Hi Ivan,
Congrats for all your projects, they are amazing. I am having a problem when I try to detect my custom images. I compile the darknet_no_gpu application as you do in your Yolov3 Series 2 video and I follow all the processes you do in the following videos. Then, I get the weights by using google colab (I got until the 6000.weights iteration) but when I am trying to detect my custom objects in different images the system returns the same image without any bounding box. I don't know why is it happening but, could it be that in the google colab I am running the command: ./darknet detector train data/obj.data yolov3-tiny-obj.cfg yolov3-tiny.conv.15 and I should do that with the ./darknet_no_gpu application?
Hi Ivan, Congrats for all your projects, they are amazing. I am having a problem when I try to detect my custom images. I compile the darknet_no_gpu application as you do in your Yolov3 Series 2 video and I follow all the processes you do in the following videos. Then, I get the weights by using google colab (I got until the 6000.weights iteration) but when I am trying to detect my custom objects in different images the system returns the same image without any bounding box. I don't know why is it happening but, could it be that in the google colab I am running the command: ./darknet detector train data/obj.data yolov3-tiny-obj.cfg yolov3-tiny.conv.15 and I should do that with the ./darknet_no_gpu application?
Thank you so much, Martí