We’re rewarding the question askers & reputations are being recalculated! Read more.

All Questions

Tagged with
Filter by
Sorted by
Tagged with
0
votes
0answers
11 views

Keras autoencoder model for face recognition is running very slow with bad accuracy

I am working on to create my face recognition model using autoencoder in keras. My dataset is composed of 20 people with 20 images on each person for training and 10 images for each person for ...
0
votes
0answers
10 views

In tensorflow 2, Is there a way to access the validation data predictions?

I am trying to access the validation data predictions of my model after using model.fit(). I know that I can access the losses using tensorboard callback, but I want to be able to access the data and ...
0
votes
0answers
15 views

Need Some Advice on my Actor Critic Stock Agent

I have tweaked an Actor Critic network I found online that learns to trade stock options based on past stock price data and a couple of technical indicators that get added to the dataframe before ...
0
votes
0answers
11 views

Train model to detect new objects - YoloV3

I did this tutorial to train my model to detect hololens. Now, I created a new Pascal Voc dataset of "guitar". I want to take my actual model that detect hololens to detect hololens and guitar. In ...
0
votes
0answers
10 views

Getting weights and biases from a CNN model and saving them into csv file

I have recently built a CNN model for image classification for cifar 10. The model works but i am having trouble to generate weights and biases for each trainable layers (convolution and dense layers) ...
1
vote
0answers
29 views

Keras : Merge two different model output into one

I am working on one deep learning model where I am trying to combine two different model's output : The overall structure is like this : So the first model takes one matrix, for example [ 10 x 30 ] ...
1
vote
0answers
13 views

what is a DT_VARIANT tensor?

The constructor of tf.data.Dataset takes an argument variant_tensor, which is only documented as: A DT_VARIANT tensor that represents the dataset. and in the DatasetV2, we expect subclasses to ...
0
votes
0answers
15 views

how to write accuracy data to TensorBoard?

Please help me? how to write accuracy data to TensorBoard ? how to write accuracy data to TensorBoard ? #--------------------------------------------------------------------------------------------...
2
votes
1answer
21 views

Tensorflow - Nan Cost Values During Training - Tried The Usual Fixes Without Success

I have already checked out these three answers on SO but they didn't really provide a solution for my problem, although maybe it'll help someone here to help me: This one, this one, and this one. I ...
0
votes
0answers
19 views

No bouding boxes create when running my trained model

I have tried to train my model using ssd_mobilenet_v1_coco_11_06_2017 ,ssd_mobilenet_v1_coco_2018_01_28 and faster_rcnn_inception_v2_coco_2018_01_28 and did it successfully however when i tried to run ...
0
votes
0answers
17 views

TensorFlow ValueError: At least two variables have the same name

I am stuck with saving the trained model session using TensorFlow's saved_model.builder.SavedModelBuilder. When I run: builder = tf.saved_model.builder.SavedModelBuilder(model_path) builder....
0
votes
0answers
17 views

int argument must be a string, a bytes-like ofject or a number, not NoneType

Why I'm getting the following error: int() argument must be a string, a bytes-like object or a number, not ´NoneType´ I think I need help figuring out how to convert a typeless variable to a ...
0
votes
0answers
4 views

prepare_attention API of tensorflow 1.0.0 equivalent in tensorflow 1.13.1

What is the equivalent API in tensorflow 1.13.1 for prepare_attention(tf.contrib.seq2seq.prepare_attention) of tensorflow 1.0.0? Thanks!!!
0
votes
0answers
18 views

TensorFlow - tensorflow.python.framework.errors_impl.FailedPreconditionError

I tried to update the following code from TF 1.7 to TF 1.14 : def build(self, input_shape): self.max_length = input_shape[1] self.word_mapping = [x[1] for x in sorted(self.idx2word.items(), ...
1
vote
2answers
36 views

What may be the problem with this cudaGetDevice() failed. Status: cudaGetErrorString symbol not found

I've been having this issue for quite some time now and I can't find a solution, I've tried so many things that I've lost track, but after some research it seems that it might have something to do ...
0
votes
0answers
34 views

AttributeError: 'list' object has no attribute 'logits_dimension'

Code: features = {"lines": np.array(train_lines)} labels = np.array(train_cat) train_input_fn = tf.estimator.inputs.numpy_input_fn( features, labels, shuffle=True, batch_size=16, ...
1
vote
0answers
11 views

When I implement FCNs using MITSceneParsing data, I got this error [TypeError: 'NoneType' object is not subscriptable]

I used MITSceneParsing data when I implement Fully Convolutional Networks. But I got this error [TypeError: 'NoneType' object is not subscriptable]. So anybody knows this reason? import pickle def ...
0
votes
0answers
16 views

Keras - UnboundLocalError: local variable 'batch_index' referenced before assignment

I have created my deep neural network model based on LSTM using Keras on Tensorflow backend. When I call thefit function of my model, getting the UnboundLocalError: local variable 'batch_index' ...
0
votes
0answers
18 views

How to convert Tensorflow 2.0 SavedModel to TensorRT?

I've trained a model in Tensorflow 2.0 and am trying to improve predict time when moving to production (on a server with GPU support). In Tensorflow 1.x I was able to get a predict speedup by using ...
0
votes
1answer
48 views
+100

Error on prediction running keras multi_gpu_model

I've an issue running a keras model on a Google Cloud Platform instance. The model is the following one: n_timesteps, n_features, n_outputs = train_x.shape[1], train_x.shape[2], train_y.shape[1] ...
0
votes
0answers
16 views

Raspberry pi - Tensorflow How to detect in real time only people and counting?

I try to make a camera with a raspberry pi that counts and sends on firebase the number of person exat in the pieces. I followed the tutorial of https://github.com/EdjeElectronics/TensorFlow-Object-...
1
vote
1answer
24 views

Display graph using Tensorflow v2.0 in Tensorboard

Following code using TensorFlow v2.0 import tensorflow as tf a = tf.constant(6.0, name = "constant_a") b = tf.constant(3.0, name = "constant_b") c = tf.constant(10.0, name = "constant_c") d = tf....
0
votes
0answers
14 views

InvalidArgumentError: Failed to create a NewWriteableFile: The filename, directory name, or volume label syntax is incorrect. ; Unknown error

i am trying to train keggle cats and dogs image dataset. i needed to see tensorboard outputs. but it came with an error import numpy as np from tensorflow.keras.datasets import cifar10 from ...
1
vote
0answers
29 views

Distributed training with Keras using multiple GPUs - Segmentation fault (core dumped)

I try to run official example from https://www.tensorflow.org/tutorials/distribute/keras using distributed Keras on two nodes with one GPU each. I run TF_CONFIG='{"cluster": {"worker": ["ip1:2222", "...
0
votes
0answers
15 views

Tensorflow get_single_element not working with tf.data.TFRecordDataset.batch()

I am trying to perform ZCA whitening on a Tensorflow Dataset. In order to do this, I am trying to extract my data from my Dataset as a Tensor, perform the whitening, then create another Dataset after. ...
0
votes
1answer
23 views

Is there support for functional layers api support in tensorflow 2.0?

I'm working on converting our model from tensorflow 1.8.0 to 2.0 but using sequential api's is quite difficult for our current model.So if there any support for functional api's in 2.0 as it is not ...
1
vote
1answer
13 views

Weight Initialization for Mask RCNN without using pretrained weights from Imagenet / COCO

# define the model model = MaskRCNN(mode='training', model_dir='./', config=config) # load weights (mscoco) and exclude the output layers model.load_weights('mask_rcnn_coco.h5', by_name=True, ...
0
votes
1answer
41 views

“Failed to load native TensorFlow runtime.”

So I created a program to load a dataset from TensorFlow and I got an error that I have no idea what it means. My code is: import tensorflow as tf from tensorflow import keras import numpy as np ...
-2
votes
1answer
42 views

Which tensorflow-gpu version is compatible with Python 3.7.3

Actually, I am tired of getting "ImportError: DLL load failed" in Windows 10 CUDA Toolkit 10.0 (Sept 2018) Download cuDNN v7.6.0 (May 20, 2019) / v7.6.4 tensorflow-gpu==1.13.1 / 1.13.2 / 1.14 / 1.15 /...
-1
votes
0answers
25 views

Automatically GPU speed getting slow

I am using NVIDIA GeForce GTX 1660 Ti Max-Q laptop for my python code at starting of the code it is using 30% of gpu so it is processing and executing the code very faster. After some time the speed ...
1
vote
0answers
52 views

Tensorflow 2.0: custom keras metric caused tf.function retracing warning

When I use the following custom metric (keras-style): from sklearn.metrics import classification_report, f1_score from tensorflow.keras.callbacks import Callback class Metrics(Callback): def ...
0
votes
1answer
25 views

got “No module named 'tensorflow.python.platform' ” when try to import tansorflow 2.0

I installed the latest anaconda navigator 1.9.7 (windows 10), and created a new env (python 3.7)in the anaconda navigator interface, then installed jupyter notebook and tensorflow 2.0 package in it. ...
0
votes
1answer
61 views

How to edit the new object-detection-tutorial.ipynb

i want to edit the object_detection_tutorial.ipynb to use my trained model but the tutorial that i followed online had the old tensorflow object detection api i tried using the old ...
0
votes
0answers
12 views

How to enable for GNMT TF code Automatic Mixed Precision for evaluation using Estimator API

I'm trying to run the GNMT TF code on a baremetal system and I've setup the CUDA stack and tensorflow-gpu v1.15. There were a few API changes for Tensorflow from 1.14 to 1.15 but after solving that, I ...
0
votes
1answer
35 views

Catch python exception thrown from TensorFlow

I’m running a python (v 3.6.5) code that is using TensorFlow (v 1.13.2) to perform inference using a trained model (on Windows 8.1). I want to catch (and log) exceptions/errors that are thrown from ...
1
vote
0answers
32 views

Deprecation warnings when using internal Keras library in Tensorflow 1.15.0

I am upgrading our codebase to Tensorflow 1.15.0 (we plan to eventually upgrade to 2.x, but it requires too many changes at the moment). Unfortunately, this version of Tensorflow seems to be plagued ...
0
votes
0answers
13 views

Is there any api for training ASR models in tensorflow

I was wondering if there is a specific high-level api in tensorflow for training ASR models on custom data. If not present, will there be one in the future??
0
votes
1answer
26 views

Custom loss is missing an operation for gradient

I'm not too sure how to deal with this and why I am getting this error. raise ValueError('An operation has `None` for gradient. ' ValueError: An operation has `None` for gradient. Please ...
0
votes
1answer
27 views

Time Series Forecasting in Tensorflow 2.0 - How to predict using the last of the Validation Dataset?

I'm (desperately) trying to figure out Tensorflow 2.0 without much luck so far, but I think I'm close with what I need right now. I've followed the doc here to make a simple network to forecast stock ...
0
votes
0answers
32 views

anaconda env: cupti64_100.dll not found

# output metadata end of epochs print('\nAdding run metadata for epoch ' + str(batch_idx) + '\n') run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE) run_metadata ...
0
votes
0answers
27 views

Keras cant slice model by layer used in loss without outputting it

I got two outputs, and only one of them (x1) is output of model. I want to get 2nd (x2) also, but it is used in loss only. import tensorflow as tf def myloss2(sigma): gtsigma = 0.5 kl = ...
-4
votes
0answers
52 views

Where to start creating neural networks on python

The task is this: we get an array of points in the image (their coordinates and the type of object). the task of the neural network is to give out the actions that we need to perform based on the data ...
1
vote
1answer
39 views

How can I improve the speed of my simple neural network?

I've just started exploring TensorFlow and I'm facing an issue regarding performance. As a starting example, I tried implementing a model to simulate a logic gate. Let's say there are two inputs A and ...
0
votes
1answer
20 views

How to run predictions on image using a pretrained tensorflow model?

I have adapted this retrain.py script to use with several pretraineds model, after training is done this generates a 'retrained_graph.pb' which I then read and try to use to run predictions on an ...
0
votes
0answers
22 views

onnx model to keras conversion [keras2onnx] error

Basically I'm trying to use onnx deep learning model to predict in python 3 with keras(tf backend). I tried to convert onnx model to keras from here but i got this error. Using TensorFlow backend. ...
0
votes
0answers
15 views

Decoding image to run predictions on using a pretrained model in tensorflow

I have adapted this retrain.py script to use with several pretraineds model, after training is done this generates a 'retrained_graph.pb' which I then read and try to use to run predictions on an ...
-1
votes
0answers
7 views

tensorflow and tflearn DLL load failed

when importing tensorflow and tflearn into my program it throws the error "ImportError: DLL load failed: The specified procedure could not be found." is there a way to get python to see it im using ...
0
votes
0answers
16 views

Segmentation fault with tensorboard 1.14

I am using deeplab network. I think it is using tensorflow 1.14 since there are still packages of slim, which is removed from tensorflow 2.0. The python version is always Python 3.6.8 in my case. I ...
2
votes
0answers
25 views

Issues while Generating TFrecords

I am Trying to generate tfrecord file with tensorflow 2.0, at the first I have generated correctly the files, but when I am trying generate them again, python console show an error below: Traceback (...
1
vote
0answers
34 views

tensorflow object detection api evaluation segmentation fault

I have Segmentation fault whenever evaluation starts, no matter I use object_detection/legacy/eval.py script or object_detection/model_main.py. I tried to reinstall tensorflow, protobuf-compiler and ...