实验主要分为四个步骤：
- load datasets
- build network
- train
- test
构建的网络模型VGG13 一共13层
俺们老师给的待完善的代码如下，需要自己填写带下划线的部分
import tensorflow as tf
from tensorflow.keras import layers, optimizers, datasets, Sequential
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
tf.random.set_seed(2345)
conv_layers = [ # 5 units of conv + max pooling
#Please build vgg13 network according to the demonstration in readme file, bellow is a instance for unit 1
#Please complete other parts. (unit 2 to unit 5)
# unit 1
layers.Conv2D(64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.Conv2D(64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit 2
#____________________________________________________________________________
#____________________________________________________________________________
#____________________________________________________________________________
# unit 3
#____________________________________________________________________________
#____________________________________________________________________________
#____________________________________________________________________________
# unit 4
#____________________________________________________________________________
#____________________________________________________________________________
#____________________________________________________________________________
# unit 5
#____________________________________________________________________________
#____________________________________________________________________________
#____________________________________________________________________________
]
def preprocess(x, y):
# [0~1]
x = tf.cast(x, dtype=tf.float32) / 255.
y = tf.cast(y, dtype=tf.int32)
return x,y
(x,y), (x_test, y_test) = datasets.cifar100.load_data()
y = tf.squeeze(y, axis=1)
y_test = tf.squeeze(y_test, axis=1)
print(x.shape, y.shape, x_test.shape, y_test.shape)
train_db = tf.data.Dataset.from_tensor_slices((x,y))
train_db = train_db.shuffle(1000).map(preprocess).batch(128)
test_db = tf.data.Dataset.from_tensor_slices((x_test,y_test))
test_db = test_db.map(preprocess).batch(64)
sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape,
tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))
def main():
# [b, 32, 32, 3] => [b, 1, 1, 512]
conv_net = Sequential(conv_layers)
# Please add your code in blank
fc_net = Sequential([
layers.Dense(____________________________),
layers.Dense(____________________________),
layers.Dense(100, activation=None), #you can try other activation function to evaluate and compare
])
# Please add your code in blank
conv_net.build(input_shape=[None, ____, _____, ___])
fc_net.build(input_shape=[None, ____])
optimizer = optimizers.Adam(lr=1e-4)
# [1, 2] + [3, 4] => [1, 2, 3, 4]
variables = conv_net.trainable_variables + fc_net.trainable_variables
for epoch in range(50):
for step, (x,y) in enumerate(train_db):
with tf.GradientTape() as tape:
# [b, 32, 32, 3] => [b, 1, 1, 512]
out = conv_net(x)
# flatten, => [b, 512]
out = tf.reshape(out, [-1, 512])
# [b, 512] => [b, 100]
logits = fc_net(out)
# [b] => [b, 100]
y_onehot = tf.one_hot(y, depth=100)
# compute loss
loss = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True)
loss = tf.reduce_mean(loss)
# Please add your code in blank
grads = tape.gradient(___________, ______________)
optimizer.apply_gradients(zip(__________, ___________))
if step %100 == 0:
print(epoch, step, 'loss:', float(loss))
total_num = 0
total_correct = 0
for x,y in test_db:
out = conv_net(x)
out = tf.reshape(out, [-1, 512])
logits = fc_net(out)
prob = tf.nn.softmax(logits, axis=1)
pred = tf.argmax(prob, axis=1)
pred = tf.cast(pred, dtype=tf.int32)
correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_num += x.shape[0]
total_correct += int(correct)
acc = total_correct / total_num
print(epoch, 'acc:', acc)
if __name__ == '__main__':
main()
这是我完善过后的代码
import tensorflow as tf
from tensorflow.keras import layers, optimizers, datasets, Sequential
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
tf.random.set_seed(2345)
# 首先我们知道Sequential这个容器，接受一个13层的list.我们先组成list；网络的第一部分。
conv_layers = [ # 5 units of conv + max pooling
# unit 1
layers.Conv2D(64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.Conv2D(64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit 2
layers.Conv2D(128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.Conv2D(128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit 3
layers.Conv2D(256, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.Conv2D(256, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit 4
layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit 5
layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same')
]
# 进行数据预处理，仅仅是类型的转换。 [0~1]
def preprocess(x, y):
x = tf.cast(x, dtype=tf.float32) / 255.
y = tf.cast(y, dtype=tf.int32)
return x, y
# load datasets 根据要求使用的是cifar100
(x, y), (x_test, y_test) = datasets.cifar100.load_data()
y = tf.squeeze(y) # 或者tf.squeeze(y, axis=1)把1维度的squeeze掉。
y_test = tf.squeeze(y_test) # 或者tf.squeeze(y, axis=1)把1维度的squeeze掉。
print(x.shape, y.shape, x_test.shape, y_test.shape)
# 训练集
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(preprocess).batch(128)
# 测试集
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(preprocess).batch(128)
# 测试一下sample的形状。
sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape,
tf.reduce_min(sample[0]), tf.reduce_max(sample[0])) # 值范围为[0,1]
def main():
# 把参数放进Sequential容器
# 输入：[b, 32, 32, 3] => 输出[b, 1, 1, 512]
conv_net = Sequential(conv_layers)
# conv_net.build(input_shape=[None, 32, 32, 3])
# x = tf.random.normal([4, 32, 32, 3])
# out = conv_net(x)
# print(out.shape)
# 创建全连接层网络；网络的第二部分；第二部分的输入为第一部分的输出。
fc_net = Sequential([
layers.Dense(256, activation=tf.nn.relu),
layers.Dense(128, activation=tf.nn.relu),
layers.Dense(100, activation=None),
])
# 这里其实把一个网络分成2个来写，
conv_net.build(input_shape=[None, 32, 32, 3])
fc_net.build(input_shape=[None, 512])
# 创建一个优化器
optimizer = optimizers.Adam(lr=1e-4)
conv_net.summary()
fc_net.summary()
# 下面的+表示拼接。python中的list列表拼接，2个列表变为一个。
# 例如：[1, 2] + [3, 4] => [1, 2, 3, 4]
variables = conv_net.trainable_variables + fc_net.trainable_variables
for epoch in range(50):
for step, (x, y) in enumerate(train_db):
with tf.GradientTape() as tape:
# [b, 32, 32, 3] => [b, 1, 1, 512]
out = conv_net(x)
# 之后squeeze或者reshape为平坦的flatten；flatten, => [b, 512]
out = tf.reshape(out, [-1, 512])
# 送入全连接层输入，得到输出logits
# [b, 512] => [b, 100]
logits = fc_net(out)
# [b] => [b, 100]转换为热编码。
y_onehot = tf.one_hot(y, depth=100)
# compute loss 结果维度[b]
loss = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True)
loss = tf.reduce_mean(loss)
# 梯度求解
grads = tape.gradient(loss, variables)
# 梯度更新
optimizer.apply_gradients(zip(grads, variables))
if step % 100 == 0:
print(epoch, step, 'loss:', float(loss))
# 做测试
total_num = 0
total_correct = 0
for x, y in test_db:
out = conv_net(x)
out = tf.reshape(out, [-1, 512])
logits = fc_net(out)
# 预测可能性。
prob = tf.nn.softmax(logits, axis=1)
pred = tf.argmax(prob, axis=1)
pred = tf.cast(pred, dtype=tf.int32)
# 拿到预测值pred和真实值比较。
correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_num += x.shape[0]
total_correct += int(correct) # 转换为numpy数据
acc = total_correct / total_num
print(epoch, 'acc:', acc)
# colab源码:https://github.com/jupyter/colaboratory
if __name__ == '__main__':
main()
在我机子上跑的结果，从上午十点开始跑的，一直跑了有十个小时，才跑了7/10，还没跑完。好慢啊。
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 32, 32, 64) 1792
conv2d_1 (Conv2D) (None, 32, 32, 64) 36928
max_pooling2d (MaxPooling2D (None, 16, 16, 64) 0
)
conv2d_2 (Conv2D) (None, 16, 16, 128) 73856
conv2d_3 (Conv2D) (None, 16, 16, 128) 147584
max_pooling2d_1 (MaxPooling (None, 8, 8, 128) 0
2D)
conv2d_4 (Conv2D) (None, 8, 8, 256) 295168
conv2d_5 (Conv2D) (None, 8, 8, 256) 590080
max_pooling2d_2 (MaxPooling (None, 4, 4, 256) 0
2D)
conv2d_6 (Conv2D) (None, 4, 4, 512) 1180160
conv2d_7 (Conv2D) (None, 4, 4, 512) 2359808
max_pooling2d_3 (MaxPooling (None, 2, 2, 512) 0
2D)
conv2d_8 (Conv2D) (None, 2, 2, 512) 2359808
conv2d_9 (Conv2D) (None, 2, 2, 512) 2359808
max_pooling2d_4 (MaxPooling (None, 1, 1, 512) 0
2D)
=================================================================
Total params: 9,404,992
Trainable params: 9,404,992
Non-trainable params: 0
_________________________________________________________________
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 256) 131328
dense_1 (Dense) (None, 128) 32896
dense_2 (Dense) (None, 100) 12900
=================================================================
Total params: 177,124
Trainable params: 177,124
Non-trainable params: 0
_________________________________________________________________
0 0 loss: 4.605703830718994
0 100 loss: 4.573154449462891
0 200 loss: 4.274768829345703
0 300 loss: 4.280937194824219
0 acc: 0.0626
1 0 loss: 4.13004207611084
1 100 loss: 4.003829002380371
1 200 loss: 3.8823888301849365
1 300 loss: 4.033702373504639
1 acc: 0.0968
2 0 loss: 3.9909071922302246
2 100 loss: 3.92575740814209
2 200 loss: 3.734340190887451
2 300 loss: 3.5258753299713135
2 acc: 0.1601
3 0 loss: 3.586297035217285
3 100 loss: 3.733517646789551
3 200 loss: 3.234541654586792
3 300 loss: 3.192173957824707
3 acc: 0.2045
4 0 loss: 3.4989943504333496
4 100 loss: 3.281524658203125
4 200 loss: 3.20217227935791
4 300 loss: 3.265291690826416
4 acc: 0.2305
5 0 loss: 3.2033958435058594
5 100 loss: 2.947575569152832
5 200 loss: 2.8855361938476562
5 300 loss: 2.885098934173584
5 acc: 0.2497
6 0 loss: 2.8828682899475098
6 100 loss: 3.0514018535614014
6 200 loss: 2.7332396507263184
6 300 loss: 3.0623221397399902
6 acc: 0.2771
7 0 loss: 3.0236001014709473
7 100 loss: 2.7354226112365723
7 200 loss: 2.4895710945129395
7 300 loss: 2.585233211517334
7 acc: 0.2853
8 0 loss: 2.621670722961426
8 100 loss: 2.807131767272949
8 200 loss: 2.6461825370788574
8 300 loss: 2.770937204360962
8 acc: 0.3049
9 0 loss: 2.8133463859558105
9 100 loss: 2.390254020690918
9 200 loss: 2.6979241371154785
9 300 loss: 2.122256278991699
9 acc: 0.3216
10 0 loss: 2.4884862899780273
10 100 loss: 2.3237156867980957
10 200 loss: 1.976022481918335
10 300 loss: 1.9411729574203491
10 acc: 0.341
11 0 loss: 2.3988051414489746
11 100 loss: 2.157597541809082
11 200 loss: 1.783387541770935
11 300 loss: 2.2747488021850586
11 acc: 0.3428
12 0 loss: 2.081052780151367
12 100 loss: 1.9125139713287354
12 200 loss: 1.9749314785003662
12 300 loss: 1.9473168849945068
12 acc: 0.3481
13 0 loss: 1.9426753520965576
13 100 loss: 1.6028225421905518
13 200 loss: 1.654457688331604
13 300 loss: 1.5368409156799316
13 acc: 0.348
14 0 loss: 1.9074410200119019
14 100 loss: 1.2604421377182007
14 200 loss: 1.33577299118042
14 300 loss: 1.4747681617736816
14 acc: 0.3456
15 0 loss: 1.408400535583496
15 100 loss: 1.4740254878997803
15 200 loss: 1.0276473760604858
15 300 loss: 1.2776360511779785
15 acc: 0.3468
16 0 loss: 1.1048237085342407
16 100 loss: 1.0582349300384521
16 200 loss: 0.7934116721153259
16 300 loss: 0.9454417824745178
16 acc: 0.3392
17 0 loss: 1.0203744173049927
17 100 loss: 0.5127657651901245
17 200 loss: 0.6567991971969604
17 300 loss: 0.74583899974823
17 acc: 0.3313
18 0 loss: 0.6991515159606934
18 100 loss: 0.49814605712890625
18 200 loss: 0.5801453590393066
18 300 loss: 0.5829309225082397
18 acc: 0.3317
19 0 loss: 0.4286673367023468
19 100 loss: 0.5325354337692261
19 200 loss: 0.3180204927921295
19 300 loss: 0.48299315571784973
19 acc: 0.3328
20 0 loss: 0.5821853280067444
20 100 loss: 0.24863868951797485
20 200 loss: 0.25470632314682007
20 300 loss: 0.23631633818149567
20 acc: 0.3273
21 0 loss: 0.328163743019104
21 100 loss: 0.19887247681617737
21 200 loss: 0.20321449637413025
21 300 loss: 0.37942832708358765
21 acc: 0.3366
22 0 loss: 0.3218492865562439
22 100 loss: 0.3823566734790802
22 200 loss: 0.2301541566848755
22 300 loss: 0.23679348826408386
22 acc: 0.3281
23 0 loss: 0.4278489351272583
23 100 loss: 0.17314794659614563
23 200 loss: 0.19846001267433167
23 300 loss: 0.15466056764125824
23 acc: 0.3397
24 0 loss: 0.3409762978553772
24 100 loss: 0.19322939217090607
24 200 loss: 0.2183304876089096
24 300 loss: 0.10360629856586456
24 acc: 0.3304
25 0 loss: 0.184882253408432
25 100 loss: 0.15770471096038818
25 200 loss: 0.11995077133178711
25 300 loss: 0.17878545820713043
25 acc: 0.3261
26 0 loss: 0.14563722908496857
26 100 loss: 0.10653193295001984
26 200 loss: 0.06353025138378143
26 300 loss: 0.10915520042181015
26 acc: 0.3338
27 0 loss: 0.159509539604187
27 100 loss: 0.049696896225214005
27 200 loss: 0.05399111658334732
27 300 loss: 0.13322849571704865
27 acc: 0.3307
28 0 loss: 0.36089855432510376
28 100 loss: 0.08262927830219269
28 200 loss: 0.18748503923416138
28 300 loss: 0.10662227123975754
28 acc: 0.3373
29 0 loss: 0.12509845197200775
29 100 loss: 0.08384230732917786
29 200 loss: 0.10343224555253983
29 300 loss: 0.13146759569644928
29 acc: 0.3421
30 0 loss: 0.16149979829788208
30 100 loss: 0.09493231028318405
30 200 loss: 0.11518850922584534
30 300 loss: 0.2519652545452118
30 acc: 0.3253
31 0 loss: 0.16040371358394623
31 100 loss: 0.08821642398834229
31 200 loss: 0.11975134164094925
31 300 loss: 0.2427465319633484
31 acc: 0.3342
32 0 loss: 0.11135876178741455
32 100 loss: 0.11297046393156052
32 200 loss: 0.11937586963176727
32 300 loss: 0.04514150321483612
32 acc: 0.3312
33 0 loss: 0.10594180226325989
33 100 loss: 0.15190201997756958
33 200 loss: 0.0702848881483078
33 300 loss: 0.03502190113067627
