edwardcho

Results 19 comments of edwardcho

Hello sir. I tried to train image-to-image translation using your code. My dataset is as follows: 1. Blur image vs clear image : paired image set, gray scale 2. Because...

If i couldn't prepare "semantic labeled image", i can't use your code??

Hello Sir, I add error message... ```python ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 768, 1, 1]) ``` This error was occurred in...

> Hi there ๐Ÿ‘‹ > > a CAM is relative to the class output of the model, not necessarily the top 1. So this arg needs to be an integer...

์ž…๋ ฅ์ด๋ฏธ์ง€์˜ ํฌ๊ธฐ๋ฅผ ์–ด๋–ป๊ฒŒ ๋ณ€๊ฒฝํ•  ์ˆ˜ ์žˆ์„์ง€์š”?? discriminator ๋Š” input_shape ์„ ๋ณ€๊ฒฝํ•ด์„œ ๊ฐ€๋Šฅํ•  ํ…๋ฐ... generator_model() ์—์„œ๋Š” ์–ด๋–ป๊ฒŒ ๋ณ€๊ฒฝํ•ด์•ผ ํ•˜๋‚˜์š”??

์ข‹์€ ์ž๋ฃŒ ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.. ์ œ๊ฐ€ MNIST ๋ฐ์ดํ„ฐ์—์„œ class ํ•˜๋‚˜์”ฉ training / test ๋ฅผ ํ•ด ๋ดค๋Š”๋ฐ์š”.. (์˜ˆ : training : ์†๊ธ€์”จ 0๋ฒˆ ์ด๋ฏธ์ง€์˜ train ์ด๋ฏธ์ง€ test : ์†๊ธ€์”จ ๋ชจ๋“  class ์˜ test...

๋„ค..๋ง์”€ ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.. ํด๋ž˜์Šค๊ฐ€ ๋‘๋ฒˆ์”ฉ ๋‚˜์˜ค๋Š” ์ด์œ ๋Š”.. ํ•˜๋‚˜์˜ model ์— ๋Œ€ํ•ด์„œ, ๊ฐ class ์— ํ•ด๋‹นํ•˜๋Š” ์ด๋ฏธ์ง€ 2๊ฐœ๋ฅผ ํ…Œ์ŠคํŠธ ํ–ˆ๋‹ค๋Š” ์˜๋ฏธ ์ž…๋‹ˆ๋‹ค. ์ œ๊ฐ€ MNIST ๋กœ ํ…Œ์ŠคํŠธ ํ•œ ์ด์œ ๋Š”, ์ œ๊ณตํ•ด์ฃผ์‹  github ์˜ ์‚ฌ์ดํŠธ์—...

Hello Sir, In many cases, I got some error. 2020-04-16 02:49:10,095 Segmentron WARNING: get flops and params error: Given groups=1, weight of size 128 512 1 1, expected input[1, 2048,...

Hello Sir, I tested your code using my datasets (image resolution : 256). I was succeed deeplabv3_plus based on mobilenet_v2. but I was failed deeplabv3_plus based on hrnet_w18_small_v1. What can...

Hello Sir, Yes, I got out-of-memory error on GPU when batch-size 2. Thanks, Edward Cho.