DavieHR

hi. I check the original code , which supplied by the paper author, that weight_scale was not like yours. the weight will multiply a constant from he's initializer . I...

hi. I found that the code in multi-gpu training may be wrong. In trainer.py, when you refresh the network, in multi-gpu, you should re-start parralle-data again. otherwise, your renew model...

run make_deep_image

1

i met a problem when run make_deep_image_analogy.sh /usr/bin/ld: /tmp/tmpxft_000079ab_00000000-29_Classifier.o: undefined reference to symbol '_ZN2cv6String10deallocateEv' //usr/local/lib/libopencv_core.so.3.2: error adding symbols: DSO missing from command line collect2: error: ld returned 1 exit status...

How large GPU memory can hold the entire network

7

I tried to train your complete network under the nvidia GTX 1080Ti with 12G GPU memory. But pytorch throw out a "out of cuda memory" error. I just wonder how...

How to download the dataset of vid?

1

BTW. THX

About light room script

2

hi, i'm wondering how you can export Images using LrPhotos .... can you give me an example on it... Thank you.

Some about implementation

2

Hi，Frank. BRILLIANT WORK. BUT, I have some question about your implementation. In the file style.py ,you write the code in the line 184 to 210. grad = net.blobs[layer].diff[0] grad +=...

How solve the padding method between caffe and tf

1

Hi, I met a problem. The padding strategy in caffe and tensorflow is different. How to solve this problem?

syntax error exists in main.py line: 20 parser.add_argumenttf.disable_eager_execution() you can use cicd tools to avoid these issues.....

question about the do fast rcnn test

1

hi,I have some doubts on the do_fast_rcnn_test code. Why did you use the data from the VOC to calculate the mAP ,rather to re-use the data from the roidb_test ?