摘要：
1，tf.layers基础函数 conv2d(). Constructs a two-dimensional convolutional layer. Takes number of filters, filter kernel size, padding, and activation funct 阅读全文
posted @ 2019-03-10 22:23
Augustone
阅读(433)
评论(0)
推荐(0)
摘要：
1，以类的方式定义一个模型 class Model(object): def __init__(self): # Initialize variable to (5.0, 0.0) # In practice, these should be initialized to random values 阅读全文
posted @ 2019-03-10 21:29
Augustone
阅读(216)
评论(0)
推荐(0)
摘要：
1，share的内容 code to create the model, and the trained weights, or parameters, for the model 2，ways There are different ways to save TensorFlow models—d 阅读全文
posted @ 2019-03-10 21:10
Augustone
阅读(3883)
评论(0)
推荐(0)
摘要：
1，dataset的方法 Dataset.make_one_shot_iterator() or get_next() 2，使用python的方法-当eager mode enabled时 print('Elements of ds_tensors:')for x in ds_tensors: pr 阅读全文
posted @ 2019-03-10 20:34
Augustone
阅读(627)
评论(0)
推荐(0)
摘要：
map, batch, shuffle 阅读全文
posted @ 2019-03-10 20:31
Augustone
阅读(159)
评论(0)
推荐(0)
摘要：
1，几种方法 Create a source dataset using one of the factory functions like Dataset.from_tensors, Dataset.from_tensor_slices or using objects that read fro 阅读全文
posted @ 2019-03-10 20:29
Augustone
阅读(1485)
评论(0)
推荐(0)
摘要：
1，tensor的特点 Tensors can be backed by accelerator memory (like GPU, TPU). Tensors are immutable 2，双向转换 TensorFlow operations automatically convert NumP 阅读全文
posted @ 2019-03-10 20:25
Augustone
阅读(1359)
评论(0)
推荐(0)
摘要：
1， def get_flat_weights(model): weight_names = [ name for name in model.get_variable_names() if "linear_model" in name and "Ftrl" not in name] weight_ 阅读全文
posted @ 2019-03-10 17:46
Augustone
阅读(359)
评论(0)
推荐(0)
摘要：
1， model_l1 = tf.estimator.LinearClassifier( feature_columns=base_columns + crossed_columns, optimizer=tf.train.FtrlOptimizer( learning_rate=0.1, l1_r 阅读全文
posted @ 2019-03-10 17:40
Augustone
阅读(536)
评论(0)
推荐(0)
摘要：
1，数字类型的 education_num = tf.feature_column.numeric_column('education_num')capital_gain = tf.feature_column.numeric_column('capital_gain')capital_loss = 阅读全文
posted @ 2019-03-10 17:33
Augustone
阅读(1800)
评论(0)
推荐(0)
浙公网安备 33010602011771号