_loss: 0.3922 - val_accuracy: 0.8263
Epoch 9/20

 1/20 [>.............................] - ETA: 14s - loss: 0.3511 - accuracy: 0.8691
 2/20 [==>...........................] - ETA: 8s - loss: 0.3323 - accuracy: 0.8877 
 3/20 [===>..........................] - ETA: 5s - loss: 0.3369 - accuracy: 0.8724
 4/20 [=====>........................] - ETA: 4s - loss: 0.3332 - accuracy: 0.8760
 5/20 [======>.......................] - ETA: 3s - loss: 0.3403 - accuracy: 0.8676
 6/20 [========>.....................] - ETA: 3s - loss: 0.3397 - accuracy: 0.8688
 7/20 [=========>....................] - ETA: 2s - loss: 0.3422 - accuracy: 0.8669
 8/20 [===========>..................] - ETA: 2s - loss: 0.3463 - accuracy: 0.8650
 9/20 [============>.................] - ETA: 2s - loss: 0.3444 - accuracy: 0.8661
10/20 [==============>...............] - ETA: 1s - loss: 0.3417 - accuracy: 0.8682
11/20 [===============>..............] - ETA: 1s - loss: 0.3413 - accuracy: 0.8677
12/20 [=================>............] - ETA: 1s - loss: 0.3424 - accuracy: 0.8670
13/20 [==================>...........] - ETA: 1s - loss: 0.3441 - accuracy: 0.8657
14/20 [====================>.........] - ETA: 0s - loss: 0.3412 - accuracy: 0.8668
15/20 [=====================>........] - ETA: 0s - loss: 0.3381 - accuracy: 0.8686
16/20 [=======================>......] - ETA: 0s - loss: 0.3397 - accuracy: 0.8676
17/20 [========================>.....] - ETA: 0s - loss: 0.3402 - accuracy: 0.8665
18/20 [==========================>...] - ETA: 0s - loss: 0.3390 - accuracy: 0.8666
19/20 [===========================>..] - ETA: 0s - loss: 0.3398 - accuracy: 0.8653
30/30 [==============================] - 6s 202ms/step - loss: 0.3388 - accuracy: 0.8661 - val_loss: 0.3671 - val_accuracy: 0.8379
Epoch 10/20

 1/20 [>.............................] - ETA: 15s - loss: 0.3103 - accuracy: 0.8809
 2/20 [==>...........................] - ETA: 8s - loss: 0.3342 - accuracy: 0.8711 
 3/20 [===>..........................] - ETA: 5s - loss: 0.3351 - accuracy: 0.8698
 4/20 [=====>........................] - ETA: 4s - loss: 0.3290 - accuracy: 0.8716
 5/20 [======>.......................] - ETA: 3s - loss: 0.3307 - accuracy: 0.8691
 6/20 [========>.....................] - ETA: 3s - loss: 0.3304 - accuracy: 0.8672
 7/20 [=========>....................] - ETA: 2s - loss: 0.3229 - accuracy: 0.8722
 8/20 [===========>..................] - ETA: 2s - loss: 0.3199 - accuracy: 0.8728
 9/20 [============>.................] - ETA: 2s - loss: 0.3155 - accuracy: 0.8737
10/20 [==============>...............] - ETA: 1s - loss: 0.3154 - accuracy: 0.8740
11/20 [===============>..............] - ETA: 1s - loss: 0.3135 - accuracy: 0.8750
12/20 [=================>............] - ETA: 1s - loss: 0.3120 - accuracy: 0.8750
13/20 [==================>...........] - ETA: 1s - loss: 0.3104 - accuracy: 0.8776
14/20 [====================>.........] - ETA: 0s - loss: 0.3106 - accuracy: 0.8779
15/20 [=====================>........] - ETA: 0s - loss: 0.3132 - accuracy: 0.8760
16/20 [=======================>......] - ETA: 0s - loss: 0.3136 - accuracy: 0.8766
17/20 [========================>.....] - ETA: 0s - loss: 0.3132 - accuracy: 0.8767
18/20 [==========================>...] - ETA: 0s - loss: 0.3136 - accuracy: 0.8772
19/20 [===========================>..] - ETA: 0s - loss: 0.3123 - accuracy: 0.8777
30/30 [==============================] - 6s 200ms/step - loss: 0.3105 - accuracy: 0.8806 - val_loss: 0.3484 - val_accuracy: 0.8493
Epoch 11/20

 1/20 [>.............................] - ETA: 14s - loss: 0.3195 - accuracy: 0.8672
 2/20 [==>...........................] - ETA: 8s - loss: 0.3088 - accuracy: 0.8789 
 3/20 [===>..........................] - ETA: 5s - loss: 0.2946 - accuracy: 0.8867
 4/20 [=====>........................] - ETA: 4s - loss: 0.3012 - accuracy: 0.8828
 5/20 [======>.......................] - ETA: 3s - loss: 0.3031 - accuracy: 0.8805
 6/20 [========>.....................] - ETA: 3s - loss: 0.3042 - accuracy: 0.8773
 7/20 [=========>....................] - ETA: 2s - loss: 0.3009 - accuracy: 0.8811
 8/20 [===========>..................] - ETA: 2s - loss: 0.2974 - accuracy: 0.8831
 9/20 [============>.................] - ETA: 2s - loss: 0.2970 - accuracy: 0.8822
10/20 [==============>...............] - ETA: 1s - loss: 0.2963 - accuracy: 0.8824
11/20 [===============>..............] - ETA: 1s - loss: 0.2950 - accuracy: 0.8817
12/20 [=================>............] - ETA: 1s - loss: 0.2919 - accuracy: 0.8844
