-
Notifications
You must be signed in to change notification settings - Fork 7.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Raspberry Pi YOLO Training #289
Comments
Hi,
to these, for resolution ~224x224 int dim = (rand() % 5 + 5) * 32;
if (get_current_batch(net)+100 > net.max_batches) dim = 224;
saturation, exposure and hue values - ranges for random changes of colours of images during training (params for data augumentation), in terms of HSV: https://en.wikipedia.org/wiki/HSL_and_HSV |
Thank you alot! Of course I first watch the training. There I came to the point, that Now my question, from where can I get these darknet19.conv.xx for training? And one more question: |
|
Thank you again ^^ Little missunderstanding, I look for darknet19, not trained on 448x448, so the previous version of it! For detection I ve to look forward, to get the best out of a Raspberry Pi. |
|
Hey, first of all, thank you for your time. I tried to train on Pascal Voc, followed your instructions, went all fine. Did I missed something or is it just a network conflict, that the parameters doesn t fit to the dataset? `[net] learning_rate=0.001 [convolutional] [maxpool] [convolutional] [maxpool] [convolutional] [maxpool] [convolutional] [maxpool] [convolutional] [maxpool] [convolutional] [maxpool] [convolutional] ########### [convolutional] [convolutional] [region] object_scale=5 absolute=1 |
|
|
|
For next day I ve nomore access to this data, so further data can be sended on monday |
To this line (with your files: data, cfg, weights): And run it. Also what cammnd do you use for training? |
I ve tried both ways. First with my data and cfg, and 2nd with your tiny-voc and voc. Doesn t worked. The command for training is written in train.cmd |
@WTeichert This command: What is the error gives this command? |
Ahh little missunderstanding. I tried using map, but nothing happend (so far as i can see) voc_eval_py3.py", line 157 was the error Could it be, that I chose the learning rate too little, so the network doesn t learn something new out of new input size? |
Attach screenshot of "nothing happend" that happen after this command - you should wait sometimes 10 minutes while mAP will be calculated) I don't know is there any mistake. I can't say anything without mAP. |
nothing happens, means nothing i can see directly. Problem is I am not into c programming, I just in a little python, so all the dector.c - compile and functions in c I understand on the very top. I am not at office these days, so I can try once more on Tuesday, but I don t think it will change the results. |
@WTeichert Try to update your code from this repo. |
Done, but same error. |
You should recompile code in MSVS after that your repo is updated. |
I just checked again difference between my cfg and tiny yolo voc. Because I did not understood the -1 |
@WTeichert It's bad mAP result. Check your dataset using Yolo_mark.
|
Ah found it, but I used PascalVoc Dataset, do I need to mark bounding boxes? @AlexeyAB I ve done check. The labels are not correctly signed, like persons are chairs, cats are boats. Should be connected to the voc.names list, am I right? But the bounding boxes are all right! And that doesn t explain why detection doesnt work. That would be sad... to not know, why it doesn t work and just try again... |
|
@AlexeyAB
Btw. why do i get complete different IOU and recall with commend: ... detector map ... or ... detector ... recall |
@AlexeyAB |
@WTeichert I trained any models on both Windows and Linux using this repo. It works fine. |
@AlexeyAB I tryed to train with 11 classes of VOC, so shortend class-list in voc-label.py and voc-names. Also set number of class to 11 in voc.data, cfg and last filter to 80. Again I get 0 mAP. What was your average loss in training? I am always around 0,5 which seems pretty high. |
@WTeichert About ~0.5 |
Ok, I found the problems. Was some mess with the voc.data and label.txt files. But I am still wondering why the cfg of tiny-yolo-voc starts steps with -1. If you could explain me that fact, I won t ask anything anymore :D |
This is: darknet/cfg/yolov2-tiny-voc.cfg Lines 18 to 22 in 5e3dcb6
the same as reduced learning_rate and removed 1st steps/scales:
Because Lines 94 to 101 in 5e3dcb6
|
Thank You so much for your help! My research is done and went all well. The manipulation of the filter number per layer and the reduce of the resolution brings the best performances of a pi! |
@WTeichert Can you attach your result cfg-file? |
Sorry, I lost the orginals at a system reset and have only the converted h5 files...
That were the results I found. here the h5 file with changed layernumber based on COCO here the h5 file with changed number of filter per layer based on COCO |
Greatings everyone,
I am in the middel of my student research project.
Therefor I am creating an object detection and classification which fits for a pi.
I am using YAD2k running on PI, because it has less computational demands.
I plan to train my network by VOC with different training cfg's.
I am asking you, for some advises, tipps or tricks I can use.
I will change so far:
I have also few questions:
What does activation: leaky or linear do?
saturation/exposure are always the same, what do they do?
Thank you for all inspiration! :)
The text was updated successfully, but these errors were encountered: