1145520074

I cant train the model when set BASICSR_JIT == 'True'

1

The error is as following: Traceback (most recent call last): File "/data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1723, in _run_ninja_build env=env) File "/data/zx/miniconda3/envs/D22/lib/python3.7/subprocess.py", line 512, in run output=stdout, stderr=stderr) subprocess.CalledProcessError: Command '['ninja', '-v']' returned...

The error is as following: python inference_gfpgan.py --upscale 2 --test_path inputs/whole_imgs --save_root results Traceback (most recent call last): File "inference_gfpgan.py", line 7, in from basicsr.utils import imwrite File "/data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/basicsr/__init__.py", line...

ROIAlign wrong??

5

when I run data_test.py, it went wrong as follows: Traceback (most recent call last): File "unit_test/data_test.py", line 48, in feat = ROIAlign(image, boxes, False, 16, 7, 7) File "unit_test/../libs/layers/crop.py", line...

Recognition Loss: 0.000000 ?

1

Train Epoch: 1 [800/928 (86%)] Loss: 0.022387 IOU Loss: 0.012452 CLS Loss: 0.009935 Recognition Loss: 0.000000 epoch : 1 loss : 0.029173220796831722 precious : 0.0 recall : 0.0 hmean :...

按照源码跑出来结果不对？

1

程序跑通了，但是出来的结果差了很多，如下： [2019-10-18 12:20:42] step = 0, average accuracy = 0.141 [2019-10-18 12:38:34] step = 1, average accuracy = 0.162 [2019-10-18 12:57:24] step = 2, average accuracy = 0.139 [2019-10-18 13:15:24]...