13/20 [==================>...........] - ETA: 1s - loss: 0.2911 - accuracy: 0.8860
14/20 [====================>.........] - ETA: 1s - loss: 0.2910 - accuracy: 0.8859
15/20 [=====================>........] - ETA: 0s - loss: 0.2908 - accuracy: 0.8859
16/20 [=======================>......] - ETA: 0s - loss: 0.2906 - accuracy: 0.8861
17/20 [========================>.....] - ETA: 0s - loss: 0.2907 - accuracy: 0.8860
18/20 [==========================>...] - ETA: 0s - loss: 0.2902 - accuracy: 0.8870
19/20 [===========================>..] - ETA: 0s - loss: 0.2910 - accuracy: 0.8862
30/30 [==============================] - 6s 202ms/step - loss: 0.2881 - accuracy: 0.8898 - val_loss: 0.3353 - val_accuracy: 0.8557
Epoch 12/20

 1/20 [>.............................] - ETA: 14s - loss: 0.2690 - accuracy: 0.9004
 2/20 [==>...........................] - ETA: 8s - loss: 0.2556 - accuracy: 0.9072 
 3/20 [===>..........................] - ETA: 5s - loss: 0.2513 - accuracy: 0.9036
 4/20 [=====>........................] - ETA: 4s - loss: 0.2599 - accuracy: 0.9014
 5/20 [======>.......................] - ETA: 3s - loss: 0.2614 - accuracy: 0.9000
 6/20 [========>.....................] - ETA: 3s - loss: 0.2639 - accuracy: 0.8968
 7/20 [=========>....................] - ETA: 2s - loss: 0.2648 - accuracy: 0.8962
 8/20 [===========>..................] - ETA: 2s - loss: 0.2618 - accuracy: 0.8984
 9/20 [============>.................] - ETA: 2s - loss: 0.2656 - accuracy: 0.8950
10/20 [==============>...............] - ETA: 1s - loss: 0.2654 - accuracy: 0.8959
11/20 [===============>..............] - ETA: 1s - loss: 0.2670 - accuracy: 0.8951
12/20 [=================>............] - ETA: 1s - loss: 0.2659 - accuracy: 0.8955
13/20 [==================>...........] - ETA: 1s - loss: 0.2657 - accuracy: 0.8959
14/20 [====================>.........] - ETA: 0s - loss: 0.2658 - accuracy: 0.8959
15/20 [=====================>........] - ETA: 0s - loss: 0.2656 - accuracy: 0.8956
16/20 [=======================>......] - ETA: 0s - loss: 0.2653 - accuracy: 0.8969
17/20 [========================>.....] - ETA: 0s - loss: 0.2655 - accuracy: 0.8975
18/20 [==========================>...] - ETA: 0s - loss: 0.2638 - accuracy: 0.8981
19/20 [===========================>..] - ETA: 0s - loss: 0.2628 - accuracy: 0.8985
30/30 [==============================] - 6s 201ms/step - loss: 0.2625 - accuracy: 0.9001 - val_loss: 0.3233 - val_accuracy: 0.8612
Epoch 13/20

 1/20 [>.............................] - ETA: 14s - loss: 0.2426 - accuracy: 0.9160
 2/20 [==>...........................] - ETA: 8s - loss: 0.2490 - accuracy: 0.9053 
 3/20 [===>..........................] - ETA: 5s - loss: 0.2469 - accuracy: 0.9121
 4/20 [=====>........................] - ETA: 4s - loss: 0.2489 - accuracy: 0.9087
 5/20 [======>.......................] - ETA: 3s - loss: 0.2440 - accuracy: 0.9102
 6/20 [========>.....................] - ETA: 3s - loss: 0.2423 - accuracy: 0.9121
 7/20 [=========>....................] - ETA: 2s - loss: 0.2419 - accuracy: 0.9116
 8/20 [===========>..................] - ETA: 2s - loss: 0.2384 - accuracy: 0.9131
 9/20 [============>.................] - ETA: 2s - loss: 0.2403 - accuracy: 0.9130
10/20 [==============>...............] - ETA: 1s - loss: 0.2404 - accuracy: 0.9125
11/20 [===============>..............] - ETA: 1s - loss: 0.2406 - accuracy: 0.9121
12/20 [=================>............] - ETA: 1s - loss: 0.2422 - accuracy: 0.9115
13/20 [==================>...........] - ETA: 1s - loss: 0.2414 - accuracy: 0.9117
14/20 [====================>.........] - ETA: 0s - loss: 0.2401 - accuracy: 0.9117
15/20 [=====================>........] - ETA: 0s - loss: 0.2406 - accuracy: 0.9118
16/20 [=======================>......] - ETA: 0s - loss: 0.2412 - accuracy: 0.9119
17/20 [========================>.....] - ETA: 0s - loss: 0.2426 - accuracy: 0.9110
18/20 [==========================>...] - ETA: 0s - loss: 0.2414 - accuracy: 0.9117
19/20 [===========================>..] - ETA: 0s - loss: 0.2402 - accuracy: 0.9120
30/30 [==============================] - 6s 202ms/step - loss: 0.2409 - accuracy: 0.9108 - val_loss: 0.3147 - val_accuracy: 0.8647
Epoch 14/20

 1/20 [>.............................] - ETA: 15s - loss: 0.2293 - accuracy: 0.9102
 2/20 [==>...........................] - ETA: 8s - loss: 0.2436 - accuracy: 0.9102 
 3/20 [===>..........................] - ETA: 6s - loss: 0.2299 - accuracy: 0.9180
 4/20 [=====>........................] - ETA: 4s - loss: 0.2242 - accuracy: 0.9224
