A computer vision ETL platform for image processing, annotation conversion, dataset inspection, and model training.
Questions tagged [roboflow]
90 questions
1
vote
0 answers
Problem with Train Custom Detector YOLOv4-Roboflow-PyTorch.ipynb
I was trying the yoloV4 pytorch model from the https://models.roboflow.com/object-detection/yolov4-pytorch I watched the tutorials and the comment section but it is still not working properly.
This is the code
%cd ..
#start training
#-b batch size…

Afraim Zahangir
- 11
- 1
1
vote
1 answer
How to find output node names for frozen graph
I'm following a Google Colab guide from Roboflow to train the MobileNetSSD Object detection model from Tensorflow on a custom dataset. Here is the link to the colab guide: https://colab.research.google.com/drive/1wTMIrJhYsQdq_u7ROOkf0Lu_fsX5Mu8a
The…

Max Claesson
- 15
- 3
1
vote
1 answer
How to place the dataset for training Yolov5?
I’m currently working on object detection using yolov5. I trained a model with a custom dataset which has 3 classes = [‘Car’,‘Motorcycle’,‘Person’]
I have many questions related to yolov5.
All the custom images are labelled using…

Vijay P
- 43
- 1
- 4
1
vote
1 answer
YOLOv5 throws a duplicate labels error even though all labels are unique
I am trying to build an object detection system using YOLOv5x. I created my dataset via the Roboflow website and after downloading the set to my notebook, I am running this command to start training:
!curl -L…

Onur-Andros Ozbek
- 2,998
- 2
- 29
- 78
1
vote
1 answer
How can I send a video frames in to POST image url with opencv?
I trying to send individual frames to a POST infer model that receive individual images.
This is what I am trying to do:
read individual frames convert to base64 and send but isn't working
import requests
import base64
import io
from PIL import…

José Benítez
- 37
- 6
1
vote
1 answer
Tensorflow 2 Object Detection API Low mAP
I am trying to train a faster r-cnn model using the Tensorflow 2.0 Object Detection however I am getting extremely low mAP at 0.01.
I have had a look at the training images in Tensorboard and the training images do not look to be loaded in correctly…

Hisho
- 305
- 1
- 3
- 9
1
vote
1 answer
Creating an ML-Model that detects card-values
This is a more generic question about training an ML-Model to detect cards.
The cards are a kid's game, 4 different colors, numbers and symbols. I don't need to detect the color, just the value (a.k.a symbol) of the cards.
I tried to take pictures…

Swissdude
- 3,486
- 3
- 35
- 68
1
vote
1 answer
Premature end of training in TF OD 2 API
I've been playing with the Tensorflow Object Detection API 2(TF OD 2) in these days, I'm using the git head commit ce3b7227. My aim is to find the most suitable model for my custom dataset, by using the existent DL Architecture present in…

José Jácome
- 23
- 4
1
vote
6 answers
/bin/bash: ./darknet: Permission denied
I've created an object detection model using Roboflow's tutorial and have all the saved weights. The one problem I have is deploying it in a Google Colaboratory. I've changed up some code, but it does not seem to work. So in short, model's…

Samay Lakhani
- 85
- 1
- 1
- 7
0
votes
0 answers
Issue with running Roboflow inference in Python Script using Google Cloud Functions API
I intend to capture an image via mobile and send the image to a python script running as a Google Cloud Function which calls my trained Roboflow object detection model.
Here is the python script on Google Cloud Functions to run inference on the…

Kédar
- 1
- 1
0
votes
0 answers
Labels in training dataset
I need some help here. I found dome training dataset of cyclists and was looking for any labels in it, but couldn't find any. Does anyone know how to possibly add them or if I'm just blind? Thanks
The dataset in question: Dataset
I tried looking…
0
votes
0 answers
Changing Project Type from Object Detection to Instance Segmentation in Roboflow
I have been working on a computer vision project using Roboflow, where I initially created a project for object detection. However, as the project progressed, I realized that instance segmentation would better suit my needs. Now, I am looking for…

INNA
- 1
- 2
0
votes
0 answers
How to load a SegFormer pytorch checkpointfile and visualize a prediction through it?
I have trained a segformer model using the code in this article (courtesy of Roboflow)
https://blog.roboflow.com/how-to-train-segformer-on-a-custom-dataset-with-pytorch-lightning/'
I end up with a checkpoint file, and now I want a seperat code to…

Jesper Andersen
- 1
- 2
0
votes
0 answers
Large Annotation boxes on OAK-D
Using Roboflow to train dataset.
Using OAK-D camera.
Dataset trained using Yolo v5.
Annotation boxes are as large as the screen but reading what the object is correct.
(https://i.stack.imgur.com/fsLAY.jpg)
This is an example of one picture I used.…

Ben gann
- 1
0
votes
1 answer
RoboFlow JS error: Uncaught (in promise) Error: The shape of dict['images'] provided in model.execute(dict) must be[1,3,640,640],but was [1,640,640,3]
I'm receiving an error message: "Error: The shape of dict['images'] provided in model.execute(dict) must be [1,3,640,640], but was [1,640,640,3]". Here is the code I'm working with:
Adding Roboflow.js…

alibali
- 9
- 1