33 acc: 0.3291
34 0 loss: 0.15665759146213531
34 100 loss: 0.1422211229801178
34 200 loss: 0.08091887831687927
34 300 loss: 0.1349743902683258
34 acc: 0.3378
35 0 loss: 0.11525900661945343
35 100 loss: 0.06358155608177185
35 200 loss: 0.1529129147529602
35 300 loss: 0.22628331184387207
35 acc: 0.3382
36 0 loss: 0.15683573484420776
36 100 loss: 0.13646073639392853
36 200 loss: 0.06633880734443665
36 300 loss: 0.09798240661621094
36 acc: 0.341
37 0 loss: 0.12612700462341309
37 100 loss: 0.04630628228187561
37 200 loss: 0.18259760737419128
37 300 loss: 0.10138311982154846
37 acc: 0.3371
38 0 loss: 0.09454572945833206
38 100 loss: 0.0678207203745842
38 200 loss: 0.04612647742033005
38 300 loss: 0.041865911334753036
38 acc: 0.329
39 0 loss: 0.0841379314661026
39 100 loss: 0.05027864873409271
39 200 loss: 0.08458943665027618
39 300 loss: 0.06776276975870132
39 acc: 0.3399
40 0 loss: 0.14195799827575684
40 100 loss: 0.12060148268938065
40 200 loss: 0.13087618350982666
40 300 loss: 0.07757624983787537
40 acc: 0.3398
41 0 loss: 0.04287588596343994
41 100 loss: 0.10122890770435333
41 200 loss: 0.056345585733652115
41 300 loss: 0.04591142758727074
41 acc: 0.3436
42 0 loss: 0.08447226136922836
42 100 loss: 0.22661612927913666
42 200 loss: 0.1079418882727623
42 300 loss: 0.06236565485596657
42 acc: 0.3395
43 0 loss: 0.10079903900623322
43 100 loss: 0.10626668483018875
43 200 loss: 0.14811712503433228
43 300 loss: 0.10150552541017532
43 acc: 0.3464
44 0 loss: 0.10644478350877762
44 100 loss: 0.06013133376836777
44 200 loss: 0.06476859003305435
44 300 loss: 0.11906753480434418
44 acc: 0.3399
45 0 loss: 0.17771360278129578
45 100 loss: 0.05107204243540764
45 200 loss: 0.1423441469669342
45 300 loss: 0.02668618969619274
45 acc: 0.3408
46 0 loss: 0.17410549521446228
46 100 loss: 0.08211968839168549
46 200 loss: 0.04328247159719467
46 300 loss: 0.05685717985033989
46 acc: 0.3496
47 0 loss: 0.04248629510402679447 100 loss: 0.1727692037820816
47 200 loss: 0.09772153943777084
47 300 loss: 0.034717023372650146
47 acc: 0.3411
48 0 loss: 0.18558627367019653
48 100 loss: 0.06087672710418701
48 200 loss: 0.04182719439268112
48 300 loss: 0.06226355582475662
48 acc: 0.3339
49 0 loss: 0.08151577413082123
49 100 loss: 0.09905587136745453
49 200 loss: 0.09194858372211456
49 300 loss: 0.0321841835975647
49 acc: 0.3387Process finished with exit code 0
建议上colab上跑去，我也想去colab上跑，chrome打不开，卡在了第一步T_T。
12月7更新：下载了某助手之后，发现可以使用colab，同一个程序在colab上跑了大概有37分钟就跑完了，感觉跟在自己的机子上跑快太多太多了，下面是我在colab上的结果：
Downloading data from https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz 169009152/169001437 [==============================] - 3s 0us/step 169017344/169001437 [==============================] - 3s 0us/step (50000, 32, 32, 3) (50000,) (10000, 32, 32, 3) (10000,) sample: (128, 32, 32, 3) (128,) tf.Tensor(0.0, shape=(), dtype=float32) tf.Tensor(1.0, shape=(), dtype=float32) Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv2d (Conv2D) (None, 32, 32, 64) 1792 conv2d_1 (Conv2D) (None, 32, 32, 64) 36928 max_pooling2d (MaxPooling2D (None, 16, 16, 64) 0 ) conv2d_2 (Conv2D) (None, 16, 16, 128) 73856 conv2d_3 (Conv2D) (None, 16, 16, 128) 147584 max_pooling2d_1 (MaxPooling (None, 8, 8, 128) 0 2D) conv2d_4 (Conv2D) (None, 8, 8, 256) 295168 conv2d_5 (Conv2D) (None, 8, 8, 256) 590080 max_pooling2d_2 (MaxPooling (None, 4, 4, 256) 0 2D) conv2d_6 (Conv2D) (None, 4, 4, 512) 1180160 conv2d_7 (Conv2D) (None, 4, 4, 512) 2359808 max_pooling2d_3 (MaxPooling (None, 2, 2, 512) 0 2D) conv2d_8 (Conv2D) (None, 2, 2, 512) 2359808 conv2d_9 (Conv2D) (None, 2, 2, 512) 2359808 max_pooling2d_4 (MaxPooling (None, 1, 1, 512) 0 2D) ================================================================= Total params: 9,404,992 Trainable params: 9,404,992 Non-trainable params: 0 _________________________________________________________________ Model: "sequential_1" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= dense (Dense) (None, 256) 131328 dense_1 (Dense) (None, 128) 32896 dense_2 (Dense) (None, 100) 12900 ================================================================= Total params: 177,124 Trainable params: 177,124 Non-trainable params: 0 _________________________________________________________________/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead. super(Adam, self).__init__(name, **kwargs)0 0 loss: 4.605703830718994 0 100 loss: 4.579543113708496 0 200 loss: 4.295363426208496 0 300 loss: 4.30647611618042 0 acc: 0.0664 1 0 loss: 4.071621894836426 1 100 loss: 3.9781930446624756 1 200 loss: 3.8503026962280273 1 300 loss: 3.9217281341552734 1 acc: 0.1171 2 0 loss: 3.844515562057495 2 100 loss: 3.8795487880706787 2 200 loss: 3.5778450965881348 2 300 loss: 3.471754312515259 2 acc: 0.1735 3 0 loss: 3.5877599716186523 3 100 loss: 3.5094151496887207 3 200 loss: 3.271711826324463 3 300 loss: 3.1189067363739014 3 acc: 0.2057 4 0 loss: 3.5270471572875977 4 100 loss: 3.260599136352539 4 200 loss: 3.163914203643799 4 300 loss: 3.1675050258636475 4 acc: 0.2258 5 0 loss: 3.282217025756836 5 100 loss: 2.930232524871826 5 200 loss: 2.9272775650024414 5 acc: 0.2513 6 0 loss: 2.9781484603881836 6 100 loss: 3.0117006301879883 6 200 loss: 2.797576904296875 6 300 loss: 3.0792269706726074 6 acc: 0.2693 7 0 loss: 3.0973868370056152 7 100 loss: 2.7252399921417236 7 200 loss: 2.588582992553711 7 300 loss: 2.557039260864258 7 acc: 0.2895 8 0 loss: 2.6511619091033936 8 100 loss: 2.7096669673919678 8 200 loss: 2.586071491241455 8 300 loss: 2.7542171478271484 8 acc: 0.3092 9 0 loss: 2.6784982681274414 9 100 loss: 2.245143413543701 9 200 loss: 2.6391384601593018 9 300 loss: 2.1213998794555664 9 acc: 0.3136 10 0 loss: 2.5744028091430664 10 100 loss: 2.397691249847412 10 200 loss: 2.04136323928833 10 300 loss: 2.032853841781616 10 acc: 0.3292 11 0 loss: 2.248678684234619 11 100 loss: 2.147101879119873 11 200 loss: 1.7349820137023926 11 300 loss: 2.121100425720215 11 acc: 0.3247 12 0 loss: 1.920336365699768 12 100 loss: 1.7461389303207397 12 200 loss: 1.8104661703109741 12 300 loss: 1.698201298713684 12 acc: 0.3321 13 0 loss: 1.660325050354004 13 100 loss: 1.674147367477417 13 200 loss: 1.4182236194610596 13 300 loss: 1.3978238105773926 13 acc: 0.3231 14 0 loss: 1.2530699968338013 14 100 loss: 0.9997458457946777 14 200 loss: 1.309718370437622 14 300 loss: 1.084842324256897 14 acc: 0.3129 15 0 loss: 1.193671703338623 15 100 loss: 0.9685628414154053 15 200 loss: 0.9058113694190979 15 300 loss: 1.01847505569458 15 acc: 0.317 16 0 loss: 0.9028932452201843 16 100 loss: 0.6653304100036621 16 200 loss: 0.46601372957229614 16 300 loss: 0.6217385530471802 16 acc: 0.3106 17 0 loss: 0.727854311466217 17 100 loss: 0.3981296718120575 17 200 loss: 0.5228483080863953 17 300 loss: 0.5998938679695129 17 acc: 0.2991 18 0 loss: 0.5805451273918152 18 100 loss: 0.3940545320510864 18 200 loss: 0.4722597301006317 18 300 loss: 0.45523616671562195 18 acc: 0.2987 19 0 loss: 0.6003919839859009 19 100 loss: 0.2240317463874817 19 200 loss: 0.3627362847328186 19 300 loss: 0.26470911502838135 19 acc: 0.3089 20 0 loss: 0.2560865879058838 20 100 loss: 0.3344946503639221 20 200 loss: 0.31515398621559143 20 300 loss: 0.39510685205459595 20 acc: 0.3026 21 0 loss: 0.4620325565338135 21 100 loss: 0.2081003040075302 21 200 loss: 0.1886335015296936 21 300 loss: 0.26929280161857605 21 acc: 0.3074 22 0 loss: 0.24272006750106812 22 100 loss: 0.22473227977752686 22 200 loss: 0.20395854115486145 22 300 loss: 0.18820872902870178 22 acc: 0.3083 23 0 loss: 0.22682049870491028 23 100 loss: 0.36543434858322144 23 200 loss: 0.07166758924722672 23 300 loss: 0.09640516340732574 23 acc: 0.3075 24 0 loss: 0.1450769156217575 24 100 loss: 0.05213901400566101 24 200 loss: 0.23339170217514038 24 300 loss: 0.07248969376087189 24 acc: 0.3092 25 0 loss: 0.2158544361591339 25 100 loss: 0.12670393288135529 25 200 loss: 0.20489054918289185 25 300 loss: 0.11157195270061493 25 acc: 0.314 26 0 loss: 0.1532250940799713 26 100 loss: 0.0750114768743515 26 200 loss: 0.3784523010253906 26 300 loss: 0.0847141444683075 26 acc: 0.3072 27 0 loss: 0.16163787245750427 27 100 loss: 0.0931471735239029 27 200 loss: 0.09946497529745102 27 300 loss: 0.1250903308391571 27 acc: 0.3134 28 0 loss: 0.13532555103302002 28 100 loss: 0.141266867518425 28 200 loss: 0.19733315706253052 28 300 loss: 0.16875949501991272 28 acc: 0.3121 29 0 loss: 0.1743878275156021 29 100 loss: 0.12369076907634735 29 200 loss: 0.10782884061336517 29 300 loss: 0.060996994376182556 29 acc: 0.3122 30 0 loss: 0.09318936616182327 30 100 loss: 0.1147213727235794 30 200 loss: 0.17644652724266052 30 300 loss: 0.07866644859313965 30 acc: 0.3107 31 0 loss: 0.14084084331989288 31 100 loss: 0.08011481910943985 31 200 loss: 0.07548494637012482 31 300 loss: 0.09042893350124359 31 acc: 0.3139 32 0 loss: 0.16660545766353607 32 100 loss: 0.07169085741043091 32 200 loss: 0.19020332396030426 32 300 loss: 0.11832849681377411 32 acc: 0.3076 33 0 loss: 0.230143740773201 33 100 loss: 0.072193942964077 33 200 loss: 0.0462278351187706 33 300 loss: 0.04750790074467659 33 acc: 0.3125 34 0 loss: 0.09428784996271133 34 100 loss: 0.10934901982545853 34 200 loss: 0.08477897942066193 34 300 loss: 0.07798942178487778 34 acc: 0.3133 35 0 loss: 0.21155236661434174 35 100 loss: 0.21073132753372192 35 200 loss: 0.0553957037627697 35 300 loss: 0.10374538600444794 35 acc: 0.3153 36 0 loss: 0.048893291503190994 36 100 loss: 0.06306926906108856 36 200 loss: 0.10471584647893906 36 300 loss: 0.08443345874547958 36 acc: 0.3165 37 0 loss: 0.06113031506538391 37 100 loss: 0.059913210570812225 37 200 loss: 0.15217798948287964 37 300 loss: 0.10389281809329987 37 acc: 0.3135 38 0 loss: 0.13415582478046417 38 100 loss: 0.13481742143630981 38 200 loss: 0.1045721173286438 38 300 loss: 0.09099530428647995 38 acc: 0.3146 39 0 loss: 0.09938441962003708 39 100 loss: 0.10667737573385239 39 200 loss: 0.10043273866176605 39 300 loss: 0.05317280814051628 39 acc: 0.313 40 0 loss: 0.07995403558015823 40 100 loss: 0.03227170556783676 40 200 loss: 0.03379109501838684 40 300 loss: 0.05735338479280472 40 acc: 0.3145 41 0 loss: 0.0556551069021225 41 100 loss: 0.02025899849832058 41 200 loss: 0.06852033734321594 41 300 loss: 0.09525291621685028 41 acc: 0.3089 42 0 loss: 0.14556632936000824 42 100 loss: 0.13306768238544464 42 200 loss: 0.10822974890470505 42 300 loss: 0.0783647745847702 42 acc: 0.3147 43 0 loss: 0.03061378188431263 43 100 loss: 0.09040059894323349 43 200 loss: 0.16824980080127716 43 300 loss: 0.08020259439945221 43 acc: 0.3084 44 0 loss: 0.13128815591335297 44 100 loss: 0.0176226869225502 44 200 loss: 0.07319459319114685 44 300 loss: 0.06256011128425598 44 acc: 0.319 45 0 loss: 0.10079637169837952 45 100 loss: 0.021738210693001747 45 200 loss: 0.1580265760421753 45 300 loss: 0.12092546373605728 45 acc: 0.3082 46 0 loss: 0.06563448160886765 46 100 loss: 0.1869114339351654 46 200 loss: 0.09348289668560028 46 300 loss: 0.037952713668346405 46 acc: 0.3089 47 0 loss: 0.18213742971420288 47 100 loss: 0.12236323207616806 47 200 loss: 0.05455945432186127 47 300 loss: 0.09804233908653259 47 acc: 0.3178 48 0 loss: 0.06900112330913544 48 100 loss: 0.15671207010746002 48 200 loss: 0.032541245222091675 48 300 loss: 0.1704862266778946 48 acc: 0.3204 49 0 loss: 0.014402791857719421 49 100 loss: 0.03425758704543114 49 200 loss: 0.03888377547264099 49 300 loss: 0.04487434774637222 49 acc: 0.3125
呕吼，只想说colab np!
224
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
