All Questions
Tagged with deep-learning tensorflow
10,812 questions
0
votes
0
answers
3
views
Unrecognized Data Type
I am follwoing the training in the (https://www.bing.com/videos/riverview/relatedvideo?q=deep+learning+with+keras+tensorflow+freecodecamp&&view=riverview&mmscn=mtsc&mid=...
0
votes
0
answers
25
views
KeyError raised at input layer when trying to build a model with 2 inputs
KeyError: "Exception encountered when calling Functional.call().\n\n\x1b[1m140112707155856\x1b[0m\n\nArguments
received by Functional.call():
\n • inputs={'input_1': 'tf.Tensor(shape=(None, 256,...
- 11
-1
votes
0
answers
14
views
How to handle varying Feature Dimensions in Graph Neural Networks training?
I have a question about how to handle datasets with different feature dimensions when training Graph Neural Networks (GNNs). For example, in one dataset (Dataset A), the node features have a dimension ...
-1
votes
0
answers
27
views
Tensorflow model takes so much RAM in google colab
When i try to train this model and this model doenst even have many trainable parameters, in google colab it crashes because it uses all the ram, i have a dataset of mp3 files, each mp3 file is 128 ...
1
vote
0
answers
40
views
InvalidArgumentError, Deep Learning with Python, Example 10.2.3
I'm trying example 10.2.3 from the book Deep Learning with Python by François Chollet. I'm getting an error on the line history = model.fit(...) using Tensorflow 2.17. However, I don't get an error if ...
- 10.1k
0
votes
0
answers
23
views
Missing a required argument: 'dec_input' in Transformer Model
I am busy with a forecasting model, and have turned to Transformers to see if they will be able to perform better than other sequence models.
I keep getting the error:
TypeError ...
- 49
-2
votes
0
answers
24
views
keep getting TypeError: load_model() missing 1 required positional argument: 'filepath' in tf version 2.15.0
I'm trying to load a model to use to for predictions, but it seems the model failed to load
my tf version: tensorflow 2.15.0
model = load_model('model.h5')
img_path = "app\model\test.jpg"
...
-2
votes
0
answers
40
views
InvalidArgumentError: only one input size may be -1, not both 0 and 1 in TensorFlow model during prediction with single image input
I'm working on a TensorFlow model for face recognition, where I preprocess images, generate embeddings, and then store them in a CSV database. The model works fine when predicting on a batch of images ...
- 1
0
votes
0
answers
24
views
Understanding the output of a simple neural network in TensorFlow Playground
I am learning about neural networks, so I started experimenting with Tensorflow playground.
to understand the basics I set all parameters manually and didn't train the model afterward. specifically I ...
- 67
0
votes
0
answers
26
views
Autoencoder Training Loss Doesn't Decrease Despite Cloned Code and Dataset
My first post on stackoverflow so thanks for any responses!
I'm learning about anomaly detection using autoencoders and found a useful looking github repo notebook link here
I've cloned the repo to my ...
- 31
0
votes
0
answers
22
views
Attribute error with ELMo embedding for CNN model
Having an issue with implementing ELMo embedding with a CNN model. I originally has some tokenization and padding but removed these steps as I am not sure they are needed when using pre-trained ...
- 1
0
votes
0
answers
31
views
Tensorflow GPU crashing after first epoch
I am training a neural network model and when running the code :
history = model.fit(
X_train, y_train_encoded,
epochs=20,
batch_size=32,
validation_data=(X_val, y_val_encoded),
)
The ...
- 465
0
votes
0
answers
17
views
Project a boolean mask from max-pooling regions back onto the input tensor
I’m working on implementing a custom max-pooling layer in TensorFlow and need help projecting a boolean mask onto the input tensor to indicate the positions that contributed to the max values in each ...
- 179
0
votes
1
answer
53
views
Multiclass classifier using Keras from 'Deep Learning with Python' yields very different accuracy compared to what's in the textbook
Below is the code for multi class classifier from Chapter 4 in 'Deep Learning with Python' by François Chollet. The textbook mentions this code will yield >95% training accuracy, but my environment ...
- 101
0
votes
0
answers
45
views
Invalid Argument Error in Tensorflow (Keras)
I was trying to run a deep learning project related to lip reading based on this Youtube video.
The entire code is on github.
The developer used the following versions of modules:
opencv-python -4.0....
- 11
0
votes
0
answers
39
views
Tensorflow model weights not loading correctly
i'm trying to load a tensorflow neural network in c++ for a chess engine. the model was trained in python and i'm converting the weights to a binary file, but the dimensions are wrong when loading in ...
-2
votes
1
answer
43
views
Model Always Classifies Images as Cats with High Confidence Despite Hyperparameter Tuning [closed]
I am trying to train a model on images using the code below. My directory structure is as follows:
The PetImages folder, which is approximately 1GB in size, is located next to my main.py script.
...
0
votes
0
answers
55
views
Value Error: expected axis -1 of input shape to have value 444, but received input with shape (None, 708)
I'm trying to train a FNN model for credit card fraud detection. My categorical features are merchant, category, city, and state. I also standardized my numerical features using StandardScaler. I ...
- 1
0
votes
1
answer
59
views
Im trying to run this code: cnn = BatchNormalization(renorm=True)(cnn)
But This error occurs:
ValueError: Unrecognized keyword arguments passed to BatchNormalization: {'renorm': True}.
And I need this "renorm=ture" .
Is there any other method to do so?
I tried ...
- 13
0
votes
1
answer
58
views
How to load a Keras model without importing Keras in a Python desktop app?
I have a trained Keras model saved as model.h5, which I would normally load using keras.models.load_model("model.h5"). I'm currently developing a Python desktop application with a GUI and ...
- 235
0
votes
0
answers
41
views
TensorFlow InvalidArgumentError: Concatenation dimension mismatch in ConcatOp - Shapes do not match
I keep getting this error:
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-50-...
1
vote
0
answers
28
views
How to Control Memory Growth When Using TensorFlow in Multi-Round Training?
I'm facing an issue related to memory growth when using TensorFlow for a multi-round training process. Specifically, I have a model training loop in which I generate training and evaluation data in ...
- 11
0
votes
1
answer
95
views
Low GPU utilization (0-5%) with high memory usage in model training
I'm working on a machine learning project using TensorFlow (version 2.10.1) to train a convolutional neural network (CNN) on sEMG signals. While my model utilizes nearly all of the GPU memory (10.8/12 ...
0
votes
0
answers
37
views
Tensorflow Keras: Running an input through a non-sequential base model without the last activation layer
I have a Transformer-Decoder layer that includes non-sequential flow of inputs with Attention layers looping for 12 times. As below:
def get_model():
input_shape = (n_chans, embed_dim)
input = ...
- 83
0
votes
0
answers
108
views
How to apply concrete dropout during inference time with batch size > 1 in Keras
I am trying to implement the concrete dropout method for a regression task, as described in Gal et al. (2017) (the paper). I am implementing it in R with the new Keras3 R package and a tensorflow ...
0
votes
0
answers
32
views
How to update a sequential retrieval model to accept the categories as a parameter?
I followed the Tensorflow Sequential Retrieval tutorial here. The model currently accepts a list of item IDs preferred by the user like so
# create a model that takes in raw query features
index = ...
- 438
0
votes
1
answer
83
views
summary() function not working in cnn (ValueError: Undefined shapes are not supported.)
I'm trying to make a classification network for IDing pictures from the cifar10 dataset.
When I try to use the summary() function, I keep getting this error.
ValueError ...
0
votes
1
answer
65
views
Unwrapping an intermediate functional layer in Keras
I want to use the AblationCAM method, using Keras. I want to use the AblationCAM method, which requires creating a new model with the input of the original model and the output of the selected layer. ...
0
votes
0
answers
58
views
Arcface model can't be loaded
i'm working on face recognition system where i used arcface as its algortihm, and i download the arcface model from github in this link https://github.com/Martlgap/livefaceidapp/blob/main/model.onnx%...
- 1
0
votes
1
answer
77
views
Key Error when trying to extract layer activation in TensorFlow sequential model
I have a Sequential model that is trained on the MNIST dataset.
After training, I am trying to create a new model to output activations from the hidden ReLU (Dense) layer.
I reshaped the test image ...
1
vote
1
answer
44
views
Custom Encoder and Decoder Layers within Keras Model Show As Unbuilt
I have a subclassed tensorflow.keras.Model Seq2Seq model with custom layers. However, when I try to run a test script to build and compile the model, running model.summary() gives:
Model: "...
- 43
0
votes
1
answer
26
views
Do steps round down when it's fractional?
I have begun experimenting with training machine learning models and encountered some confusion around the concepts of epochs and steps in the training process. While researching online, I came across ...
- 1
0
votes
1
answer
201
views
`TypeError: Unsupported integer size (0)` when attempted to save custom Keras model
I have a subclassed tensorflow.keras.Model Seq2Seq model with custom layers. However when I try to save it via tensorflow.keras.Model.save() method, it throwing the following error:
File "/home/...
- 43
0
votes
0
answers
33
views
Model is unable to overfit, even with a tiny dataset
I'm trying to create a CNN that can predict the position of up to 5 objects. Each point has 4 values: x and y coordinates, a presence value(0 if it's a padding value, 1 if it exists) and a depth value(...
- 1
2
votes
0
answers
26
views
tried changing the output of vae model to satisfy loss function but something doesnt work
I tried to create a VAE model which generally contains a custom loss for which GradientTape() or a class is used for implementation. I didn't want to use these methods and instead tried a workaround ...
0
votes
1
answer
25
views
gradient becomes none after apply mask on trainable variable
When I implement the following code, gradient of x becomes none after apply mask on trainable variable. After removed the mask the gradient is able to be calculated. I am wondering what the reason of ...
- 1
0
votes
1
answer
65
views
Simple Gradient Descent in Python vs Keras
I am practicing neural networks by building my own in notebooks. I am trying to check my model against an equivalent model in Keras. My model seems to work the same as other simple coded neural ...
- 11
0
votes
1
answer
49
views
Model Can't Predict Correctly Even Though Has A Good Classification Report
I have tried to run this model from the link:
https://www.kaggle.com/code/alexfordna/garbage-classification-mobilenetv2-92-accuracy/notebook
When I did it on colab with similar dataset (but smaller, ...
- 1
0
votes
1
answer
57
views
I need to write complex-value neural network in tensorflow but I get an error
I have complex input to into the neural network, and I also need the neural network to have complex weights, but when writing the code, I get the error as below:
---------------------------------------...
- 129
0
votes
0
answers
130
views
Tensorflow 2.1 Keras error, the metric has not yet been built
i was stacking 5 pretrain model sort of like transfer learning.
I was facing issue about The metric has not yet been built error issue and I not sure how to solve it.
i am using tensorflow 2.17 ...
- 15
0
votes
1
answer
102
views
TensorFlow 2.17.0 Error: tf.where() not working as expected after update
After updating TensorFlow to version 2.17.0, I'm encountering an error in a part of my model that previously worked fine. The error occurs when using tf.where() to create a gate based on a probability ...
- 23
0
votes
0
answers
60
views
0.0 loss function while training transformer
I'm trying to complete Kaggle competition
I created some sort of transformer model where I train 2 models on keywords column and on hashtags (which I extracted from text column). Here is a model for ...
- 57
0
votes
0
answers
34
views
FileNotFoundError: pose_cfg.yaml
I am trying to train my DeepLabCut network on some animal videos I have using departmental resources - GPU. I have activated my environment, made sure there are no broken requirements, no matter what ...
0
votes
0
answers
16
views
Tensorflow fit() function: steps_per_epoch = 1 causes oscillations in loss
I have a simple convolutional neural network that takes an input of size (5,5,3). The code of the training is added below. As you can see input is generated randomly and, only a single entry is used ...
- 1
1
vote
0
answers
33
views
How to create graph for higher order derivative in Tensorflow
My target is to forcing gradients to be statistically indistinguishable across tasks in a multi-task model by exposing them into a discriminator (inspired by Adversarial Learning, training weights to ...
- 11
1
vote
0
answers
50
views
Get the output of an intermediate layer in Keras for GradCAM for a subclassed model
I am trying to get the output of an intermediate layer for a resnet-style model that I developed using Keras and TensorFlow. My model consists of nested keras.Model objects. For clarity, I am adding ...
- 61
0
votes
0
answers
32
views
High AUC on training data but incorrect predictions
I am doing a model that have two outputs: 1 categorical and 1 binary.
After training the model, it has a very high accuracy on training data, and low accuracy on validation data. I wanted to see which ...
0
votes
1
answer
71
views
Layer expects 2 input(s), but it received 1 input tensors
I am trying to build model to predict posts likes, the model takes text and content type which is one hot encoded column.
I have made a TensorFlow dataset but when trying to fit the model I got this ...
0
votes
0
answers
35
views
ValueError: Cannot Reshape Tensor When Training ENet Model with Discriminative Loss Function
I’m currently working on a lane detection project using instance segmentation and following this tutorial. I’m attempting to train an ENet model with a discriminative loss function, but I'm ...
0
votes
0
answers
53
views
How to modify tflite model?
Although many model have sigmoid layer, the embedded system sometimes not supported this layer.
So, I want to remove this layer and then call this in my codes.
Could you tell me solution if you know ...
- 1