deep-learning

问题 I am trying to use a keras (version 2.2.50) neural network / sequential model to create a simple agent in a reinforcement learning setting using the reinforcelearn package (version 0.2.1) according to this vignette: https://cran.r-project.org/web/packages/reinforcelearn/vignettes/agents.html . This is the code I use: library('reinforcelearn') library('keras') model = keras_model_sequential() %>% layer_dense(units = 10, input_shape = 4, activation = "linear") %>% compile(optimizer = optimizer

问题 So I am currently trying to build a race recognition program using a convolution neural network. I'm inputting 200px by 200px versions of the UTKFaceRegonition dataset (put my dataset on a google drive if you want to take a look). Im using 8 different classes (4 races * 2 genders) using keras and tensorflow, each having about 700 images but I have done it with 1000. The problem is when I run the network it gets at best 13.5% accuracy and about 11-12.5% validation accuracy, with a loss around

问题 I want to freeze a pre-trained network in Keras. I found base.trainable = False in the documentation. But I didn't understand how it works. With len(model.trainable_weights) I found out that I have 30 trainable weights. How can that be? The network shows total trainable params: 16,812,353. After freezing I have 4 trainable weights. Maybe I don't understand the difference between params and weights. Unfortunately I am a beginner in Deep Learning. Maybe someone can help me. 回答1: A Keras Model

问题 To my understanding, in order to update model parameters through gradient descend, the algorithm needs to calculate at some point the derivative of the error function E with respect of the output y: dE/dy. Nevertheless, I've seen that if you want to use a custom loss function in Keras, you simply need to define E and you don't need to define its derivative. What am I missing? Each lost function will have a different derivative, for example: If loss function is the mean square error: dE/dy = 2

问题 I am trying to implement the NIMA Research paper by Google where they rate the image quality. I am using the TID2013 data set. I have 3000 images each one having a score from 0.00 to 9.00 df.head() >> Image Name Score 0 I01_01_1.bmp 5.51429 1 i01_01_2.bmp 5.56757 2 i01_01_3.bmp 4.94444 3 i01_01_4.bmp 4.37838 4 i01_01_5.bmp 3.86486 I FOUND the code for loss function given below def earth_mover_loss(y_true, y_pred): cdf_true = K.cumsum(y_true, axis=-1) cdf_pred = K.cumsum(y_pred, axis=-1) emd =

问题 What is the difference between sparse_categorical_crossentropy and categorical_crossentropy ? When should one loss be used as opposed to the other? For example, are these losses suitable for linear regression? 回答1: Simply: categorical_crossentropy ( cce ) uses a one-hot array to calculate the probability, sparse_categorical_crossentropy ( scce ) uses a category index Consider a classification problem with 5 categories (or classes). In the case of cce , the one-hot target may be [0, 1, 0, 0, 0

问题 def __init__(self, **kwargs): self.__dict__.update(self._defaults) # set up default values self.__dict__.update(kwargs) # and update with user overrides self.class_names = self._get_class() self.anchors = self._get_anchors() self.sess = K.get_session() RuntimeError: get_session is not available when using TensorFlow 2.0. 回答1: Tensorflow 2.0 does not expose the backend.get_session directly any more but the code still there and expose for tf1. https://github.com/tensorflow/tensorflow/blob/r2.0

问题 def __init__(self, **kwargs): self.__dict__.update(self._defaults) # set up default values self.__dict__.update(kwargs) # and update with user overrides self.class_names = self._get_class() self.anchors = self._get_anchors() self.sess = K.get_session() RuntimeError: get_session is not available when using TensorFlow 2.0. 回答1: Tensorflow 2.0 does not expose the backend.get_session directly any more but the code still there and expose for tf1. https://github.com/tensorflow/tensorflow/blob/r2.0

问题 I want to build an LSTM based neural network which takes two kinds of inputs and predicts two kinds of outputs. A rough structure can be seen in following figure.. The output 2 is dependent upon output 1 and as described in answer to a similar question here, I have tried to implement this by setting the initial state of LSTM 2 from hidden states of LSTM 1. I have implemented this using tensorflow using following code. import tensorflow as tf from tensorflow.keras.layers import Input from

问题 I want to build an LSTM based neural network which takes two kinds of inputs and predicts two kinds of outputs. A rough structure can be seen in following figure.. The output 2 is dependent upon output 1 and as described in answer to a similar question here, I have tried to implement this by setting the initial state of LSTM 2 from hidden states of LSTM 1. I have implemented this using tensorflow using following code. import tensorflow as tf from tensorflow.keras.layers import Input from