 5/20 [======>.......................] - ETA: 3s - loss: 0.2265 - accuracy: 0.9211
 6/20 [========>.....................] - ETA: 3s - loss: 0.2301 - accuracy: 0.9196
 7/20 [=========>....................] - ETA: 2s - loss: 0.2285 - accuracy: 0.9196
 8/20 [===========>..................] - ETA: 2s - loss: 0.2312 - accuracy: 0.9172
 9/20 [============>.................] - ETA: 2s - loss: 0.2309 - accuracy: 0.9173
10/20 [==============>...............] - ETA: 1s - loss: 0.2306 - accuracy: 0.9166
11/20 [===============>..............] - ETA: 1s - loss: 0.2305 - accuracy: 0.9165
12/20 [=================>............] - ETA: 1s - loss: 0.2298 - accuracy: 0.9163
13/20 [==================>...........] - ETA: 1s - loss: 0.2299 - accuracy: 0.9163
14/20 [====================>.........] - ETA: 0s - loss: 0.2271 - accuracy: 0.9185
15/20 [=====================>........] - ETA: 0s - loss: 0.2269 - accuracy: 0.9191
16/20 [=======================>......] - ETA: 0s - loss: 0.2270 - accuracy: 0.9185
17/20 [========================>.....] - ETA: 0s - loss: 0.2247 - accuracy: 0.9200
18/20 [==========================>...] - ETA: 0s - loss: 0.2255 - accuracy: 0.9191
19/20 [===========================>..] - ETA: 0s - loss: 0.2251 - accuracy: 0.9201
30/30 [==============================] - 6s 200ms/step - loss: 0.2249 - accuracy: 0.9185 - val_loss: 0.3083 - val_accuracy: 0.8677
Epoch 15/20

 1/20 [>.............................] - ETA: 15s - loss: 0.2235 - accuracy: 0.9297
 2/20 [==>...........................] - ETA: 8s - loss: 0.2194 - accuracy: 0.9287 
 3/20 [===>..........................] - ETA: 6s - loss: 0.2232 - accuracy: 0.9238
 4/20 [=====>........................] - ETA: 4s - loss: 0.2185 - accuracy: 0.9248
 5/20 [======>.......................] - ETA: 3s - loss: 0.2181 - accuracy: 0.9258
 6/20 [========>.....................] - ETA: 3s - loss: 0.2187 - accuracy: 0.9261
 7/20 [=========>....................] - ETA: 2s - loss: 0.2233 - accuracy: 0.9244
 8/20 [===========>..................] - ETA: 2s - loss: 0.2206 - accuracy: 0.9253
 9/20 [============>.................] - ETA: 2s - loss: 0.2188 - accuracy: 0.9243
10/20 [==============>...............] - ETA: 1s - loss: 0.2199 - accuracy: 0.9242
11/20 [===============>..............] - ETA: 1s - loss: 0.2179 - accuracy: 0.9251
12/20 [=================>............] - ETA: 1s - loss: 0.2175 - accuracy: 0.9253
13/20 [==================>...........] - ETA: 1s - loss: 0.2174 - accuracy: 0.9246
14/20 [====================>.........] - ETA: 1s - loss: 0.2142 - accuracy: 0.9259
15/20 [=====================>........] - ETA: 0s - loss: 0.2116 - accuracy: 0.9271
16/20 [=======================>......] - ETA: 0s - loss: 0.2119 - accuracy: 0.9270
17/20 [========================>.....] - ETA: 0s - loss: 0.2118 - accuracy: 0.9267
18/20 [==========================>...] - ETA: 0s - loss: 0.2109 - accuracy: 0.9269
19/20 [===========================>..] - ETA: 0s - loss: 0.2118 - accuracy: 0.9261
30/30 [==============================] - 6s 203ms/step - loss: 0.2112 - accuracy: 0.9255 - val_loss: 0.3049 - val_accuracy: 0.8692
Epoch 16/20

 1/20 [>.............................] - ETA: 15s - loss: 0.1807 - accuracy: 0.9336
 2/20 [==>...........................] - ETA: 8s - loss: 0.1794 - accuracy: 0.9404 
 3/20 [===>..........................] - ETA: 6s - loss: 0.1848 - accuracy: 0.9395
 4/20 [=====>........................] - ETA: 4s - loss: 0.1844 - accuracy: 0.9370
 5/20 [======>.......................] - ETA: 3s - loss: 0.1842 - accuracy: 0.9363
 6/20 [========>.....................] - ETA: 3s - loss: 0.1811 - accuracy: 0.9368
 7/20 [=========>....................] - ETA: 2s - loss: 0.1813 - accuracy: 0.9369
 8/20 [===========>..................] - ETA: 2s - loss: 0.1823 - accuracy: 0.9358
 9/20 [============>.................] - ETA: 2s - loss: 0.1834 - accuracy: 0.9351
10/20 [==============>...............] - ETA: 1s - loss: 0.1873 - accuracy: 0.9338
11/20 [===============>..............] - ETA: 1s - loss: 0.1869 - accuracy: 0.9343
12/20 [=================>............] - ETA: 1s - loss: 0.1876 - accuracy: 0.9347
13/20 [==================>...........] - ETA: 1s - loss: 0.1884 - accuracy: 0.9339
14/20 [====================>.........] - ETA: 1s - loss: 0.1891 - accuracy: 0.9337
15/20 [=====================>........] - ETA: 0s - loss: 0.1890 - accuracy: 0.9340
16/20 [=======================>......] - ETA: 0s - loss: 0.1876 - accuracy: 0.9344
17/20 [========================>.....] - ETA: 0s - loss: 0.1867 - accuracy: 0.9352
18/20 [==========================>...] - ETA: 0s - loss: 0.1874 - accuracy: 0.9350
19/20 [===========================>..] - ETA: 0s - loss: 0.1885 - accuracy: 0.9348
30/30 [==============================] - 6s 202ms/step - loss: 0.1911 - accuracy: 0.9321 - val_loss: 0.2996 - val_accuracy: 0.8722
Epoch 17/20

 1/20 [>.............................] - ETA: 15s - loss: 0.2013 - accuracy: 0.9219
 2/20 [==>...........................] - ETA: 8s - loss: 0.1983 - accuracy: 0.9297 
 3/20 [===>..........................] - ETA: 6s - loss: 0.1909 - accuracy: 0.9362
 4/20 [=====>........................] - ETA: 4s - loss: 0.1927 - accuracy: 0.9346
 5/20 [======>.......................] - ETA: 4s - loss: 0.1915 - accuracy: 0.9359
 6/20 [========>.....................] - ETA: 3s - loss: 0.1901 - accuracy: 0.9355
 7/20 [=========>....................] - ETA: 2s - loss: 0.1887 - accuracy: 0.9344
 8/20 [===========>..................] - ETA: 2s - loss: 0.1912 - accuracy: 0.9333
 9/20 [============>.................] - ETA: 2s - loss: 0.1907 - accuracy: 0.9349
10/20 [==============>...............] - ETA: 1s - loss: 0.1918 - accuracy: 0.9348
11/20 [===============>..............] - ETA: 1s - loss: 0.1887 - accuracy: 0.9357
12/20 [=================>............] - ETA: 1s - loss: 0.1896 - accuracy: 0.9354
13/20 [==================>...........] - ETA: 1s - loss: 0.1893 - accuracy: 0.9363
14/20 [====================>.........] - ETA: 1s - loss: 0.1895 - accuracy: 0.9354
15/20 [=====================>........] - ETA: 0s - loss: 0.1881 - accuracy: 0.9354
16/20 [=======================>......] - ETA: 0s - loss: 0.1877 - accuracy: 0.9358
17/20 [========================>.....] - ETA: 0s - loss: 0.1870 - accuracy: 0.9361
18/20 [==========================>...] - ETA: 0s - loss: 0.1876 - accuracy: 0.9354
19/20 [===========================>..] - ETA: 0s - loss: 0.1875 - accuracy: 0.9353
30/30 [==============================] - 6s 205ms/step - loss: 0.1859 - accuracy: 0.9370 - val_loss: 0.3001 - val_accuracy: 0.8726
Epoch 18/20

 1/20 [>.............................] - ETA: 18s - loss: 0.1795 - accuracy: 0.9297
 2/20 [==>...........................] - ETA: 10s - loss: 0.1775 - accuracy: 0.9355
 3/20 [===>..........................] - ETA: 7s - loss: 0.1709 - accuracy: 0.9382 
 4/20 [=====>........................] - ETA: 5s - loss: 0.1768 - accuracy: 0.9326
 5/20 [======>.......................] - ETA: 4s - loss: 0.1730 - accuracy: 0.9352
 6/20 [========>.....................] - ETA: 3s - loss: 0.1740 - accuracy: 0.9378
 7/20 [=========>....................] - ETA: 3s - loss: 0.1740 - accuracy: 0.9381
 8/20 [===========>..................] - ETA: 2s - loss: 0.1721 - accuracy: 0.9395
 9/20 [============>.................] - ETA: 2s - loss: 0.1741 - accuracy: 0.9379
10/20 [==============>...............] - ETA: 2s - loss: 0.1772 - accuracy: 0.9363
11/20 [===============>..............] - ETA: 1s - loss: 0.1762 - accuracy: 0.9379
12/20 [=================>............] - ETA: 1s - loss: 0.1747 - accuracy: 0.9375
13/20 [==================>...........] - ETA: 1s - loss: 0.1744 - accuracy: 0.9389
14/20 [====================>.........] - ETA: 1s - loss: 0.1745 - accuracy: 0.9385
15/20 [=====================>........] - ETA: 0s - loss: 0.1731 - accuracy: 0.9384
16/20 [=======================>......] - ETA: 0s - loss: 0.1728 - accuracy: 0.9386
17/20 [========================>.....] - ETA: 0s - loss: 0.1724 - accuracy: 0.9388
18/20 [==========================>...] - ETA: 0s - loss: 0.1718 - accuracy: 0.9393
19/20 [===========================>..] - ETA: 0s - loss: 0.1720 - accuracy: 0.9395
30/30 [==============================] - 7s 219ms/step - loss: 0.1719 - accuracy: 0.9403 - val_loss: 0.2969 - val_accuracy: 0.8743
Epoch 19/20

 1/20 [>.............................] - ETA: 15s - loss: 0.1690 - accuracy: 0.9336
 2/20 [==>...........................] - ETA: 8s - loss: 0.1825 - accuracy: 0.9375 
 3/20 [===>..........................] - ETA: 6s - loss: 0.1645 - accuracy: 0.9453
 4/20 [=====>........................] - ETA: 4s - loss: 0.1615 - accuracy: 0.9453
 5/20 [======>.......................] - ETA: 4s - loss: 0.1647 - accuracy: 0.9426
 6/20 [========>.....................] - ETA: 3s - loss: 0.1627 - accuracy: 0.9440
 7/20 [=========>....................] - ETA: 3s - loss: 0.1635 - accuracy: 0.9436
 8/20 [===========>..................] - ETA: 2s - loss: 0.1634 - accuracy: 0.9446
 9/20 [============>.................] - ETA: 2s - loss: 0.1634 - accuracy: 0.9451
10/20 [==============>...............] - ETA: 1s - loss: 0.1618 - accuracy: 0.9455
11/20 [===============>..............] - ETA: 1s - loss: 0.1606 - accuracy: 0.9466
12/20 [=================>............] - ETA: 1s - loss: 0.1594 - accuracy: 0.9478
13/20 [==================>...........] - ETA: 1s - loss: 0.1603 - accuracy: 0.9465
14/20 [====================>.........] - ETA: 1s - loss: 0.1597 - accuracy: 0.9471
15/20 [=====================>........] - ETA: 0s - loss: 0.1591 - accuracy: 0.9473
16/20 [=======================>......] - ETA: 0s - loss: 0.1582 - accuracy: 0.9482
17/20 [========================>.....] - ETA: 0s - loss: 0.1570 - accuracy: 0.9489
18/20 [==========================>...] - ETA: 0s - loss: 0.1583 - accuracy: 0.9485
19/20 [===========================>..] - ETA: 0s - loss: 0.1588 - accuracy: 0.9475
30/30 [==============================] - 6s 210ms/step - loss: 0.1597 - accuracy: 0.9454 - val_loss: 0.2963 - val_accuracy: 0.8748
Epoch 20/20

 1/20 [>.............................] - ETA: 15s - loss: 0.1607 - accuracy: 0.9473
 2/20 [==>...........................] - ETA: 8s - loss: 0.1588 - accuracy: 0.9463 
 3/20 [===>..........................] - ETA: 6s - loss: 0.1581 - accuracy: 0.9486
 4/20 [=====>........................] - ETA: 5s - loss: 0.1546 - accuracy: 0.9512
 5/20 [======>.......................] - ETA: 4s - loss: 0.1526 - accuracy: 0.9516
 6/20 [========>.....................] - ETA: 3s - loss: 0.1543 - accuracy: 0.9512
 7/20 [=========>....................] - ETA: 2s - loss: 0.1532 - accuracy: 0.9528
 8/20 [===========>..................] - ETA: 2s - loss: 0.1541 - accuracy: 0.9534
 9/20 [============>.................] - ETA: 2s - loss: 0.1542 - accuracy: 0.9531
10/20 [==============>...............] - ETA: 1s - loss: 0.1539 - accuracy: 0.9523
11/20 [===============>..............] - ETA: 1s - loss: 0.1536 - accuracy: 0.9515
12/20 [=================>............] - ETA: 1s - loss: 0.1515 - accuracy: 0.9518
13/20 [==================>...........] - ETA: 1s - loss: 0.1529 - accuracy: 0.9509
14/20 [====================>.........] - ETA: 1s - loss: 0.1542 - accuracy: 0.9508
15/20 [=====================>........] - ETA: 0s - loss: 0.1539 - accuracy: 0.9509
16/20 [=======================>......] - ETA: 0s - loss: 0.1515 - accuracy: 0.9519
17/20 [========================>.....] - ETA: 0s - loss: 0.1503 - accuracy: 0.9520
18/20 [==========================>...] - ETA: 0s - loss: 0.1510 - accuracy: 0.9521
19/20 [===========================>..] - ETA: 0s - loss: 0.1517 - accuracy: 0.9515
30/30 [==============================] - 6s 213ms/step - loss: 0.1513 - accuracy: 0.9509 - val_loss: 0.2954 - val_accuracy: 0.8758
49/49 - 5s - loss: 0.3182 - accuracy: 0.8657
loss: 0.318
accuracy: 0.866

你可能感兴趣的:(TensorFlow)

  • Python开发常用的三方模块如下： 换个网名有点难 python开发语言
    Python是一门功能强大的编程语言，拥有丰富的第三方库，这些库为开发者提供了极大的便利。以下是100个常用的Python库，涵盖了多个领域：1、NumPy，用于科学计算的基础库。2、Pandas，提供数据结构和数据分析工具。3、Matplotlib，一个绘图库。4、Scikit-learn，机器学习库。5、SciPy，用于数学、科学和工程的库。6、TensorFlow，由Google开发的开源机
  • 关于python版本与TensorFlow安装的版本问题 iiimharrygGc. pythontensorflow开发语言
    实测在conda环境下，python3.12的版本无法安装TensorFlow2.14.0（截至2024.5.21）最新版本在python3.7版本下正常安装ps：上述安装均在anacondanavigator软件内安装
  • Vue + Django的人脸识别系统 DXSsssss pythonDRFtensorflow人脸识别
    最近在研究机器学习，刚好最近看了vue+Djangodrf的一些课程，学以致用，做了一个人脸识别系统。项目前端使用Vue框架，用到了elementui组件，写起来真是方便。比之前传统的dtl方便了太多。后端使用了drf，识别知识刚开始打算使用opencv+tensorflow,但是发现吧识别以后的结果返回到浏览器当中时使用opencv比较麻烦（主要是我太菜，想不到比较好的方法），因此最终使用了tf
  • Awesome TensorFlow weixin_30594001 人工智能移动开发大数据
    AwesomeTensorFlowAcuratedlistofawesomeTensorFlowexperiments,libraries,andprojects.Inspiredbyawesome-machine-learning.WhatisTensorFlow?TensorFlowisanopensourcesoftwarelibraryfornumericalcomputationusin
  • 【ShuQiHere】小白也能懂的 TensorFlow 和 PyTorch GPU 配置教程 ShuQiHere tensorflowpytorch人工智能
    【ShuQiHere】在深度学习中，GPU的使用对于加速模型训练至关重要。然而，对于许多刚刚入门的小白来说，如何在TensorFlow和PyTorch中指定使用GPU进行训练可能会感到困惑。在本文中，我将详细介绍如何在这两个主流的深度学习框架中指定使用GPU进行训练，并确保每一个步骤都简单易懂，跟着我的步骤来，你也能轻松上手！1.安装所需库首先，确保你已经安装了TensorFlow或PyTorch
  • TensorFlow的基本概念以及使用场景 张柏慈 决策树
    TensorFlow是一个机器学习平台，用于构建和训练机器学习模型。它使用图形表示计算任务，其中节点表示数学操作，边表示计算之间的数据流动。TensorFlow的主要特点包括：1.多平台支持：TensorFlow可以运行在多种硬件和操作系统上，包括CPU、GPU和移动设备。2.自动求导：TensorFlow可以自动计算模型参数的梯度，通过优化算法更新参数，以提高模型的准确性。3.分布式计算：Ten
  • 基于VGG的猫狗识别 卑微小鹿 tensorflowtensorflow
    由于猫和狗的数据在这里，所以就做了一下分类的神经网络1、首先进行图像处理：importcsvimportglobimportosimportrandomos.environ['TF_CPP_MIN_LOG_LEVEL']='2'importtensorflowastffromtensorflowimportkerasfromtensorflow.kerasimportlayersimportnum
  • 轻松升级：Ollama + OpenWebUI 安装与配置【AIStarter】 ai_xiaogui AI作画AI软件人工智能AI写作AIStarter
    Ollama是一个开源项目，用于构建和训练大规模语言模型，而OpenWebUI则提供了一个方便的前端界面来管理和监控这些模型。本文将指导你如何更新这两个工具，并顺利完成配置。准备工作确保你的系统已安装Git和Python环境。安装必要的依赖库，如TensorFlow或PyTorch等。更新步骤克隆项目：使用Git命令行工具克隆最新的Ollama和OpenWebUI仓库到本地。更新代码：确保你正在使
  • 深度学习之基于Tensorflow卷积神经网络水果蔬菜分类识别系统 qq1744828575 pythonpythonplotly
    欢迎大家点赞、收藏、关注、评论啦，由于篇幅有限，只展示了部分核心代码。文章目录一项目简介二、功能三、系统四.总结一项目简介  一、项目背景与目标背景：在现代农业、智能零售等领域，自动化分类与识别技术对于提高效率、优化供应链管理具有重要意义。为了响应这一需求，本项目旨在构建一个基于深度学习技术的水果蔬菜分类识别系统。目标：构建一个准确率高、性能稳定的水果蔬菜分类识别模型，利用Tensorflow框架
  • ImportError: cannot import name ‘conv_utils‘ from ‘keras.utils‘ CheCacao keras深度学习pythontensorflowtensorflow2人工智能
    将fromkeras.utilsimportconv_utils改为fromtensorflow.python.keras.utilsimportconv_utilsImportError:nomodulenamed'tensorflow.keras.engine将fromkeras.engine.topologyimportLayer改为fromtensorflow.python.keras.l
  • jupyter出错ImportError: cannot import name ‘np_utils‘ from ‘keras.utils‘ ，怎么解决？ 七月初七淮水竹亭～ 人工智能pythonjupyterkeras深度学习
    文章前言此篇文章主要是记录一下我遇到的问题以及我是如何解决的，希望下次遇到类似问题可以很快解决。此外，也希望能帮助到大家。遇到的问题出错：ImportError:cannotimportname'np_utils'from'keras.utils'，如图：如何解决首先我根据网上文章的一些提示，将fromkeras.utilsimportnp_utils换成了fromtensorflow.keras
  • tensorflow和python不兼容_tensorflow与numpy的版本兼容性问题的解决 weixin_39727934
    在Python交互式窗口导入tensorflow出现了下面的错误：ox8免费资源网root@ubuntu:~#python3Python3.6.8(default,Oct72019,12:59:55)[GCC8.3.0]onlinuxType"help","copyright","credits"or"license"formoreinformation.>>>importtensorflowas
  • numpy python 兼容_tensorflow与numpy的版本兼容性问题 weixin_39761822 numpypython兼容
    在Python交互式窗口导入tensorflow出现了下面的错误：root@ubuntu:~#python3Python3.6.8(default,Oct72019,12:59:55)[GCC8.3.0]onlinuxType"help","copyright","credits"or"license"formoreinformation.>>>importtensorflowastf;/usr/
  • 安装tensorflow2.5.0 发现 tensorflow 和 numba 两者对应Numpy版本冲突 GJK_ tensorflownumpy人工智能
    问题：python3.8安装tensorflow2.5.0发现tensorflow和numba两者对应Numpy版本冲突tensorflow-gpu2.5.0requiresnumpy~=1.19.2numba0.58.1requiresnumpy=1.22解决方法：将numba降低版本为0.53pipinstallnumba==0.53再将numpy版本改为1.19.2pipinstallnum
  • python3.7安装keras教程_python 3.7 安装 sklearn keras(tf.keras) weixin_39641103
    #1sklearn一般方法网上有很多教程，不再赘述。注意顺序是numpy+mkl，然后scipy的环境，scipy，然后sklearn#2anocondaanaconda原始的环境已经自带了sklearn，这里说一下新建环境（比如创建了一个tensorflow的环境），activatetensorflow2.0，然后condainstallsklearn即可，会帮你把各种需要的库都安装。#kera
  • Python高层神经网络 API库之Keras使用详解 Rocky006 pythonkeras开发语言
    概要随着深度学习在各个领域的广泛应用，许多开发者开始使用各种框架来构建和训练神经网络模型。Keras是一个高层神经网络API，使用Python编写，并能够运行在TensorFlow、CNTK和Theano之上。Keras旨在简化深度学习模型的构建过程，使得开发者能够更加专注于实验和研究。本文将详细介绍Keras库，包括其安装方法、主要特性、基本和高级功能，以及实际应用场景，帮助全面了解并掌握该库的
  • 将本地已有的项目上传到新建的git仓库的方法 10676
    将本地已有的一个非git项目上传到新建的git仓库的方法一共有两种。一、克隆+拷贝第一种方法比较简单，直接用把远程仓库拉到本地，然后再把自己本地的项目拷贝到仓库中去。然后push到远程仓库上去即可。此方法适用于本地项目不是一个git仓库的情况。1、首先克隆[email protected]:yuanmingchen/tensorflow_study.git2、然后复制自己项目的所有文件到
  • Python(PyTorch和TensorFlow)图像分割卷积网络导图(生物医学) 亚图跨际 交叉知识Python生物医学脑肿瘤图像皮肤病变多模态医学图像多尺度特征生物医学腹部胰腺图像病灶边界气胸图像
    要点语义分割图像三层分割椭圆图像脑肿瘤图像分割动物图像分割皮肤病变分割多模态医学图像多尺度特征生物医学肖像多类和医学分割通用图像分割模板腹部胰腺图像分割分类注意力网络病灶边界分割气胸图像分割Python生物医学图像卷积网络该网络由收缩路径和扩展路径组成，收缩路径是一种典型的卷积网络，由重复应用卷积组成，每个卷积后跟一个整流线性单元(ReLU)和一个最大池化操作。在收缩过程中，空间信息减少，而特征信
  • AttributeError: ‘tuple‘ object has no attribute ‘shape‘ 晓胡同学 keras深度学习tensorflow
    AttributeError:‘tuple’objecthasnoattribute‘shape’在将keras代码改为tensorflow2代码的时候报了如下错误AttributeError:'tuple'objecthasnoattribute'shape'经过调查发现，损失函数写错了原来的是这样model.compile(loss=['binary_crossentropy'],optimi
  • Autoencoder chuange6363 人工智能python
    自编码器Autoencoder稀疏自编码器SparseAutoencoder降噪自编码器DenoisingAutoencoder堆叠自编码器StackedAutoencoder本博客是从梁斌博士的博客上面复制过来的，本人利用Tensorflow重新实现了博客中的代码深度学习有一个重要的概念叫autoencoder，这是个什么东西呢，本文通过一个例子来普及这个术语。简单来说autoencoder是一
  • OSError: libnccl.so.2: cannot open shared object file: No such file or directory 王小葱鸭 python
    linux安装完torch或者tensorflow的gpu版本，安装没问题，但是import就有问题，报错OSError:libnccl.so.2:cannotopensharedobjectfile:Nosuchfileordirectory，是缺少nvidia的ncll，下面介绍解决方法：1安装ncll下载链接https://developer.nvidia.com/nccl/nccl-dow
  • 深度学习框架 人工智能操作系统 训练&前向推理 PyTorch Tensorflow MindSpore caffe 张量加速引擎TBE 深度学习编译器 多面体 polyhedral AI集群框架 EwenWanW 深度学习人工智能pytorch深度学习编译器
    深度学习框架人工智能操作系统训练&前向推理深度学习框架发展到今天，目前在架构上大体已经基本上成熟并且逐渐趋同。无论是国外的Tensorflow、PyTorch，亦或是国内最近开源的MegEngine、MindSpore，目前基本上都是支持EagerMode和GraphMode两种模式。AI嵌入式框架OneFlow&清华计图Jittor&华为深度学习框架MindSpore&旷视深度学习框架MegEn
  • Tensorflow中Keras搭建神经网络六步法及参数详解 -- Tensorflow自学笔记12 青瓷看世界 tensorflow笔记人工智能深度学习神经网络
    一.tf.keras搭建神经网络六步法1.import相关模块如importtensorflowastf。2.指定输入网络的训练集和测试集如指定训练集的输入x_train和标签y_train，测试集的输入x_test和标签y_test。3.逐层搭建网络结构model=tf.keras.models.Sequential()。4.在model.compile()中配置训练方法选择训练时使用的优化器、
  • MacBook Air M1 使用 miniconda 安装python3.11.7 和 tensorflow2.16.1详细 - TensorFlow自学笔记1 青瓷看世界 tensorflowtensorflow人工智能macpython深度学习
    1m1mac安装xcode命令工具在Terminal终端执行以下代码：xcode-select--install2下载支持m1芯片arm64的miniconda在miniconda官网，找到下图中保护AppleM1的bash安装包，Miniconda—Anacondadocumentation3安装miniconda在Terminal执行下列代码：1）cd"miniconda下载目录"2）bash
  • 机器学习框架巅峰对决：TensorFlow vs. PyTorch vs. Scikit-Learn实战分析 @sinner 技术选型机器学习tensorflowpytorchscikit-learn
    1.引言1.1机器学习框架的重要性在机器学习的黄金时代，框架的选择对于开发高效、可扩展的模型至关重要。合适的框架可以极大地提高开发效率，简化模型的构建和训练过程，并支持大规模的模型部署。因此，了解和选择最合适的机器学习框架对于研究人员和工程师来说是一个关键的步骤。1.2三大框架概览：TensorFlow、PyTorch、Scikit-Learn目前，最流行的机器学习框架主要有TensorFlow、
  • Tensorflow2.16中的Keras包含哪些层(layers)?层的功能及参数详细解释 -- TensorFlow自学笔记6 青瓷看世界 tensorflowtensorflowkeras人工智能
    在Keras中，层（Layer）是构建神经网络的基本组件。Keras提供了多种类型的层，用于处理不同类型的输入数据和执行特定的数学操作。英文版可参考TensorFlow官方文档：Module:tf.keras.layers|TensorFlowv2.16.1一.层的分类‌1.基本网络层‌1.1.Dense层用于执行全连接操作；1.2.卷积层Conv1D、Conv2D、Conv3D层，用于执行一维、
  • Tensorflow2 如何扩展现有数据集(缩放、随机旋转、水平翻转、平移等)，从而提高模型的准确率 -- Tensorflow自学笔记14 青瓷看世界 tensorflow人工智能python
    实际生活中的数据集，往往不是标准的数据，而是有倾斜角度、有旋转、有偏移的数据，为了提高数据集的真实性，提高模型预测的准确率，可以用ImageDataGenerator函数来扩展数据集importtensorflowastffromtensorflow.keras.preprocessing.imageimportImageDataGeneratorimage_gen_train=ImageData
  • 机器学习100天-Day2503 Tensorboard 训练数据可视化（线性回归） 我的昵称违规了
    首页.jpg源代码来自莫烦python(https://morvanzhou.github.io/tutorials/machine-learning/tensorflow/4-1-tensorboard1/)今日重点读懂教程中代码，手动重写一遍，在浏览器中获取到训练数据Tensorboard是一个神经网络可视化工具，通过使用本地服务器在浏览器上查看神经网络训练日志，生成相应的可是画图，帮助炼丹师
  • Python(TensorFlow)和Java及C++受激发射损耗导图 亚图跨际 Python交叉知识算法去噪预测算法聚焦荧光团伪影消除算法囊泡动力学自动化多尺度统计物距
    要点神经网络监督去噪预测算法聚焦荧光团和检测模拟平台伪影消除算法性能优化方法自动化多尺度囊泡动力学成像生物研究多维分析统计物距粒子概率算法Python和MATLAB图像降噪算法消除噪声的一种方法是将原始图像与表示低通滤波器或平滑操作的掩模进行卷积。例如，高斯掩模包含由高斯函数确定的元素。这种卷积使每个像素的值与其相邻像素的值更加协调。一般来说，平滑滤波器将每个像素设置为其自身及其附近相邻像素的平均
  • 中文车牌识别系统 `End-to-end-for-Chinese-Plate-Recognition` 教程 皮静滢Annette
    中文车牌识别系统End-to-end-for-Chinese-Plate-Recognition教程End-to-end-for-chinese-plate-recognition基于u-net，cv2以及cnn的中文车牌定位，矫正和端到端识别软件，其中unet和cv2用于车牌定位和矫正，cnn进行车牌识别，unet和cnn都是基于tensorflow的keras实现项目地址:https://gi
  • 多线程编程之卫生间 周凡杨 java并发卫生间线程厕所
    如大家所知，火车上车厢的卫生间很小，每次只能容纳一个人，一个车厢只有一个卫生间，这个卫生间会被多个人同时使用，在实际使用时，当一个人进入卫生间时则会把卫生间锁上，等出来时打开门，下一个人进去把门锁上，如果有一个人在卫生间内部则别人的人发现门是锁的则只能在外面等待。问题分析：首先问题中有两个实体，一个是人，一个是厕所，所以设计程序时就可以设计两个类。人是多数的，厕所只有一个（暂且模拟的是一个车厢）。
  • How to Install GUI to Centos Minimal sunjing linuxInstallDesktopGUI
    http://www.namhuy.net/475/how-to-install-gui-to-centos-minimal.html   I have centos 6.3 minimal running as web server. I’m looking to install gui to my server to vnc to my server. You can insta
  • Shell 函数 daizj shell函数
    Shell 函数 linux shell 可以用户定义函数，然后在shell脚本中可以随便调用。 shell中函数的定义格式如下： [function] funname [()]{ action; [return int;] } 说明： 1、可以带function fun() 定义，也可以直接fun() 定义,不带任何参数。 2、参数返回
  • Linux服务器新手操作之一 周凡杨 Linux 简单 操作
    1.whoami      当一个用户登录Linux系统之后，也许他想知道自己是发哪个用户登录的。      此时可以使用whoami命令。      [ecuser@HA5-DZ05 ~]$ whoami       e
  • 浅谈Socket通信（一） 朱辉辉33 socket
    在java中ServerSocket用于服务器端，用来监听端口。通过服务器监听，客户端发送请求，双方建立链接后才能通信。当服务器和客户端建立链接后，两边都会产生一个Socket实例，我们可以通过操作Socket来建立通信。    首先我建立一个ServerSocket对象。当然要导入java.net.ServerSocket包    ServerSock
  • 关于框架的简单认识 西蜀石兰 框架
    入职两个月多，依然是一个不会写代码的小白，每天的工作就是看代码，写wiki。 前端接触CSS、HTML、JS等语言，一直在用的CS模型，自然免不了数据库的链接及使用，真心涉及框架，项目中用到的BootStrap算一个吧，哦，JQuery只能算半个框架吧，我更觉得它是另外一种语言。 后台一直是纯Java代码，涉及的框架是Quzrtz和log4j。 都说学前端的要知道三大框架，目前node.
  • You have an error in your SQL syntax; check the manual that corresponds to your 林鹤霄
    You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near 'option,changed_ids  ) values('0ac91f167f754c8cbac00e9e3dc372
  • MySQL5.6的my.ini配置 aigo mysql
    注意：以下配置的服务器硬件是：8核16G内存    [client]   port=3306   [mysql]   default-character-set=utf8     [mysqld]   port=3306   basedir=D:/mysql-5.6.21-win
  • mysql 全文模糊查找 便捷解决方案 alxw4616 mysql
    mysql 全文模糊查找 便捷解决方案 2013/6/14 by 半仙 [email protected] 目的: 项目需求实现模糊查找. 原则: 查询不能超过 1秒. 问题: 目标表中有超过1千万条记录. 使用like '%str%' 进行模糊查询无法达到性能需求. 解决方案: 使用mysql全文索引. 1.全文索引 : MySQL支持全文索引和搜索功能。MySQL中的全文索
  • 自定义数据结构 链表(单项 ,双向,环形) 百合不是茶 单项链表双向链表
         链表与动态数组的实现方式差不多,    数组适合快速删除某个元素    链表则可以快速的保存数组并且可以是不连续的       单项链表;数据从第一个指向最后一个   实现代码:        //定义动态链表 clas
  • threadLocal实例 bijian1013 javathreadjava多线程threadLocal
