Category "tensorflow"

TF-Agents _action_spec: how to define the correct shape for discrete action space?

Scenario 1 My custom environment has the following _action_spec: self._action_spec = array_spec.BoundedArraySpec( shape=(highestIndex+1,), dtype=np.

How to utilize Yolo on high resolution images 8k

I have recently started working in this field. And currently the requirement is to train Yolov3 on a custom dataset where images are of 8k resolution. Is there

ImportError: python3.8/site-packages/tensorflow/python/profiler/internal/_pywrap_traceme.so: failed to map segment from shared object

When I import from tensorflow.keras.preprocessing import image in a single python file it works perfectly. Even in python interpreter console it is imported suc

AttributeError: 'MapDataset' object has no attribute 'client_ids' in tensorflow_federated TFF

I'm trying to test a compression technique in federated learning with non-IID using this API tff.simulation.datasets.build_single_label_dataset(), following the

Why do I get this error while calling predict in Keras?

I'm a newbie to Tensorflow, I've done many models but today when calling predict I get this error : ValueError: Exception encountered when calling layer "sequen

Invalid Argument Error / Graph Execution Error

I'm having multiple errors while running this VGG training code (code and errors shown below). I don't know if its because of my dataset or is it something else

How to use CPU only for Embedding?

I need to avoid this error: tensorflow.python error.framework.errors_impl.InternalError: Failed copying input tensor from /job:localhost/replica:0/task:0/device

Labels -1, 0 and 1 for classification in Tensorflow

I am trying to write a model that outputs a vector of length N consisting of labels -1,0 and 1. Each of the labels depicts one of three decisions for the system

how to make DataFlow from CSV in googleDrive to tf DataSet - in Colab

according to the instructions in Colab I could get buffer & even take a pd.DataFrame from it (file is just example)... # ... authentification file_id =

WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train

I am trying to run a yolov4 + DeepSORT object tracker on tensorflow. However, when I attempt to run save_model.py to convert the darknet weights of yolov4 to a

Tensorflow: Create the torch.gather() equivalent in tensorflow

I want to replicate the torch.gather() function in TensorFlow 2.X. I have a Tensor A (shape: [2, 4, 3]) and a corresponding Index-Tensor I (shape: [2,2,3]). Usi

ValueError: `logits` and `labels` must have the same shape

I'm trying to use Imagenet V2 with transfer-learning for multiclass classification (6 classes), but getting the following error. Can anyone please help? ValueEr

Error when loading a custom layer from config

I have a custom preprocessing layer which basically takes the input and applies the preprocessing function of a pretrained network coming from tensorflow.keras.

How to run these Coral AI models inference in a computer rather than on the TPU?

I have the Coral AI usb TPU and I have succesfully run the Getting Started example, deploying the already compiled / trained example model (image classification

tf.data pipeline from large numpy arrays for a multiple input, multiple output Keras model and distributed training

This question relates to the optimal setup for a multiple-input multiple-output Keras (Tensorflow) model given corresponding numpy arrays. For example, suppose

DatasetNotFoundError: Dataset smartwatch_gestures not found

I need to use the smartwatch_gestures from Tensorflow datasets and here is my code: pip install --upgrade tfds-nightly import tensorflow_datasets as tfds impor

Could not find a version that satisfies the requirement tensorflow - python3.9 64bit

I'm trying to use Tensorflow for some federated learning purposes, but I can't successfully install it using pip. pip install tensorflow Error message I get is

Tensorflow autodiff with respect to matrix entry

In the following code, the Jacobian I get is None. Why is that? a1 = tf.constant(2.0) a2 = tf.constant(1.5) with tf.GradientTape(persistent=True) as tape:

TensorFlowLite tensor with type UINT8 and a Java object of type [[F (which is compatible with the TensorFlowLite type FLOAT32)

I was creating a mobile app that can recognize images using flutter and I got this runtime error when testing the app. Caused by: java.lang.IllegalArgumentExcep

ValueError: Data cardinality is ambiguous (x sizes: 60000 y sizes: 10000 Make sure all arrays contain the same number of samples.)

I'm using mnist dataset for my project on VsCode IDE. Following is the complete code. what is it that I'm doing wrong and how can I solve this error? # Import L