# Questions tagged [pytorch]

For conceptual questions that somehow involve the PyTorch library, but note that programming questions are off-topic here.

97 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
71 views

### How are partial derivatives calculated in a computational graph?

I am trying to understand how are partial derivatives calculated in a computational graph. I understand reasoning behind computational graphs and I am bold enough to say I understand how they work, at ...
• 131
2k views

### What is the fundamental difference between max pooling and adaptive max pooling used in PyTorch

PyTorch provides max pooling and adaptive max pooling. Both, max pooling and adaptive max pooling, is defined in three dimensions: 1d, 2d and 3d. For simplicity, I am discussing about 1d in this ...
• 3,531
130 views

### Reverse Process in Diffusion Model Doesn't Return Original Image

I am attempting to program a Denoising Diffusion Model based on the one introduced in the article by Ho et al. (2020). However, I have run into issues while testing the reverse diffusion process. ...
27 views

### How to create a loss function that penalizes duplicate indices in the output tensor?

We're working on a sequence-to-sequence problem using pytorch, and are using cross-entropy to calculate the loss when comparing the output sequence to the target sequence. This works fine and ...
• 121
200 views

### What is an "additional channel dimension" contain in batch normalization?

Consider the following explanations regarding batch normalization layers in PyTorch #1: one dimensional batch normalization class torch.nn.BatchNorm1d(.........) Applies Batch Normalization over a 2D ...
• 3,531
436 views

### Positional Encoding in Transformer on multi-variate time series data hurts performance

I set up a transformer model that embeds positional encodings in the encoder. The data is multi-variate time series-based data. As I just experiment with the positional encoding portion of the code I ...
• 121
27 views

### Is there any closed form analytical expression to represent fractional max pooling?

There are Nineteen types of pooling layers in PyTorch. Almost all of the layers are provided with corresponding analytical formulae. But analytical formulae are not provided for the fractional max-...
• 3,531
274 views

### Is there any animation that illustrates the "fold" and "unfold" operations of convolutional layers?

There are fourteen convolution layers in PyTorch. Among them six are related to convolution, another six are related to transposed convolution. The remaining two are fold and unfold operations. The ...
• 3,531
176 views

### How will the filter size affect the transpose convolution operation?

After a series of convolutions, I am up-sampling a compressed representation, I was curious what is the methodology I should follow to choose an optimum kernel size for up-sampling. How will the ...
• 41
180 views

### Why does GAN loss converge to log(2) and not -log(2)?

In Goodfellow's paper, he says: Hence, by inspecting Eq. 4 at $D^*_G (\mathbf{x}) = \frac{1}{2}$, we find $C(G) = \log \frac{1}{2}+ \log \frac{1}{2} = − \log 4$. To see that this is the best ...
85 views

### Why does the BatchNormalization layer produce different outputs during training and inference?

I modified resnet50 architecture to get a regression network. I just add batchnorm1d and ReLU layers just before the fully connected layer. During the training, the output of batchnorm1d layer is ...
• 141
697 views

### How can I train YOLO with the COCO dataset?

I am trying to implement the original YOLO architecture for object detection, but I am using the COCO dataset. However, I am a bit confused about the image sizes of COCO. The original YOLO was trained ...
1 vote
33 views

### How can an MLP be implemented with convolutional layers?

I am studying the architecture of the network pointnet, specifically the MLPs stages of the pipeline highlighted in red in the following image (taken from the author page here): It is strange to find ...
1 vote
29 views

### Why would increasing layers in PyTorch Transformer significantly increase loss?

I have a simple torch.nn.Transformer module for machine translation on the Multi30k dataset. It performs pretty well (32.2 Bleu score) but I looked at scaling up ...
1 vote
21 views

### dropout as the final layer or in every layer to avoid underfitting/overfitting

I am training a Dense neural network where I am having input as a 3x3 matrix, and predicting the eigenvalues of that matrix. Initially, I was having num_samples = 2000, so my model was not able to ...
1 vote
33 views

