I have searched, but the following error appears，Hope you can help answer

2021-12-04 15:50:36,768 one_stage_nas INFO: Namespace(config_file='/data/yy/hinas/configs/sr/DIV2K_2c3n/03_x2_train_CR.yaml', device='3', opts=[])
2021-12-04 15:50:36,779 one_stage_nas INFO: Loaded configuration file /data/yy/hinas/configs/sr/DIV2K_2c3n/03_x2_train_CR.yaml
2021-12-04 15:50:36,780 one_stage_nas INFO:
DATASET:
DATA_ROOT: /data/yy/hinas/data

DATA_ROOT: /data/data2/zhk218/data/nas_data

DATA_NAME: DIV2K_800

DATA_NAME: Set14
CROP_SIZE: 64
TASK: "sr"
LOAD_ALL: False
SEARCH:
TIE_CELL: False
INPUT:
CROP_SIZE_TRAIN: 64
SOLVER:
TRAIN:

MAX_ITER: 600000

MAX_ITER: 100

CHECKPOINT_PERIOD: 10

CHECKPOINT_PERIOD: 1000

VALIDATE_PERIOD: 10
LOSS: ['l1', 'log_ssim']
LOSS_WEIGHT: [1.0, 0.6]
DATALOADER:
NUM_WORKERS: 4
BATCH_SIZE_TRAIN: 16
BATCH_SIZE_TEST: 16
S_FACTOR: 2
R_CROP: 4
DATA_LIST_DIR: ../preprocess/dataset_json
MODEL:
FILTER_MULTIPLIER: 16
META_ARCHITECTURE: Sr_compnet

META_ARCHITECTURE: Sr_supernet

META_MODE: Width
NUM_STRIDES: 3
NUM_LAYERS: 2
NUM_BLOCKS: 3
IN_CHANNEL: 3
PRIMITIVES: "NO_DEF_L"
ACTIVATION_F: "Leaky"
USE_ASPP: True
USE_RES: True

OUTPUT_DIR: output

2021-12-04 15:50:36,782 one_stage_nas INFO: Running with config:
DATALOADER:
BATCH_SIZE_TEST: 16
BATCH_SIZE_TRAIN: 16
DATA_AUG: 1
DATA_LIST_DIR: ../preprocess/dataset_json
NUM_WORKERS: 4
R_CROP: 4
SIGMA: []
S_FACTOR: 2
DATASET:
CROP_SIZE: 64
DATA_NAME: Set14
DATA_ROOT: /data/yy/hinas/data
LOAD_ALL: False
TASK: sr
TEST_DATASETS: []
TO_GRAY: False
TRAIN_DATASETS: []
TRAIN_DATASETS_WEIGHT: []
INPUT:
CROP_SIZE_TRAIN: 64
MAX_SIZE_TEST: 1024
MAX_SIZE_TRAIN: 1024
MIN_SIZE_TEST: -1
MIN_SIZE_TRAIN: -1
MODEL:
ACTIVATION_F: Leaky
AFFINE: True
ASPP_RATES: (2, 4, 6)
FILTER_MULTIPLIER: 16
IN_CHANNEL: 3
META_ARCHITECTURE: Sr_compnet
META_MODE: Width
NUM_BLOCKS: 3
NUM_LAYERS: 2
NUM_STRIDES: 3
PRIMITIVES: NO_DEF_L
RES: add
USE_ASPP: True
USE_RES: True
WEIGHT:
WS_FACTORS: [1, 1.5, 2]
OUTPUT_DIR: output
RESULT_DIR: .
SEARCH:
ARCH_START_EPOCH: 20
PORTION: 0.5
R_SEED: 0
SEARCH_ON: False
TIE_CELL: False
VAL_PORTION: 0.02
SOLVER:
BIAS_LR_FACTOR: 2
CHECKPOINT_PERIOD: 10
LOSS: ['l1', 'log_ssim']
LOSS_WEIGHT: [1.0, 0.6]
MAX_EPOCH: 30
MOMENTUM: 0.9
SCHEDULER: poly
SEARCH:
LR_A: 0.001
LR_END: 0.001
LR_START: 0.025
MOMENTUM: 0.9
T_MAX: 10
WD_A: 0.001
WEIGHT_DECAY: 0.0003
TRAIN:
INIT_LR: 0.05
MAX_ITER: 100
POWER: 0.9
VAL_PORTION: 0.01
VALIDATE_PERIOD: 10
WEIGHT_DECAY: 4e-05
WEIGHT_DECAY_BIAS: 0
Loading genotype from output/sr/Set14/Outline-2c3n_TC-False_ASPP-True_Res-True_Prim-NO_DEF_L/search/models/model_best.geno
2021-12-04 15:50:58,502 one_stage_nas.utils.checkpoint INFO: No checkpoint found. Initializing model from scratch
2021-12-04 15:50:58,549 one_stage_nas.trainer INFO: Model Params: 0.26M
2021-12-04 15:50:58,556 one_stage_nas.trainer INFO: Start training
/home/yy/miniconda/conda/envs/hinas/lib/python3.7/site-packages/torch/nn/functional.py:2423: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
Traceback (most recent call last):
File "train.py", line 134, in
main()
File "train.py", line 130, in main
train(cfg, output_dir)
File "train.py", line 68, in train
cfg
File "../one_stage_nas/engine/trainer.py", line 87, in do_train
pred, loss_dict = model(images, targets)
File "/home/yy/miniconda/conda/envs/hinas/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/yy/miniconda/conda/envs/hinas/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 141, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/yy/miniconda/conda/envs/hinas/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "../one_stage_nas/modeling/sr_compnet.py", line 214, in forward
pred = F.interpolate(images, size=pred.size()[-2:], mode='bicubic') + pred
File "/home/yy/miniconda/conda/envs/hinas/lib/python3.7/site-packages/torch/nn/functional.py", line 2459, in interpolate
" (got {})".format(input.dim(), mode))
NotImplementedError: Input Error: Only 3D, 4D and 5D input Tensors supported (got 4D) for the modes: nearest | linear | bilinear | trilinear (got bicubic)

and the model_best.geno is 354bytes. Whether or not this has anything to do with "No checkpoint found. Initializing model from scratch"

After running the 03_search_CR_R0.yaml, the genotype of the best supernet accuracy is Val: SSIM:0.615 PSNR:23.8382. However，When I train the net by the genotype. The loss function does not converge and sometimes it is nan. I don't change the code.

The follow is the train.yaml file
DATASET:
DATA_ROOT:
DATA_NAME: BSD500_300
CROP_SIZE: 64
TASK: "dn"
LOAD_ALL: True
TO_GRAY: True
SEARCH:
TIE_CELL: False
INPUT:
CROP_SIZE_TRAIN: 64
SOLVER:
TRAIN:
MAX_ITER: 600000
CHECKPOINT_PERIOD: 1000
VALIDATE_PERIOD: 1000
LOSS: ['mse', 'log_ssim']
LOSS_WEIGHT: [1.0, 0.6]
DATALOADER:
NUM_WORKERS: 2
BATCH_SIZE_TRAIN: 24
BATCH_SIZE_TEST: 24
SIGMA: [30]
DATA_AUG: 5
MODEL:
FILTER_MULTIPLIER: 20
META_ARCHITECTURE: Dn_compnet
META_MODE: Width
NUM_STRIDES: 3
NUM_LAYERS: 3
NUM_BLOCKS: 4
IN_CHANNEL: 1
PRIMITIVES: "NO_DEF_L"
ACTIVATION_F: "Leaky"
USE_ASPP: False
USE_RES: True

OUTPUT_DIR: output_R0

l have trid to use learning rate = 0.01. The loss is small but still does not converge

sr_eval.py consumes a large amount of GPU memory.
my GPU is 16GB, the code sr_eval.py just use 5 pictures. If there are more than 5 images, the cuda out of memory. Do you have this problem?

您好，谢谢开源，非常棒的工作。
我想知道 cfg.SEARCH.PORTION 这个参数的具体设置是怎样的，是论文中描述的 0.5 么？
还有 engineer 文件夹中 cfg.DATALOADER.R_CROP的设置 貌似都找不到 ，这些参数对数据集的处理应该都是很关键的。
期待您的回复，谢谢~

这段代码是什么意思，看了半天也没看懂，论文中也没看到具体的解释

I did not modify the source code, but the following error occurred during training
Loading genotype from output/sr/Set14/Outline-2c3n_TC-False_ASPP-True_Res-False_Prim-NO_DEF_L/search/models/model_best.geno
2021-12-14 04:24:08,598 one_stage_nas.utils.checkpoint INFO: No checkpoint found. Initializing model from scratch
2021-12-14 04:24:08,600 one_stage_nas.trainer INFO: Model Params: 0.25M
2021-12-14 04:24:08,601 one_stage_nas.trainer INFO: Start training
Traceback (most recent call last):
File "train.py", line 137, in
main()
File "train.py", line 133, in main
train(cfg, output_dir)
File "train.py", line 71, in train
cfg
File "../one_stage_nas/engine/trainer.py", line 87, in do_train
pred, loss_dict = model(images, targets)
File "/home/data2/yt_data/anaconda3/envs/hinas/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/data2/yt_data/anaconda3/envs/hinas/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 141, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/data2/yt_data/anaconda3/envs/hinas/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "../one_stage_nas/modeling/sr_compnet.py", line 239, in forward
loss.append(loss_item(pred, targets) * weight)
File "/home/data2/yt_data/anaconda3/envs/hinas/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "../one_stage_nas/modeling/loss.py", line 34, in forward
mu1 = F.conv2d(img1, self.window, padding=self.window_size // 2, groups=self.channel)
RuntimeError: Expected object of backend CUDA but got backend CPU for argument #2 'weight'

Hello,

It seems that the inference config file for denoising is missing.
FileNotFoundError: [Errno 2] No such file or directory: '../configs/dn/BSD500_3c4n/03_train_CR_R0/03_infe.yaml'

Can you please upload the inference file?

Thank you.