Movatterモバイル変換

Question 1

Advice

0votes

1replies

67views

How to read a large Python project (for example, a project of Deep Learning or Reinforcement Learning)

I've downloaded many Python projects about Reinforcement Learning from Github, but each takes me too much time to read.It's easy to comprehend a simple Python project with only a few *.py files, but ...

Xingrui Zhuang

27

asked23 hours ago

Question 2

-2votes

0answers

35views

Resource specifications or requirements of Vision Language models(llm that is specialized for processing images) [closed]

I’m having difficulty finding the hardware resource specifications for different LLMs and VLMs. The leaderboard at this link — https://huggingface.co/spaces/opencompass/open_vlm_leaderboard — includes ...

G KANISHK SAMURAI

1

askedNov 25 at 13:04

Question 3

Advice

1vote

3replies

76views

Python library recommendation for the implementation of a neural network modification algorithm

I want to implement in python some algorithms from a paper that allow for a pre-trained neural network to be modified (adding or removing neurons or layers) conserving (theoretically) the outputs of ...

Rubén Sales Castellar

1

askedNov 21 at 9:50

Question 4

1vote

0answers

67views

Should I use torch.inference_mode() in a prediction method even when using model.eval()? [duplicate]

I'm following the book "Deep Learning with PyTorch Step By Step" and I have a question about the predict method in the StepByStep class (from this repository: GitHub).The current ...

Matteo

93

askedNov 4 at 12:43

Question 5

2votes

1answer

110views

Will tf.keras.Sequential containing multiple custom layers be correctly fully serializable and deserializable in my case?

I am implementing a U-Net variant in TensorFlow/Keras with custom layers. In one of my layers custom layers UPDoubleConv, I have a Sequential self.blocks containing a repeated pattern of UpSampling2D ...

Ahmed

105

askedNov 3 at 12:00

Question 6

2votes

2answers

92views

Decoder only model AI making repetitive responses

I am making a Decoder only transformer using Pytorch and my dataset of choice is the fullEnglish dataset from kaggle Plaintext Wikipedia (full English).The problem is that my model output is ...

Kirito

13

askedOct 29 at 14:32

Question 7

2votes

1answer

35views

AttributeError: 'NoneType' object has no attribute 'blocks' when running Cache-DiT example with Wan2.2 model

I’m trying to useCache-DiTto accelerate inference for the Wan2.2 model.However, when I run the example script,python run_wan_2.2_i2v.py --steps 28 --cacheI get the following error.Namespace(...

傅靖茹

51

askedOct 27 at 9:21

Question 8

-1votes

1answer

41views

Pretrained ESRGAN (.pb) gives reddish or purple image — is this a preprocessing issue or model issue?

I'm trying to use a pretrained ESRGAN model that I downloaded in .pb format.The model runs without errors, but the output image has a noticeable reddish/purple tint instead of the correct colors....

Ahmed Almakki

1

askedOct 20 at 15:54

Question 9

0votes

0answers

64views

Utilizing GPU with RNN models which takes it's output as input [torch]

I have a machine-translation model. In this model, I calculate a vector for a given sentence and I take this vector, aggregate with each generated output of RNN and put it into RNN again for ...

cuneyttyler

1,395

askedOct 15 at 14:20

Question 10

1vote

0answers

25views

Why does the same YOLOv8n-pose model with different weights have significantly different inference speeds?

I’m testing YOLOv8n-pose models that share the exact same architecture, input size, hardware (GPU), framework, batch size, and precision settings. The only difference between them is the trained ...

Hạnh Nhi Đỗ

11

askedOct 15 at 10:15

Question 11

1vote

1answer

130views

Torch Conv2d results in both dimensions convolved

I have input shape to a convolution (50, 1, 7617, 10). Here, 7617 is word vectors as rows, and 10 is the number of words in columns. I want to convolve column-wise and obtain (2631, 1, 7617, 1), 1 ...

cuneyttyler

1,395

askedOct 12 at 5:34

Question 12

0votes

1answer

86views

Avoid overlap of bipartite network nodes in ggraph

I'm plotting a bipartite (two-mode) network using igraph and ggraph.But the nodes are overlapping a lot, even though there is still space in the graphic window.I would like to plot this using ggraph,...

mmmap

67

askedOct 7 at 12:51

Question 13

0votes

0answers

133views

Kohya-SS SDXL LoRA Training Resets Steps Despite Successful State Loading

I am running SDXL LoRA training using Kohya's sd-scripts and accelerate. I have enabled --save_state and am trying to resume training, but the training steps always reset to 0, even though the log ...

Akash Chaudhari

21

askedOct 5 at 14:01

Question 14

0votes

0answers

83views

Trouble configuring R-group substitution in REINVENT 4 (AstraZeneca) — validation errors for RLConfig and ScorerConfig

I’m using AstraZeneca’s REINVENT 4 (v4.6.27) to generate SMILES from a scaffold via R-group substitution, optimizing for 5-HT2A / D2 / 5-HT1A (maximize) and minimizing H1 / M1 / α1A, with DockStream ...

Reuben Udohaya

1

askedSep 30 at 15:39

Question 15

0votes

1answer

117views

ValueError: Only instances of keras.Layer can be added to a Sequential model when using TensorFlow Hub KerasLayer

I’m trying to build a Keras Sequential model using a feature extractor from TensorFlow Hub, but I’m running into this error:ValueError: Only instances of `keras.Layer` can be added to a Sequential ...

user31600948

1

askedSep 30 at 9:02

Movatterモバイル変換

Collectives™ on Stack Overflow

How to read a large Python project (for example, a project of Deep Learning or Reinforcement Learning)

Resource specifications or requirements of Vision Language models(llm that is specialized for processing images) [closed]

Python library recommendation for the implementation of a neural network modification algorithm

Should I use torch.inference_mode() in a prediction method even when using model.eval()? [duplicate]

Will tf.keras.Sequential containing multiple custom layers be correctly fully serializable and deserializable in my case?

Decoder only model AI making repetitive responses

AttributeError: 'NoneType' object has no attribute 'blocks' when running Cache-DiT example with Wan2.2 model

Pretrained ESRGAN (.pb) gives reddish or purple image — is this a preprocessing issue or model issue?

Utilizing GPU with RNN models which takes it's output as input [torch]

Why does the same YOLOv8n-pose model with different weights have significantly different inference speeds?

Torch Conv2d results in both dimensions convolved

Avoid overlap of bipartite network nodes in ggraph

Kohya-SS SDXL LoRA Training Resets Steps Despite Successful State Loading

Trouble configuring R-group substitution in REINVENT 4 (AstraZeneca) — validation errors for RLConfig and ScorerConfig

ValueError: Only instances of keras.Layer can be added to a Sequential model when using TensorFlow Hub KerasLayer

Hot Network Questions

Subscribe to RSS