### Periodical fluctuations in loss curves

I am training a neural network (specifically a GRU based architecture but I think this is not too relevant for the question). My loss curves, especially the training loss but also the validation loss, ...
1 vote
134 views

### What is wrong with my PyTorch model training on CIFAR10?

I am training a ResNet model on CIFAR10 dataset. For the training subset, I selected a random 1% of the train data from the default train/test split. For the test subset I used the whole default test ...
• 11
1 vote
115 views

### Higher validation loss after using Dropout

I’m working on a classification problem (500 classes). My NN has 3 fully connected layers, followed by an LSTM layer. I use nn.CrossEntropyLoss() as my loss ...
1 vote
226 views

### Where can I get Imagenet test dataset labels for evaluation

I have the imagenet train, validation and test set. I have been able to assign each image in the validation set into its respective class folders with the help of some online resources. However, for ...
1 vote
156 views

### How can I produce crossbred images out of two datasets?

I'm very new to AI and deep learning. So my question is going to be very basic. I'm trying to understand which approach I would need to use to cross-breed set of images. Let's say I'm having dataset ...
1 vote
138 views

### How to compute the loss for a sequence labeling task without the Softmax distribution?

For a sequence labeling task (NER), we compute the loss by passing the softmax distribution of the classes (e.g. vocabulary) with the gold label to the loss function (...
• 123
1 vote
322 views

### Multi label classification on non binary labels with pytorch

I am working on a project consisting of medical images and a huge dataset of multi-label and non-binary labels/outcomes ( sex, blood pressure, age and 40 more ). Would be the best approach to hard ...
1 vote
79 views

### Are there any benefits of adding attention to linear layers?

Is attention useful only in transformer/convolution layers? Can I add it to linear layers? If yes, how (on a conceptual level, not necessarily the code to implement the layers)?
• 13
1 vote
2k views

### Deep Q-Learning with multiple discrete actions

I am working on a DQN project with Pytorch, where I should choose multiple discrete actions, each in a range, say, (0, 15). I am wondering how I can model it, such ...
• 11
1 vote
72 views

### Batch normalization for multiple datasets?

I am working on a task of generating synthetic data to help the training of my model. This means that the training is performed on synthetic + real data, and tested on real data. I was told that batch ...
• 221
1 vote
471 views

### Is there any gain by lazy initialization of weights, biases and number of input channels for a convolution operation?

The basic layers for performing convolution operations 1,2,3 in PyTorch are ...
• 3,531
1 vote
143 views

### How can I model any structure for a neural network?

Hello I am currently doing research on the effect of altering a neural network's structure. Particularly I am investigating what affect would putting a random DAG (directed acyclic graph) in the ...
1 vote
59 views

### What's the best way to take a list of lists as DQN input?

I have my own environment for the DQN algorithm. In my environment, the state space is represented by a list of lists, where each sublist can be of different lengths. In my case, the length of the ...
• 11
1 vote
521 views

### Why does the VAE using a KL-divergence with a non-standard mean does not produce good images?

I know I can make a VAE do generation with a mean of 0 and std-dev of 1. I tested it with the following loss function: ...
• 53
1 vote
215 views

### variational auto encoder loss goes down but does not reconstruct input. out of debugging ideas

My variational autoencoder seems to work for MNIST, but fails on slightly "harder" data. By "fails" I mean there are at least two apparent problems: Very poor reconstruction, for ...
• 719
1 vote
35 views

### is it ok to take random actions while training a3c as in below code

i am trying to train an A3C algorithm but I am getting same output in the multinomial function. can I train the A3C with random actions as in below code. can someone expert comment. ...
• 121
1 vote
96 views

### Is it good practice to save NLP Transformer based pre-trained models into file system in production environment

I have developed a multi label classifier using BERT. I'm leveraging Hugging Face Pytorch implementation for transformers. I have saved the pretrained model into the file directory in dev environment. ...
• 141
1 vote
365 views

