Open abhidxt299 opened 4 years ago
Bhaiya is this the same issue that was given in the Whatsapp group? Like we had to train the model with different classes of chess pawns.
Yes, it is. But this time, I wish you'd try out a different method of classifying the object. You can first try to implement whatever is shown in the 1st link.
I want to work on this isue.
Is there any specific subtask I need to do or the whole task. And do we need to choose an object detector directly from Roboflow?
You have to do the entire task. For the 2nd part of the question, it's totally up to you. But I'd suggest you to start with Roboflow.
Ok
hey @afrajshaikh anyway we can work on this together, I was also interested , was thinking of using rcnn
hi @Raghav-Dhir, what about YOLO v5 ?
i asked @abhidxt299 about that , he said it would be preferred if we go for R-CNN's or RFCN's.
Cool
@Raghav-Dhir have you decided which one to use?
https://towardsdatascience.com/step-by-step-r-cnn-implementation-from-scratch-in-python-e97101ccde55 i think this should be good starting point
Cool
@Raghav-Dhir in which format you downloaded the dataset?
in csv format and also i think we should have a common collab file
although i have still figure out some things https://colab.research.google.com/drive/1zeN3JqbS6jDEWxa35RMJ-5Z5OndJ2qM-?usp=sharing we can do changes in this
I have requested access
@Raghav-Dhir i talked to @abhidxt299 he said we dont need to implement a detector from scratch right now, we can directly select a detector for now as we will be making our own afterwards. There are many object detectors available on roboflow under models section you check that
@Raghav-Dhir @afrajshaikh you can try using YOLOv3 model. It'd be a really good start.
Sure
have made some changes in the shared notebook. wanted you to check before training the model
@Raghav-Dhir which model are you training?
I just kept YOLO v3 for training
like half an hour ago
yeah it was around 500 epochs so i reduced that and added the _classes.txt and _annotations.txt
just see the file once
also tell me if you can see the keras-yolo3 folder because i am not sure if it will visible to you or not
@Raghav-Dhir i guess you first downloaded the data on desktop and then you are importing it, you could have just imported the dataset by copying and pasting the download link.
I am not sure about the import dataset (from dektop) code, i tried it previously but was unable to do it, I think for using it in collab you need to first upload it on google drive folder. Seniors plz confirm.
@afrajshaikh i have copied the download link only
when i imported the dateset annotation was in txt format only, in your case it is in csv format so you converted it into txt right?
It has to be in txt then you can train it.
yes i did
For how many epoch you are training and your videos.py code block took lot of time?
https://drive.google.com/file/d/1-8tZgdZrPOkF9nHhOQL7IoNpTVS--H_G/view?usp=sharing I trained the model by keeping epochs 200. For training batch size was 8 and while testing it was 4. Test set loss was around 43 and validation set loss was around 40.
validation set batch_size=4*
Select a suitable object detector and train it on a dataset of chess pawns. You can use any of the dataset in the links provided.