jiqizhixin / ml-tutorial-experiment Goto Github PK

pool1 = tf.nn.max_pool(relu1, ksize=[1, 2, 2, 1],strides=[1,1,1,1], padding='SAME')
the strides should be [1,2,2,1] instead of [1,1,1,1]
input:28×28×32
output:14×14×32

AttributeError Traceback (most recent call last)
in ()
----> 1 train(BATCH_SIZE=36)

in train(BATCH_SIZE)
63
64 #判别器的损失；在一个batch的数据上进行一次参数更新
---> 65 d_loss = d.train_on_batch(X, y)
66 print("batch %d d_loss : %f" % (index, d_loss))
67

D:\Program Files\Anaconda3\lib\site-packages\keras\models.py in train_on_batch(self, x, y, class_weight, sample_weight)
1067 return self.model.train_on_batch(x, y,
1068 sample_weight=sample_weight,
-> 1069 class_weight=class_weight)
1070
1071 def test_on_batch(self, x, y,

D:\Program Files\Anaconda3\lib\site-packages\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1841 sample_weight=sample_weight,
1842 class_weight=class_weight,
-> 1843 check_batch_axis=True)
1844 if self.uses_learning_phase and not isinstance(K.learning_phase(), int):
1845 ins = x + y + sample_weights + [1.]

D:\Program Files\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size)
1428 output_shapes,
1429 check_batch_axis=False,
-> 1430 exception_prefix='target')
1431 sample_weights = _standardize_sample_weights(sample_weight,
1432 self._feed_output_names)

D:\Program Files\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
68 elif isinstance(data, list):
69 data = [x.values if x.class.name == 'DataFrame' else x for x in data]
---> 70 data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
71 else:
72 data = data.values if data.class.name == 'DataFrame' else data

D:\Program Files\Anaconda3\lib\site-packages\keras\engine\training.py in (.0)
68 elif isinstance(data, list):
69 data = [x.values if x.class.name == 'DataFrame' else x for x in data]
---> 70 data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
71 else:
72 data = data.values if data.class.name == 'DataFrame' else data

AttributeError: 'int' object has no attribute 'ndim'

with tf.variable_scope('layer6-fc2'):
fc2_weights = tf.get_variable('weight', [FC_SIZE, NUM_LABELS],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses', regularizer(fc1_weights))

    fc2_biases = tf.get_variable('bias', [NUM_LABELS], initializer=tf.constant_initializer(0.1))
    logit = tf.matmul(fc1, fc2_weights) + fc2_biases
return logit

inner the function tf.add_to_collection() should be regularizer(fc2_weights) instead of regularizer(fc1_weights)

CapsNet结构解析与实现-，最后运行的结果报错
WARNING:tensorflow:Error encountered when serializing global_step.
Type is unsupported, or the types of the items don't match field type in CollectionDef.
'Tensor' object has no attribute 'to_proto'

你好,非常感谢提供教程,我是小白,TCN中有个部分不是特别明白
TCN输入不定长的问题,比如输入是10x20
x40,相当于10是batch size,20是序列长度,40是每个元素的长度,如果使用TCN,对于序列长度不一致,是直接按最大序列长度补0吗?

I'll like to learn to code.

这个项目应该如何在Linux环境下运行，GAN新手，麻烦告知

OSError: Unable to open file (Unable to open file: name = 'generator', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)

纯新手，求问这是为什么呢

如何使用该模型进行预测和重构

generate这个文件如何生成？

首先谢谢提供代码。

按照代码思路运行之后，在第2000轮基本就收敛了，但是生成的图片好像不太好，网络加深好像也不太能行，这是怎么回事呢？