Welcome to OStack Knowledge Sharing Community for programmer and developer-Open, Learning and Share
Welcome To Ask or Share your Answers For Others

Categories

Recent questions tagged TensorFlow

0 votes
885 views
1 answer
    I am using deep learning library keras and trying to stack multiple LSTM with no luck. Below is my code ... running keras on tensorflow backend See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
842 views
1 answer
    I have windows 10. I have completed installing Tensorflow. It works. It says "Hello Tensorflow!". But it has all ... . But I code for fun. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
514 views
1 answer
    I am trying to train a Tensor-flow js model on images coming in from my web cam. Basically I'm trying ... the predictions are way off (random) See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
705 views
1 answer
    I want to save my trained keras model as .h5 file. Should be straight forward. Short example: #%% import tensorflow as ... to have it as .h5. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
666 views
1 answer
    Any non-zero recurrent_dropout yields NaN losses and weights; latter are either 0 or NaN. Happens for stacked ... from tensorflow.keras imports. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
623 views
1 answer
    Google recently announced the Clould ML, https://cloud.google.com/ml/ and it's very useful. ... requrements significant code modifcation. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
554 views
1 answer
    I'm working on implementing prioritized experience replay for a deep-q network, and part of the specification is ... . Any help is appreciated. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
995 views
1 answer
    I'd like print out the learning rate for each training step of my nn. I know that Adam has an ... this (for visualization in tensorboard) See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
599 views
1 answer
    I'm working on a segmentation problem in Keras and I want to display segmentation results at the end of every ... that with Keras + TensorFlow? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
1.4k views
1 answer
    TensorBoard seems to have a feature to display multiple different runs and toggle them. How can I make multiple ... them to differentiate them? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
695 views
1 answer
    The first arguments in a normal Dense layer is also units, and is the number of neurons/nodes in that layer. A ... the next layer. Am I right? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
675 views
1 answer
    TF Map function supports parallel calls. I'm seeing no improvements passing num_parallel_calls to map. With ... doing it wrong? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
656 views
1 answer
    It seems like the error has occurred in the past in different contexts here, but I'm not dumping the model ... can't pickle _thread.lock objects See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
663 views
1 answer
    I'm trying to debug a somewhat complicated and non-canonical NN architecture. Computing the forward pass is fine ... I'm using it incorrectly. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
1.1k views
1 answer
    For the application, such as pair text similarity, the input data is similar to: pair_1, pair_2. In these ... // _BATCH_SIZE, verbose=1) See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
731 views
1 answer
    I have installed Cuda 10.1 and cudnn on Ubuntu 18.04 and it seems to be installed properly as type nvcc and ... How can I resolve this? Thanks See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
1.0k views
1 answer
    I have a non trivial input pipeline that from_generator is perfect for... dataset = tf.data.Dataset.from_generator ... examples I could follow? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
753 views
1 answer
    I am using keras and tensorflow 1.4. I want to explicitly specify which neurons are connected between two ... but somehow 'ugly' solution) See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
628 views
1 answer
    I am working on a Time Series Forecasting problem using LSTM. The input contains several features, so I am ... am using Tensorflow and Keras. See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
701 views
1 answer
    I need a conditional control flow in my graph. If pred is True, the graph should call an op that updates a ... And how to solve this problem? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
536 views
1 answer
    It is really straightforward to see and understand the scalar values in TensorBoard. However, it's not clear ... =learning_rate).minimize(loss) See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
1.0k views
1 answer
    I have trained fasttext model with Gensim over the corpus of very short sentences (up to 10 words). I know that ... do it well. Any idea? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
1.2k views
1 answer
    I downloaded a retrained_graph.pb and retrained_labels.txt file of a model I trained in Azure cognitive service ... lite-a-tutorial-85b41f53230c See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
602 views
1 answer
    I have a TensorFlow computational graph for a loss tensor L that depends on 2 tf.Variables, A and B. I'd like to ... A fixed. How do I do this? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
610 views
1 answer
    Note : this question was initially asked on github, but it was asked to be here instead I'm having trouble ... problem with tensorflow as well? See Question&Answers more detail:os...
asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)
0 votes
761 views
1 answer
    I have a CRNN fitted model with CTC loss output. I have the prediction and I use keras.backend.ctc_decode to decode it. ... the training part, the final CTC loss was around 0.1...
asked Jan 29, 2021 in Technique[技术] by 深蓝 (71.8m points)
Ask a question:
Welcome to OStack Knowledge Sharing Community for programmer and developer-Open, Learning and Share
Click Here to Ask a Question

...