Recent questions tagged TensorFlow

0 votes

678 views

1 answer

tensorflow - CTC Loss InvalidArgumentError: sequence_length(b) <= time

I am running into this error while trying to use tf.nn.ctc_loss through keras (ctc_batch_cost): InvalidArgumentError ... is sequence_length(b)? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

628 views

1 answer

tensorflow - ImportError: cannot import name 'abs'

I got problem while doing object detection using tensorflow-gpu I was follwing the youtube tutorials :https://www. ... 'abs' is. Please help See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

768 views

1 answer

tensorflow - Average weights in keras models

How to average weights in Keras models, when I train few models with the same architecture with different ... each one separately. Thanks! See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.0k views

1 answer

tensorflow - How to disable dropout while prediction in keras?

I am using dropout in neural network model in keras. Little bit code is like model.add(Dropout(0.5)) model ... Dropout while testing in keras?? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

603 views

1 answer

tensorflow - InvalidArgumentError: The node has inputs from different frames

I was playing around with Tensorflow and ran into a problem with this code: def process_tree_tf(matrix, weights, idxs ... . Thank you very much! See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

549 views

1 answer

tensorflow - Sequence to Sequence - for time series prediction

I've tried to build a sequence to sequence model to predict a sensor signal over time based on its first few inputs ... ) What am I doing wrong? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

tensorflow - ValueError: No gradients provided for any variable

I'm facing a trouble with tensorFlow. Executing the following code import tensorflow as tf import input_data ... ), dtype=float32). See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

925 views

1 answer

tensorflow - Are tf.layers.dense() and tf.contrib.layers.fully_connected() interchangeable?

I am used to using tf.contrib.layers.fully_connected to build a fully connected layer. Recently I ran into tf. ... , producing the same output? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

560 views

1 answer

tensorflow - What are the advantages of using tf.train.SequenceExample over tf.train.Example for variable length features?

Recently I read this guide on undocumented featuers in TensorFlow, as I needed to pass variable length sequences ... it bear any consequence? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

513 views

1 answer

tensorflow - What are the advantages of using tf.train.SequenceExample over tf.train.Example for variable length features?

Recently I read this guide on undocumented featuers in TensorFlow, as I needed to pass variable length sequences ... it bear any consequence? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

539 views

1 answer

tensorflow - What are the advantages of using tf.train.SequenceExample over tf.train.Example for variable length features?

Recently I read this guide on undocumented featuers in TensorFlow, as I needed to pass variable length sequences ... it bear any consequence? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

606 views

1 answer

tensorflow - What are the advantages of using tf.train.SequenceExample over tf.train.Example for variable length features?

Recently I read this guide on undocumented featuers in TensorFlow, as I needed to pass variable length sequences ... it bear any consequence? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

665 views

1 answer

tensorflow - How to print the result of `tf.data.Dataset.from_tensor_slices`?

I'm a new to tensorflow, so I try every single command appeared in the official document. How ... output_classes # print dataset.output_shapes See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

tensorflow - How do you convert a .onnx to tflite?

I've exported my model to ONNX via: # Export the model torch_out = torch.onnx._export(learn.model, # model being ... = '1.0.0.dev20181029' See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

550 views

1 answer

tensorflow - What is the mathematics behind the "smoothing" parameter in TensorBoard's scalar graphs?

I presume it is some kind of moving average, but the valid range is between 0 and 1. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

716 views

1 answer

tensorflow - validation during training of Estimator

With the TensorFlow r1.3 monitors are deprecated: "2016-12-05", "Monitors are deprecated. Please use tf. ... of validation monitor with hooks? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

682 views

1 answer

tensorflow - ValueError: Trying to share variable rnn/multi_rnn_cell/cell_0/basic_lstm_cell/kernel

This it the code: X = tf.placeholder(tf.float32, [batch_size, seq_len_1, 1], name='X') labels = tf. ... using a GPU version of tensorflow. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

815 views

1 answer

tensorflow - How does the Flatten layer work in Keras?

I am using the TensorFlow backend. I am applying a convolution, max-pooling, flatten and a dense layer ... be appreciated with actual values. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

656 views

1 answer

tensorflow - How to deal with multi step time series forecasting in multivariate LSTM in keras

I am trying to do multi-step time series forecasting using multivariate LSTM in Keras. Specifically, I have two ... , green is the prediction) See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

971 views

1 answer

tensorflow - What is the definition of a non-trainable parameter?

What is the definition of non-trainable parameter in a model? For example, while you are building your own model, ... be the reason behind it? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

550 views

1 answer

tensorflow - Replace Validation Monitors with tf.train.SessionRunHook when using Estimators

I am running a DNNClassifier, for which I am monitoring accuracy while training. monitors.ValidationMonitor from contrib ... much in advance. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

591 views

1 answer

tensorflow - What do the options in ConfigProto like allow_soft_placement and log_device_placement mean?

We see this quite often in many of the TensorFlow tutorials: sess = tf.Session(config=tf. ... and log_device_placement mean? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

627 views

1 answer

tensorflow - How to average summaries over multiple batches?

Assuming I have a bunch of summaries defined like: loss = ... tf.scalar_summary("loss", loss) # ... ... computed on the entire validation set? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

779 views

1 answer

tensorflow - Keras deep learning model to android

I'm developing a real-time object classification app for android. First I created a deep learning model ... android for image classification. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

887 views

1 answer

tensorflow - Choosing number of Steps per Epoch

If I want to train a model with train_generator, is there a significant difference between choosing 10 Epochs with ... is any downside to this See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

612 views

1 answer

tensorflow - How do I find the variable names and values that are saved in a checkpoint?

I want to see the variables that are saved in a TensorFlow checkpoint along with their values. How can I find the ... . Is there any other way? See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

651 views

1 answer

tensorflow - keras tensorboard: plot train and validation scalars in a same figure

So I am using tensorboard within keras. In tensorflow one could use two different summarywriters for train and ... this in keras? Thanks. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

675 views

1 answer

tensorflow - What's the difference between tf.Session() and tf.InteractiveSession()?

In which cases should tf.Session() and tf.InteractiveSession() be considered for what purpose? When I tried to use ... the later one, it worked. See Question&Answers more detail:os...

asked Oct 24, 2021 in Technique[技术] by 深蓝 (71.8m points)

Categories

Just Browsing Browsing

Most popular tags