tensorflow2.0

问题 I am training a model in tf.keras with tensorflow 2.0. I am having an issue where my model appears to train successfully, but it is not iterating through the entire dataset. I restructured the code into tensorflow 1.15, and I do not have this issue in tensorflow 1.x. I am following this tutorial for Multiple Input Series. Below are more details: I have a time-series dataset. It is very small so I am able to load it into memory, so I do not need the dataset API. I am windowing the time-series

问题 Following this link, I've been trying to install the tflite-support module using pip. I get the following error: ERROR: Command errored out with exit status 1: command: /usr/local/opt/python/bin/python3.7 -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/private/var/folders/gg/1zr67t6d11lczcdmc7tc3y000000gn/T/pip-install-tfso4suc/tflite-support/setup.py'"'"'; __file__='"'"'/private/var/folders/gg/1zr67t6d11lczcdmc7tc3y000000gn/T/pip-install-tfso4suc/tflite-support/setup.py'"'"';f

问题 Following this link, I've been trying to install the tflite-support module using pip. I get the following error: ERROR: Command errored out with exit status 1: command: /usr/local/opt/python/bin/python3.7 -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/private/var/folders/gg/1zr67t6d11lczcdmc7tc3y000000gn/T/pip-install-tfso4suc/tflite-support/setup.py'"'"'; __file__='"'"'/private/var/folders/gg/1zr67t6d11lczcdmc7tc3y000000gn/T/pip-install-tfso4suc/tflite-support/setup.py'"'"';f

问题 In usual backprop, we forward-prop once, compute gradients, then apply them to update weights. But suppose we wish to forward-prop twice , and backprop through both , and apply gradients only then (skip on first). Suppose the following: x = tf.Variable([2.]) w = tf.Variable([4.]) with tf.GradientTape(persistent=True) as tape: w.assign(w * x) y = w * w # w^2 * x print(tape.gradient(y, x)) # >>None From docs, a tf.Variable is a stateful object, which blocks gradients , and weights are tf

问题 In usual backprop, we forward-prop once, compute gradients, then apply them to update weights. But suppose we wish to forward-prop twice , and backprop through both , and apply gradients only then (skip on first). Suppose the following: x = tf.Variable([2.]) w = tf.Variable([4.]) with tf.GradientTape(persistent=True) as tape: w.assign(w * x) y = w * w # w^2 * x print(tape.gradient(y, x)) # >>None From docs, a tf.Variable is a stateful object, which blocks gradients , and weights are tf

问题 I am starting with Tensorflow 2.0 and trying to implement Guided BackProp to display Saliency Map. I started by computing the loss between y_pred and y_true of an image, then find gradients of all layers due to this loss. with tf.GradientTape() as tape: logits = model(tf.cast(image_batch_val, dtype=tf.float32)) print('`logits` has type {0}'.format(type(logits))) xentropy = tf.nn.softmax_cross_entropy_with_logits(labels=tf.cast(tf.one_hot(1-label_batch_val, depth=2), dtype=tf.int32), logits

问题 The bounty expires in 7 days . Answers to this question are eligible for a +50 reputation bounty. thunder is looking for a more detailed answer to this question: Can you make it working for semantic segmentation? import tensorflow as tf import numpy as np from sklearn.model_selection import train_test_split np.random.seed(4213) data = np.random.randint(low=1,high=29, size=(500, 160, 160, 10)) labels = np.random.randint(low=0,high=5, size=(500, 160, 160)) nclass = len(np.unique(labels)) print

问题 When writing customized tf.keras layers, we have to implement the " call " method, since a object of a class can be called like a function with "()" only(?) if the object has a valid " __call__ " method. while I didn't find something like class tf.keras.model(): def __call__(self, input): return self.call(input) in the keras.model source, how could all this work? 回答1: from keras.models import Model import inspect inspect.getmro(Model) # (keras.engine.training.Model, keras.engine.network

问题 An error is being generated while training a federated model that uses hub.KerasLayer. The details of error and stack trace is given below. The complete code is available of gist https://gist.github.com/aksingh2411/60796ee58c88e0c3f074c8909b17b5a1. Help and suggestion in this regard would be appreciated. Thanks. from tensorflow import keras def create_keras_model(): encoder = hub.load("https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1") return tf.keras.models.Sequential([ hub

问题 An error is being generated while training a federated model that uses hub.KerasLayer. The details of error and stack trace is given below. The complete code is available of gist https://gist.github.com/aksingh2411/60796ee58c88e0c3f074c8909b17b5a1. Help and suggestion in this regard would be appreciated. Thanks. from tensorflow import keras def create_keras_model(): encoder = hub.load("https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1") return tf.keras.models.Sequential([ hub