cspearl

Error while trying to train custom dataset -__init__() error

6

Hi, any help would be appreciated. I am trying to train a custom dataset from scratch. I cloned the repo 2 days back and did the setup for custom datasets...

[General Issue] Error when trying to train in batch size > 1

2

1. PaddleSeg version: PaddleSeg release/2.6 2. Operation system: Linux - Google Colab 3. Python version: 3.7 4. CUDA/cuDNN version: CUDA11.1/cuDNN 7.6.5 5. Additional context: There is no error in training...

Scene Graph prediction on custom video without downloading any dataset and using pre trained models

1

I actually just want to use pretrained models files and detect scene graphs in a custom video/images, instead of downloading AG dataset or training right now. But I am not...

Binary segmentation on a custom dataset

7

Hi, I am new to segmentation and trying to use this repo to train the network from scratch on a custom dataset having only 2 classes (binary segmentation) and so...

Constant IoU after every validation

7

Hi, I was a bit late to reply to my issue(assigned to @MengzhangLI ) that I was having so it probably got skipped. Please find the details of the issue...

Getting predicted label images without overlay

3

I want the final predicted label images( labeled as 0, 1, ..) but when using - python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show-dir] --show-dir saves the results by...

[General Issue] Adding weights to loss

3

Hi. I am trying to train a custom dataset - Binary segmentation. 1. But since there is a huge class imbalance, I want to add higher weight for the foreground...

Training on images with 4 channels

3

Hi I am trying to train the model on a custom dataset which has images in 4 channels. RGB images and NIR images could you help me out as to...