### Classification or regression for deep Q learning

DQN implemented at https://github.com/PacktPublishing/PyTorch-1.x-Reinforcement-Learning-Cookbook/blob/master/Chapter07/chapter7/dqn.py uses the mean square error loss function for the neural network ...
• 325
1 vote
76 views

### In layman's terms, what is stochastic computation graph?

I'm going through the distributions package on PyTorch's documentation and came across the term stochastic computation graph. In layman's terms, what is it?
• 43
1 vote
81 views

### Benchmarking SAC on Pybullet

So far I have seen TD3 and DDPG benchmarks on Pybullet environments, but I am looking for SAC benchmarks on Pybullet too, anyone can help?
• 151
1 vote
215 views

### How can I use GPT-2 to modify seed text of one form into a different form (LENGTH INVARIANT) whilst retaining meaning?

I am currently starting a research project whereby I am trying to convert text of one form into another. i.e. If I were to write a seed sentance of the form "Scientists have finally achieved the ...
1 vote
341 views

### Replace epsilon greedy action selection and the standard DQN by an Independent Gaussian Noise Network Model

Here is my code Recently, I solved the game of Atari Breakout using a classic DQN model. The convergence of the mean reward slowly improved during three days. I was interested in learning a method ...
• 161
1 vote
202 views

### Is it possible to do token classification using a model such as GPT-2?

I am trying to use PyTorch's transformers as a part of a research project to do sentiment analysis of several types of review data (laptop and restaurant). To do this, my team is taking a token-...
• 153
1 vote
103 views

### time-series prediction : loss going down, then stagnates with very high variance

I am trying to design a model based on LSTM cells to do time-series prediction. The ouput value is an integer in [0,13]. I have noticed that one-hot encoding it and ...
• 111
1 vote
273 views

### RealNVP gives wrong probabilities

I am trying to use RealNVP with some data I have (the input size is a 1D vector of size 22). Here is the link to the RealNVP paper and here is a nice, short explanation of it (the paper is pretty long)...
• 149
1 vote
178 views

### Why is my variational auto-encoder generating random noise?

This is my first variational autoencoder. Background info: I am using the MNIST digits dataset. The model is created and trained in PyTorch. The model is able to get a reasonably low loss, but the ...
• 11
1 vote
28 views

### How can I train a neural network to find the hyper-parameters with which the data was generated?

I have 10000 tuples of numbers (x1, x2, y) generated from the equation: y = np.cos(0.583 * x1) + np.exp(0.112 * x2). I want to ...
• 149
1 vote
81 views

### Why are the current means and the old ones the same in this implementation of Elastic Weight Consolidation?

I'm trying to re-implement Elastic Weight Consolidation (EWC) as outlined in this paper. As a reference, I am also using this Github repository (another implementation). My model/idea is pretty ...
• 111
1 vote
23 views

### Can Grad CAM feature maps be used for Training?

I am trying to recreate the architecture of the following paper: https://arxiv.org/pdf/1807.03058.pdf Can someone help me in explaining how are the feature maps coming out of the output of GradCam ...
• 11
1 vote
215 views

### Super Resolution CNN generates black dots on output images

I have been trying to train a CNN for the super-resolution task based on the work of Dong et al., 2015 [1]. The network structure built in PyTorch is as follows: ...
• 173
1 vote
20 views

### Limits for a bottleneck

I have some 64x64 pixels frames from a (simulated) video, with a spaceship moving on a fixed background. The spaceship moves in a straight line with constant velocity from left to right (along the x-...
1 vote
388 views

### How to properly optimize shared network between actor and critic?

I'm building an actor-critic reinforcment learning algorithm to solve environments. I want to use a single encoder to find representation of my environment. When I share the encoder with the actor ...
• 183
1 vote
116 views

### How to make episode ending "good" in reinforcement learning?

TL;DR: read the bold. The rest are details I am trying to implement Reinforcement Learning:An Introduction, section 13.5 myself: on OpenAi's cartpole The algorithm seems to be learning something ...
• 719