    实例1： package com.bijian.thread; public class MyThread extends Thread { private static ThreadLocal tl = new ThreadLocal() { protected synchronized Object initialValue() { return new Inte
  • activemq安全设置—设置admin的用户名和密码 bijian1013 javaactivemq
            ActiveMQ使用的是jetty服务器, 打开conf/jetty.xml文件，找到 <bean id="adminSecurityConstraint" class="org.eclipse.jetty.util.security.Constraint"> <p
  • 【Java范型一】Java范型详解之范型集合和自定义范型类 bit1129 java
    本文详细介绍Java的范型，写一篇关于范型的博客原因有两个，前几天要写个范型方法(返回值根据传入的类型而定)，竟然想了半天，最后还是从网上找了个范型方法的写法；再者，前一段时间在看Gson, Gson这个JSON包的精华就在于对范型的优雅简单的处理，看它的源代码就比较迷糊，只其然不知其所以然。所以，还是花点时间系统的整理总结下范型吧。   范型内容 范型集合类 范型类
  • 【HBase十二】HFile存储的是一个列族的数据 bit1129 hbase
    在HBase中，每个HFile存储的是一个表中一个列族的数据，也就是说，当一个表中有多个列簇时，针对每个列簇插入数据，最后产生的数据是多个HFile，每个对应一个列族，通过如下操作验证   1. 建立一个有两个列族的表   create 'members','colfam1','colfam2'   2. 在members表中的colfam1中插入50*5
  • Nginx 官方一个配置实例 ronin47 nginx 配置实例
    user www www; worker_processes 5; error_log logs/error.log; pid logs/nginx.pid; worker_rlimit_nofile 8192; events { worker_connections 4096;} http { include conf/mim
  • java-15.输入一颗二元查找树，将该树转换为它的镜像， 即在转换后的二元查找树中，左子树的结点都大于右子树的结点。 用递归和循环 bylijinnan java
    //use recursion public static void mirrorHelp1(Node node){ if(node==null)return; swapChild(node); mirrorHelp1(node.getLeft()); mirrorHelp1(node.getRight()); } //use no recursion bu
  • 返回null还是empty bylijinnan javaapachespring编程
    第一个问题，函数是应当返回null还是长度为0的数组（或集合）？ 第二个问题，函数输入参数不当时，是异常还是返回null？ 先看第一个问题 有两个约定我觉得应当遵守： 1.返回零长度的数组或集合而不是null（详见《Effective Java》） 理由就是，如果返回empty，就可以少了很多not-null判断： List<Person> list
  • [科技与项目]工作流厂商的战略机遇期 comsci 工作流
          在新的战略平衡形成之前，这里有一个短暂的战略机遇期，只有大概最短6年，最长14年的时间，这段时间就好像我们森林里面的小动物，在秋天中，必须抓紧一切时间存储坚果一样，否则无法熬过漫长的冬季。。。。         在微软，甲骨文，谷歌，IBM,SONY
  • 过度设计-举例 cuityang 过度设计
    过度设计，需要更多设计时间和测试成本，如无必要，还是尽量简洁一些好。 未来的事情，比如 访问量，比如数据库的容量，比如是否需要改成分布式  都是无法预料的 再举一个例子，对闰年的判断逻辑： 　　1、 if($Year%4==0) return True; else return Fasle; 　　2、if (   ($Year%4==0  &am
  • java进阶，《Java性能优化权威指南》试读 darkblue086 java性能优化
    记得当年随意读了微软出版社的.NET 2.0应用程序调试，才发现调试器如此强大，应用程序开发调试其实真的简单了很多，不仅仅是因为里面介绍了很多调试器工具的使用，更是因为里面寻找问题并重现问题的思想让我震撼，时隔多年，Java已经如日中天，成为许多大型企业应用的首选，而今天，这本《Java性能优化权威指南》让我再次找到了这种感觉，从不经意的开发过程让我刮目相看，原来性能调优不是简单地看看热点在哪里，
  • 网络学习笔记初识OSI七层模型与TCP协议 dcj3sjt126com 学习笔记
      协议：在计算机网络中通信各方面所达成的、共同遵守和执行的一系列约定 　　计算机网络的体系结构：计算机网络的层次结构和各层协议的集合。 　　两类服务： 　　面向连接的服务通信双方在通信之前先建立某种状态，并在通信过程中维持这种状态的变化，同时为服务对象预先分配一定的资源。这种服务叫做面向连接的服务。 　　面向无连接的服务通信双方在通信前后不建立和维持状态，不为服务对象
  • mac中用命令行运行mysql dcj3sjt126com mysqllinuxmac
    参考这篇博客：http://www.cnblogs.com/macro-cheng/archive/2011/10/25/mysql-001.html  感觉workbench不好用（有点先入为主了）。 1，安装mysql 在mysql的官方网站下载 mysql 5.5.23 http://www.mysql.com/downloads/mysql/，根据我的机器的配置情况选择了64
  • MongDB查询（1）——基本查询[五] eksliang mongodbmongodb 查询mongodb find
    MongDB查询 转载请出自出处：http://eksliang.iteye.com/blog/2174452 一、find简介 MongoDB中使用find来进行查询。 API:如下 function ( query , fields , limit , skip, batchSize, options ){.....}  参数含义： query:查询参数 fie
  • base64，加密解密 经融加密，对接 y806839048 经融加密对接
    String data0 = new String(Base64.encode(bo.getPaymentResult().getBytes(("GBK")))); String data1 = new String(Base64.decode(data0.toCharArray()),"GBK"); // 注意编码格式，注意用于加密，解密的要是同
  • JavaWeb之JSP概述 ihuning javaweb
      什么是JSP？为什么使用JSP？ JSP表示Java Server Page，即嵌有Java代码的HTML页面。使用JSP是因为在HTML中嵌入Java代码比在Java代码中拼接字符串更容易、更方便和更高效。   JSP起源    在很多动态网页中，绝大部分内容都是固定不变的，只有局部内容需要动态产生和改变。  如果使用Servl
  • apple watch 指南 啸笑天 apple
    1. 文档 WatchKit Programming Guide（中译在线版 By @CocoaChina） 译文 译者 原文 概览 - 开始为 Apple Watch 进行开发 @星夜暮晨 Overview - Developing for Apple Watch 概览 - 配置 Xcode 项目 - Overview - Configuring Yo
  • java经典的基础题目 macroli java编程
    1.列举出 10个JAVA语言的优势 a:免费，开源，跨平台(平台独立性)，简单易用，功能完善，面向对象，健壮性，多线程，结构中立，企业应用的成熟平台, 无线应用 2.列举出JAVA中10个面向对象编程的术语 a:包，类，接口，对象，属性，方法，构造器，继承，封装，多态，抽象，范型 3.列举出JAVA中6个比较常用的包 Java.lang;java.util;java.io;java.sql;ja
  • 你所不知道神奇的js replace正则表达式 qiaolevip 每天进步一点点学习永无止境纵观千象regex
    var v = 'C9CFBAA3CAD0'; console.log(v); var arr = v.split(''); for (var i = 0; i < arr.length; i ++) { if (i % 2 == 0) arr[i] = '%' + arr[i]; } console.log(arr.join('')); console.log(v.r
  • [一起学Hive]之十五-分析Hive表和分区的统计信息(Statistics) superlxw1234 hivehive分析表hive统计信息hive Statistics
    关键字：Hive统计信息、分析Hive表、Hive Statistics   类似于Oracle的分析表，Hive中也提供了分析表和分区的功能，通过自动和手动分析Hive表，将Hive表的一些统计信息存储到元数据中。   表和分区的统计信息主要包括：行数、文件数、原始数据大小、所占存储大小、最后一次操作时间等；   14.1 新表的统计信息 对于一个新创建
  • Spring Boot 1.2.5 发布 wiselyman spring boot
        Spring Boot 1.2.5已在7月2日发布，现在可以从spring的maven库和maven中心库下载。   这个版本是一个维护的发布版，主要是一些修复以及将Spring的依赖提升至4.1.7(包含重要的安全修复)。   官方建议所有的Spring Boot用户升级这个版本。   项目首页 | 源
按字母分类： ABCDEFGHIJKLMNOPQRSTUVWXYZ其他