Konstantinos Monachopoulos

Seeing from the issues, this is a common request... How do we download the video files using the .JSON file? How can we pre-process to extract the downloaded videos into...

Loss metric while Inference .pb file

3

Hello, Thank you very much for the job that you have done with yolo. I have managed to convert .cfg and .weight to a .pb file (yolo-voc.pb and yolo-voc.meta). For...

Error on quantised model

2

I managed to convert the .ckpt file to .pb file and currently extracting the output image from add_37:0 tensor. The results however are different from inferencing using the checkpoint file....

Is there a way to adjust the architecture of the model in a way that after training can be saved without the dropout layers? After saving it to protobuf format...

Hello, I want to extract a test error using the (vgg16.npy) pre-trained model. Suppose that I want to extract the error of the images that are in KittiSeg/DATA/data_road/testing/image_2. How can...

Describe the problem I am using the pre-trained style transfer models from Baidu Drive. I have converted them to .pb format using the export() function. When I inference a single...

The last layers should hold different names (or types) : ``` layer { name: "loss1/top-1"

Build Error. Why it is obligatory to use GPU?

4

In file included from ./include/caffe/common.hpp:19:0, from ./include/caffe/blob.hpp:8, from ./include/caffe/layers/detection_loss_layer.hpp:6, from src/caffe/layers/detection_loss_layer.cpp:6: ./include/caffe/util/device_alternate.hpp:15:36: error: no ‘void caffe::DetectionLossLayer::Forward_gpu(const std::vector&, const std::vector&)’ member function declared in class ‘caffe::DetectionLossLayer’ const vector& top) { NO_GPU;...

Hi, I managed to train and validate the model on a small subset of the dataset and trying to save the full model instead of only the weights through the...