Kristell

@mitmul : Any updates on this would be helpful.

Thank you! I was looking to train and test resnet +SSD.

I am using GTX 960 (4gb). I am able to start the training after reducing the batch size to 2, instead of 8 in train.prototxt and test.prototxt. I am also...

I am not using any python script to start the training. Instead I downloaded the prototxts from pynetbuilder page and started the training by running the following command from SSD...

@forever3000 : It is definitely SSD since I don't have simple caffe installed in my PC.

can you share me your deploy.prototxt for RESNET? What was your training loss at the end and did you finetune from Imagenet model or trained from scratch

Thanks for the deploy.prototxt. The last layer name is 'detection_out', not 'label'. So change your python script accordingly to deploy the trained model. And did you use multiple GPUs to...

I am using the same method to train , except for the number of GPUs used. So does GPU count affect the training convergence?

I have trained VOC using resnet101. Since I trained this using 8x aws gpu, I trained using smaller batch size (accum batch size was still 32) . I want to...