tensorflow

问题 I am using TensorFlow 2.1.0-dev20191125 Unfortunately I can't compile a simple example with error: "AttributeError: module 'tensorflow.python.framework.ops' has no attribute 'RegisterShape'" My source code: from tensorflow.python.framework import ops as _ops _ops.RegisterShape("GRUBlockCell")(None) Is it looks like incorrectly installed TF ? 回答1: Shape functions for core ops were moved to C++ via REGISTER_OP(...).SetShapeFn(...) . So you may have to first create/register your operation in C++

问题 I'm trying to set seeds and configure keras settings to ensure my experiments are reproducible. When I run the following (based on code in an answer to this question): # Import libraries import numpy as np import pandas as pd import tensorflow as tf from tensorflow.keras.models import load_model from tensorflow.keras.regularizers import l2 # for setting seeds and configuring keras so that experiments are reproducible from numpy.random import seed import random as rn import os from tensorflow

问题 I'm trying to set seeds and configure keras settings to ensure my experiments are reproducible. When I run the following (based on code in an answer to this question): # Import libraries import numpy as np import pandas as pd import tensorflow as tf from tensorflow.keras.models import load_model from tensorflow.keras.regularizers import l2 # for setting seeds and configuring keras so that experiments are reproducible from numpy.random import seed import random as rn import os from tensorflow

问题 It seems that tf.data.Dataset provides a more flexible and more sophisticated alternative to TF queues (subclasses of QueueBase ). (E.g. a TF queue cannot really be reopened after it was closed, see here, here.) (There also seems to be some downsides with Dataset , like that it runs (mostly) on CPU.) I liked the FIFOQueue . Is there some equivalent Dataset ? More specifically, I have one (or multiple) background thread which would get data from somewhere (might not be TF related), and this

问题 It seems that tf.data.Dataset provides a more flexible and more sophisticated alternative to TF queues (subclasses of QueueBase ). (E.g. a TF queue cannot really be reopened after it was closed, see here, here.) (There also seems to be some downsides with Dataset , like that it runs (mostly) on CPU.) I liked the FIFOQueue . Is there some equivalent Dataset ? More specifically, I have one (or multiple) background thread which would get data from somewhere (might not be TF related), and this

问题 When I work with Python, I am used to work in a notebook environment (either Jupyter Notebook locally or Google Colab, where my examples below are tested). I am sometimes omitting the print() command when I am interested in a variable. Example: for each in ['a','b','c']: print(each) This prints a b c as expected. However, for each in ['a','b','c']: each doesn't print anything. If later I type in a new cell each , the notebook prints 'c' , as expected. If I write print(each) , I get c as

问题 Why Tensorflow results are different in Python versions 3.5 (SQL server, machine learning services) and 3.7 (local machine, anaconda)? I found out, it depends on 4 parameters values: dataset size number of epochs number of 1st layer (input) neurons number of 2nd layer (hidden) neurons Here is the example: identical results: dataset size - 50 000 number of epochs - 5/3/2 number of 1st layer (input) neurons - 300 **number of 2nd layer (hidden) neurons - 80% from 1st layer** different results:

问题 Hi i am working on classification model to predict angle of image in python for that i am using Correcting Image Orientation Using Convolutional Neural Networks tutorial with ROTNET. Tutorial is very much explained but training is stuck after 5 to 7 step with angel error 101 but tutorial says we only need to wait for 10 epochs to get an average angle error of 1-2 degrees! but i am not reaching there any one having any idea what is thing i am doing wrong. Or this is happening because i am

问题 I am training on Google Colab with data and model weights loaded from/save to GCP. I am using Keras callbacks to save the weights to GCP. This is what the callback looks like callbacks = [tf.keras.callbacks.ModelCheckpoint(filepath='gs://mybucket/'+ 'savename' + '_loss_{loss:.2f}', monitor='loss', verbose=1, save_weights_only=True, save_freq='epoch')] The training saves the model weights successfully to my GCP bucket, but when I try to load those weights in a new session, the cell just hangs,

问题 I made the following architecture Layer (type) Output Shape Param # ================================================================= embedding_7 (Embedding) (None, 50, 64) 512000 _________________________________________________________________ bidirectional_5 (Bidirection (None, 200) 132000 _________________________________________________________________ dense_9 (Dense) (None, 1) 201 ================================================================= Total params: 644,201 Trainable params: