def neural_net_keep_prob_input(): """ Return a Tensor for keep probability : return: Tensor for keep probability. """ # TODO: Implement Function return tf.placeholder(tf.float32, name='keep_prob') """ DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE """ tf.reset_default_graph() tests.test_nn_image_inputs(neural_net_image_input) tests.test_nn_label_inputs(neural_net_label_input) tests.test_nn_keep_prob_inputs(neural_net_keep_prob_input) # ### Convolution and Max Pooling Layer # Convolution layers have a lot of success with images. For this code cell, you should implement the function `conv2d_maxpool` to apply convolution then max pooling: # * Create the weight and bias using `conv_ksize`, `conv_num_outputs` and the shape of `x_tensor`. # * Apply a convolution to `x_tensor` using weight and `conv_strides`. # * We recommend you use same padding, but you're welcome to use any padding. # * Add bias # * Add a nonlinear activation to the convolution. # * Apply Max Pooling using `pool_ksize` and `pool_strides`. # * We recommend you use same padding, but you're welcome to use any padding. # # **Note:** You **can't** use [TensorFlow Layers](https://www.tensorflow.org/api_docs/python/tf/layers) or [TensorFlow Layers (contrib)](https://www.tensorflow.org/api_guides/python/contrib.layers) for **this** layer, but you can still use TensorFlow's [Neural Network](https://www.tensorflow.org/api_docs/python/tf/nn) package. You may still use the shortcut option for all the **other** layers.
def neural_net_keep_prob_input(): """ Return a Tensor for keep probability : return: Tensor for keep probability. """ # TODO: Implement Function prob = tf.placeholder(tf.float32, name='keep_prob') return prob """ DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE """ tf.reset_default_graph() tests.test_nn_image_inputs(neural_net_image_input) tests.test_nn_label_inputs(neural_net_label_input) tests.test_nn_keep_prob_inputs(neural_net_keep_prob_input) # ### 卷积和最大池化层 # # 卷积层级适合处理图片。对于此代码单元,你应该实现函数 `conv2d_maxpool` 以便应用卷积然后进行最大池化: # # * 使用 `conv_ksize`、`conv_num_outputs` 和 `x_tensor` 的形状创建权重(weight)和偏置(bias)。 # * 使用权重和 `conv_strides` 对 `x_tensor` 应用卷积。 # * 建议使用我们建议的间距(padding),当然也可以使用任何其他间距。 # * 添加偏置 # * 向卷积中添加非线性激活(nonlinear activation) # * 使用 `pool_ksize` 和 `pool_strides` 应用最大池化 # * 建议使用我们建议的间距(padding),当然也可以使用任何其他间距。