wishforgood
wishforgood
 No changes in the end.
Not yet, at last I decided to try other models like wide-resnet.
``` import json import os from collections import Counter work_dir = 'C:/Users/Admin/Downloads' object_list = open('object_list.txt', 'r') object_list = object_list.readlines() for idx, line in enumerate(object_list): object_list[idx] = object_list[idx].strip('\n') name_counter = Counter()...
Here are my codes to count the objects.
@taizan Could you please provide any description of the procedure of generating a color image in normal size(e.g. 1024x1024) from a line image in the same size? I would like...
@taizan Thanks every much for your response! Actually my problem is this: now I have trained the 1st and 2nd stage with my own dataset, and I want to check...
I tried to use the normal color image as the ref image. However, in the code b, g, r, a channel information are needed. But a normal image can only...
I haven't changed the meanstd value and dropout rate. The meanstd value is (0.5071, 0.4867, 0.4408), (0.2675, 0.2565, 0.2761). The dropout rate is 0.3. Both are just as you configured...
That will be great, thank you very much!
Hi, could you please show me your training curve?