tensorflow

问题 I'm new in TensorFlow and I'm trying to create a classifier using Keras. My training data is spitted into two files: - one with training examples, each example is a vector of 64 floats - second with labels, each label is an int within range (0,..,SIZE) (SIZE is 100) and it describes a class. Both files are quire large and I can't fit them into memory so I've used tf.Dataset. I create two Datasets (one for features and one for labels) and them merge them using tf.data.Dataset.zip(). However

问题 I have initialised an Adadelta optimizer in Keras (using Tensorflow backend) and assigned it to a model: my_adadelta = keras.optimizers.Adadelta(learning_rate=0.01, rho=0.95) my_model.compile(optimizer=my_adadelta, loss="binary_crossentropy") During training, I am using a callback to print the learning rate after every epoch: class LRPrintCallback(Callback): def on_epoch_end(self, epoch, logs=None): lr = self.model.optimizer.lr print(K.eval(lr)) However, this prints the same (initial)

问题 Have built a Reinforcement Learning DQN with variable length sequences as inputs, and positive and negative rewards calculated for actions. Some problem with my DQN model in Keras means that although the model runs, average rewards over time decrease, over single and multiple cycles of epsilon. This does not change even after significant period of training. My thinking is that this is due to using MeanSquareError in Keras as the Loss function (minimising error). So I am trying to implement

问题 Have built a Reinforcement Learning DQN with variable length sequences as inputs, and positive and negative rewards calculated for actions. Some problem with my DQN model in Keras means that although the model runs, average rewards over time decrease, over single and multiple cycles of epsilon. This does not change even after significant period of training. My thinking is that this is due to using MeanSquareError in Keras as the Loss function (minimising error). So I am trying to implement

问题 I'm trying to convert single images into it's depthmap , but I can't find any useful tutorial or documentation. I'd like to use opencv, but if you know a way to get the depth map using for example tensorflow, I'd be glad to hear it. There are numerous tutorials for stereo vision but I want to make it cheaper because it's for a project to help blind people. I'm currently using esp32 cam to stream frame by frame and receiving the images on python using opencv. 回答1: Usually, we need a

问题 Basically I only reused code from iris utils and iris pipeline with minor change on serving input: def _get_serve_tf_examples_fn(model, tf_transform_output): model.tft_layer = tf_transform_output.transform_features_layer() feature_spec = tf_transform_output.raw_feature_spec() print(feature_spec) feature_spec.pop(_LABEL_KEY) @tf.function def serve_tf_examples_fn(*args): parsed_features = {} for arg in args: parsed_features[arg.name.split(":")[0]] = arg print(parsed_features) transformed

问题 I have a dir with NumPy array files: bias1.npy, kernel1.npy, bias2.npy, kernel2.npy . How can I build a TF model that uses those arrays as kernels and biases of layers? 回答1: To avoid confusion bias matrix for the consistency of the numpy file is the 2D matrix with one column. This post shows how did I reproduce tf's model based on the numpy weights and biases. class NumpyInitializer(tf.keras.initializers.Initializer): # custom class converting numpy arrays to tf's initializers # used to

问题 I need to be able to deploy a keras model for Tensorflow.js prediction, but the Firebase docs only seem to support a TFLite object, which tf.js cannot accept. Tf.js appears to accept JSON files for loading (loadGraphModel() / loadLayersModel() ), but not a keras SavedModel (.pb + /assets + /variables). How can I attain this goal? Note for the Tensorflow.js portion: There are a lot of pointers to the tfjs_converter, but the closest API function offered to what I'm looking for is the

问题 Currently I can train a LSTM network using one csv file based on this tutorial: https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/ This code generate sliding windows where the last n_steps of the features are saved to predict the actual target (similar to this: Keras LSTM - feed sequence data with Tensorflow dataset API from the generator): #%% Import import pandas as pd import tensorflow as tf from tensorflow.python.keras.models import Sequential,

问题 I've made a simple version of Curve Fever also known as "Achtung Die Kurve". I want the machine to figure out how to play the game optimally. I copied and slightly modified an existing DQN from some Atari game examples that is made with Google's Tensorflow. I'm tyring to figure out an appropriate reward function. Currently, I use this reward setup: 0.1 for every frame it does not crash -500 for every crash Is this the right approach? Do I need to tweak the values? Or do I need a completely