tensorflow2.0

问题 I'm getting back into python and have been trying out some stuff with tensorflow and keras. I wanted to use the plot_model function and after sorting out some graphviz issues I am now getting this error - TypeError: add_node() received a non node class object: I've tried to find an answer myself but have come up short, as the only answer I found with this error didn't seem to be to do with tf. Any suggestions or alternative ideas would be greatly appreciated. Here's the code and error message

问题 I'm trying to build a CNN + RNN using a pre-trained model from tensorflow-hub: base_model = hub.KerasLayer('https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/4', input_shape=(244, 244, 3) base_model.trainable = False model = Sequential() model.add(TimeDistributed(base_model, input_shape=(15, 244, 244, 3))) model.add(LSTM(512)) model.add(Dense(256, activation='relu')) model.add(Dense(3, activation='softmax')) adam = Adam(learning_rate=learning_rate) model.compile(loss='categorical

问题 I'm trying to build a CNN + RNN using a pre-trained model from tensorflow-hub: base_model = hub.KerasLayer('https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/4', input_shape=(244, 244, 3) base_model.trainable = False model = Sequential() model.add(TimeDistributed(base_model, input_shape=(15, 244, 244, 3))) model.add(LSTM(512)) model.add(Dense(256, activation='relu')) model.add(Dense(3, activation='softmax')) adam = Adam(learning_rate=learning_rate) model.compile(loss='categorical

问题 I'm implementing a custom Layer with the Keras API (working with TF2.0-beta ). I want to use the epoch number in my calculation in order to decay a parameter over time (meaning - in the call() method). I'm used to tf.get_global_step() but understand that TF deprecated all global scopes, and definitely for a good reason. If I had the model instance, I could use model.optimizer.iterations , but I'm not sure how I get the instance of my parent model when I'm implementing a Layer. Do I have any

问题 I am trying to train a Mask RCNN model based on the official MaskRCNN model present here: tensorflow/models. Below are the steps I followed: Created a tfrecord for training and validation. I have checked encoding and decoding of the tfrecords, it is working fine. Set up the config file as below: # my_maskrcnn.yaml train: train_file_pattern: "data/<dataset_name>/train/tfrecords/train.tfrecord-*" batch_size: 2 eval: eval_file_pattern: "data/<data_set_name>/val/tfrecords/val.tfrecord-*" batch

问题 If you execute the following TensorFlow 2.1 code import tensorflow as tf import tensorflow_probability as tfp tf.config.experimental_run_functions_eagerly(True) def get_mnist_data(normalize=True, categorize=True): img_rows, img_cols = 28, 28 (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data() if tf.keras.backend.image_data_format() == 'channels_first': x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols) x_test = x_test.reshape(x_test.shape[0], 1, img_rows

问题 I am trying to modify a non-trainable model variable from a callback on beginning of each epoch. Essentially I would like to have a mechanism similar to the learning rate scheduler (which has built in infrastructure in TF) but applicable to an arbitrary model variable. The code below is a minimum example to show the concept. I am trying to modify the decay variable but it does not work. Apparently the initial value of the variable (1.0) is treated as a constant and folded by the graph and

问题 I am implementing the following architecture in Tensorflow 2.0 Dual Encoder LSTM C and R are sentences encoded into a fixed dimension by the two LSTM's. Then they are passed through a function sigmoid(CMR). We can assume that R and C are both 256 dimensional matrices and M is a 256 * 256 matrix. The matrix M is learned during training. Since I want to train M, I declared M = tf.Variable(shape,trainable = True). But after fitting the model, the values of M are still not changing. How to tell

问题 I am implementing the following architecture in Tensorflow 2.0 Dual Encoder LSTM C and R are sentences encoded into a fixed dimension by the two LSTM's. Then they are passed through a function sigmoid(CMR). We can assume that R and C are both 256 dimensional matrices and M is a 256 * 256 matrix. The matrix M is learned during training. Since I want to train M, I declared M = tf.Variable(shape,trainable = True). But after fitting the model, the values of M are still not changing. How to tell

问题 The Keras' documentation describes here how to write a custom layer by inheriting from the Layer class. Now, I have another custom layer CustomLayer , from which I want to inherit. Let's call my new custom layer CustomLayer2 . I guess that the process of inheriting, even though I will not be inheriting from Layer but from CustomLayer , will be the same described in the linked documentation, but I will also inherit the custom functionality of CustomLayer . Anyway, inside this custom layer