Python API Guides

  (仅记录日常用到的api)

TensorFlow API 树 (Python)

• Tensor转换：　 Ref
  • 生成tensor
    • tf.string_to_number
    • tf.to_double
    • tf.to_float
    • tf.to_bfloat16
    • tf.to_int32
    • tf.to_int64
    • tf.cast
  • tensor形状op
    • tf.shape
    • tf.size
    • tf.rank
    • tf.reshape
    • tf.squeeze
    • tf.expand_dims
  • 切片和插入op
    • tf.slice
    • tf.split
    • tf.pad
    • tf.concat
    • tf.transpose
• 断言和布尔检查：　 Ref Defined in tensorflow/python/ops/check_ops.py
• Graphs运作：　 Ref
  • 会话管理
    • tf.Session Defined in tensorflow/python/client/session.py
    • tf.InteractiveSession Defined in tensorflow/python/client/session.py.
    • tf.get_default_session Defined in tensorflow/python/framework/ops.py.
  • 错误类和方便功能
    • tf.OpError Defined in tensorflow/python/framework/errors_impl.py.
• 常量、序列和随机变量：　 Ref
  • 生成常量tensor
    • tf.zeros
    • tf.zeros_like
    • tf.ones
    • tf.ones_like
    • tf.fill
    • tf.constant
  • 生成序列op
    • tf.linspace
    • tf.range
  • 生成随机tensor
    • tf.random_normal
    • tf.truncated_normal
    • tf.random_uniform
    • tf.random_shuffle
• 构建网络层：　 Ref
  • 高级构建op
    • tf.contrib.layers.avg_pool2d
    • tf.contrib.layers.batch_norm
    • tf.contrib.layers.convolution2d
    • tf.nn.conv2d_transpose
    • tf.contrib.layers.convolution2d_transpose
    • tf.nn.dropout
    • tf.contrib.layers.fully_connected
    • tf.contrib.layers.max_pool2d
    • tf.nn.relu
    • tf.nn.relu6
    • tf.nn.softmax
    • tf.stack
    • tf.contrib.layers.unit_norm
  • 正则化op Defined in tensorflow/contrib/layers/python/layers/regularizers.py.
    • tf.contrib.layers.l1_regularizer
    • tf.contrib.layers.l2_regularizer
  • 初始化op Defined in tensorflow/contrib/layers/python/layers/initializers.py
  • （权重）优化op Defined in tensorflow/contrib/layers/python/layers/optimizers.py
    • tf.contrib.layers.optimize_loss
  • 总结op Defined in tensorflow/contrib/layers/python/layers/summaries.py
    • tf.contrib.layers.summarize_activation
    • tf.contrib.layers.summarize_tensor
    • tf.contrib.layers.summarize_tensors
    • tf.contrib.layers.summarize_collection
    • tf.contrib.layers.summarize_activations
• RNN：　 Ref
• 过程控制：　 Ref
  • 过程控制op
    • tf.identity
    • tf.tuple
  • 逻辑op
    • tf.logical_and
    • tf.logical_not
    • tf.logical_or
    • tf.logical_xor
  • 对照op
    • tf.equal
    • tf.not_equal
    • tf.less
    • tf.less_equal
    • tf.greater
    • tf.greater_equal
    • tf.where
  • 调试op
    • tf.is_finite Defined in tensorflow/python/ops/gen_math_ops.py
    • tf.Assert Defined in tensorflow/python/ops/control_flow_ops.py.
    • tf.Print Defined in tensorflow/python/ops/logging_ops.py.
• 构建graph：　 Ref
  • 核心graph数据结构op Defined in tensorflow/python/framework/ops.py
    • tf.Graph
    • tf.Operation
    • tf.Tensor
  • tensor类型op Defined in tensorflow/python/framework/dtypes.py
    • tf.DType
    • tf.as_dtype
  • Utility函数op Defined in tensorflow/python/framework/ops.py
    • tf.device
    • tf.container
    • tf.name_scope
    • tf.get_default_graph
    • tf.reset_default_graph
  • 自定义op
    • class tf.TensorShape Defined in tensorflow/python/framework/tensor_shape.py.
• 图像：　 Ref
  • 图像调整op
    • tf.image.resize_images
• 输入和读取：　 Ref
  • 占位符op
    • tf.placeholder
    • tf.placeholder_with_default
  • 读取op
    • tf.ReaderBase
    • tf.IdentityReader
    • tf.TFRecordReader
  • 转换成tensor
    • tf.decode_csv　
    • tf.decode_raw
  • 队列op
    • tf.QueueBase
    • tf.FIFOQueue
  • 文件处理op
    • tf.matching_files
    • tf.read_file
    • tf.write_file
  • 流水线输入op
    • tf.train.batch
    • tf.train.maybe_batch
    • tf.train.batch_join
    • tf.train.maybe_batch_join
    • tf.train.shuffle_batch
• 数学计算：　 Ref {Detail} Defined in　tensorflow/python/ops/math_ops.py
  • 算数op
    • tf.add
    • tf.subtract
    • tf.multiply
    • tf.scalar_mul
    • tf.div
    • tf.divide
    • tf.truediv
    • tf.floordiv
    • tf.realdiv
    • tf.truncatediv
    • tf.floor_div
    • tf.truncatemod
    • tf.floormod
    • tf.mod
    • tf.cross
  • 基本数学op
    • tf.add_n
    • tf.abs
    • tf.negative
    • tf.sign
    • tf.square
    • tf.round
    • tf.sqrt
    • tf.exp
    • tf.expm1
    • tf.log
    • tf.log1p
    • tf.ceil
    • tf.floor
    • tf.maximum
    • tf.minimum
    • tf.cos
    • tf.sin
    • tf.tan
    • tf.acos
    • tf.asin
    • tf.atan
  • 矩阵的线代op
    • tf.diag
    • tf.trace
    • tf.transpose
    • tf.eye
    • tf.matrix_diag
    • tf.matrix_transpose
    • tf.matmul
    • tf.norm
    • tf.cholesky
  • 复数op
    • tf.complex
    • tf.conj
    • tf.imag
    • tf.real
  • 降维op
    • tf.reduce_sum
    • tf.reduce_prod
    • tf.reduce_min
    • tf.reduce_max
    • tf.reduce_mean
    • tf.reduce_all
    • tf.reduce_any
  • 切片op
    • tf.segment_sum
    • tf.segment_prod
    • tf.segment_min
    • tf.segment_max
    • tf.segment_mean
    • tf.sparse_segment_sum
    • tf.sparse_segment_mean
  • 序列比较和索引提取op
    • tf.argmin
    • tf.argmax
    • tf.where
    • tf.unique
• 神经网络：　 Ref
  • 激活op
    • tf.nn.relu
    • tf.nn.relu6
    • tf.nn.crelu
    • tf.nn.elu
    • tf.nn.softplus
    • tf.nn.softsign
    • tf.nn.dropout
    • tf.nn.bias_add
    • tf.sigmoid
    • tf.tanh
  • 卷积op
    • tf.nn.convolution
    • tf.nn.conv2d
    • tf.nn.depthwise_conv2d
    • tf.nn.depthwise_conv2d_native
    • tf.nn.separable_conv2d
    • tf.nn.atrous_conv2d
    • tf.nn.atrous_conv2d_transpose
    • tf.nn.conv2d_transpose
    • tf.nn.conv1d
    • tf.nn.conv3d
    • tf.nn.conv3d_transpose
    • tf.nn.conv2d_backprop_filter
    • tf.nn.conv2d_backprop_input
    • tf.nn.conv3d_backprop_filter_v2
    • tf.nn.depthwise_conv2d_native_backprop_filter
    • tf.nn.depthwise_conv2d_native_backprop_input
  • 池化op
    • tf.nn.avg_pool
    • tf.nn.max_pool
    • tf.nn.max_pool_with_argmax
    • tf.nn.avg_pool3d
    • tf.nn.max_pool3d
    • tf.nn.fractional_avg_pool
    • tf.nn.fractional_max_pool
    • tf.nn.pool
  • 归一化op
    • tf.nn.l2_normalize
    • tf.nn.local_response_normalization
    • tf.nn.sufficient_statistics
    • tf.nn.normalize_moments
    • tf.nn.moments
    • tf.nn.weighted_moments
    • tf.nn.fused_batch_norm
    • tf.nn.batch_normalization
    • tf.nn.batch_norm_with_global_normalization
  • 误差损失op
    • tf.nn.l2_loss
    • tf.nn.log_poisson_loss
  • 分类op
    • tf.nn.sigmoid_cross_entropy_with_logits
    • tf.nn.softmax
    • tf.nn.log_softmax
    • tf.nn.softmax_cross_entropy_with_logits
    • tf.nn.sparse_softmax_cross_entropy_with_logits
    • tf.nn.weighted_cross_entropy_with_logits
  • 查找嵌入tensor的value
    • tf.nn.embedding_lookup
    • tf.nn.embedding_lookup_sparse
  • 候选抽样op
    • tf.nn.sampled_softmax_loss
• variable：　 Ref
  • variable
    • tf.Variable
  • variable管理op
    • tf.global_variables
    • tf.local_variables
    • tf.model_variables
    • tf.trainable_variables
    • tf.moving_average_variables
    • tf.global_variables_initializer
    • tf.local_variables_initializer
    • tf.variables_initializer
    • tf.is_variable_initialized
    • tf.report_uninitialized_variables
    • tf.assert_variables_initialized
    • tf.assign
    • tf.assign_add
    • tf.assign_sub
  • variable保存和恢复op
    • tf.train.Saver
    • tf.train.latest_checkpoint
    • tf.train.get_checkpoint_state
    • tf.train.update_checkpoint_state
  • variable共享op
    • tf.get_variable
    • tf.get_local_variable
    • tf.VariableScope
    • tf.variable_scope
    • tf.variable_op_scope
    • tf.get_variable_scope
    • tf.constant_initializer
    • tf.random_normal_initializer
    • tf.truncated_normal_initializer
    • tf.random_uniform_initializer
    • tf.uniform_unit_scaling_initializer
    • tf.zeros_initializer
    • tf.ones_initializer