Closed BrainPotter closed 4 years ago
I meet the same problem and do not know how to solve it. Could you give me some favor?
I meet the same problem and do not know how to solve it. Could you give me some favor?
Try to use pytorch >= 1.1.0 Best luck!
Also try to use the latest tensorboard by pip install tb-nightly future
I have encountered the same problem, you just need to update your tensorboard with higher version. Best
When I run the python train.py -opt options/train/train_SRResNet.yml I got the following error
export CUDA_VISIBLE_DEVICES=0 Disabled distributed training. 19-11-11 17:11:42.438 - INFO: name: 001_MSRResNetx4_scratch_DIV2K use_tb_logger: True model: sr distortion: sr scale: 4 gpu_ids: [0] datasets:[ train:[ name: DIV2K mode: LQGT dataroot_GT: ../datasets/DIV2K/DIV2K800_sub.lmdb dataroot_LQ: ../datasets/DIV2K/DIV2K800_sub_bicLRx4.lmdb use_shuffle: True n_workers: 6 batch_size: 16 GT_size: 128 use_flip: True use_rot: True color: RGB phase: train scale: 4 data_type: lmdb ] val:[ name: val_set5 mode: LQGT dataroot_GT: ../datasets/val_set5/Set5 dataroot_LQ: ../datasets/val_set5/Set5_bicLRx4 phase: val scale: 4 data_type: img ] ] network_G:[ which_model_G: MSRResNet in_nc: 3 out_nc: 3 nf: 64 nb: 16 upscale: 4 scale: 4 ] path:[ pretrain_model_G: None strict_load: True resume_state: None root: /home/lijunnian/Desktop/image_Debluring/EDVR experiments_root: /home/lijunnian/Desktop/image_Debluring/EDVR/experiments/001_MSRResNetx4_scratch_DIV2K models: /home/lijunnian/Desktop/image_Debluring/EDVR/experiments/001_MSRResNetx4_scratch_DIV2K/models training_state: /home/lijunnian/Desktop/image_Debluring/EDVR/experiments/001_MSRResNetx4_scratch_DIV2K/training_state log: /home/lijunnian/Desktop/image_Debluring/EDVR/experiments/001_MSRResNetx4_scratch_DIV2K val_images: /home/lijunnian/Desktop/image_Debluring/EDVR/experiments/001_MSRResNetx4_scratch_DIV2K/val_images ] train:[ lr_G: 0.0002 lr_scheme: CosineAnnealingLR_Restart beta1: 0.9 beta2: 0.99 niter: 1000000 warmup_iter: -1 T_period: [250000, 250000, 250000, 250000] restarts: [250000, 500000, 750000] restart_weights: [1, 1, 1] eta_min: 1e-07 pixel_criterion: l1 pixel_weight: 1.0 manual_seed: 10 val_freq: 5000.0 ] logger:[ print_freq: 100 save_checkpoint_freq: 5000.0 ] is_train: True dist: False
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 return f(*args, kwds) /usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 return f(*args, *kwds) /usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 return f(args, kwds) Traceback (most recent call last): File "train.py", line 310, in
main()
File "train.py", line 81, in main
tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt['name'])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/tensorboard/writer.py", line 199, in init
self._get_file_writer()
File "/usr/local/lib/python3.5/dist-packages/torch/utils/tensorboard/writer.py", line 248, in _get_file_writer
self.file_writer = FileWriter(logdir=self.log_dir, **self.kwargs)
File "/usr/local/lib/python3.5/dist-packages/torch/utils/tensorboard/writer.py", line 65, in init
logdir, max_queue, flush_secs, filename_suffix)
File "/usr/local/lib/python3.5/dist-packages/tensorboard/summary/writer/event_file_writer.py", line 73, in init
if not tf.io.gfile.exists(logdir):
File "/usr/local/lib/python3.5/dist-packages/tensorboard/lazy.py", line 65, in getattr
return getattr(load_once(self), attr_name)
AttributeError: module 'tensorflow' has no attribute 'io'
python 3.5.2 Pytorch 1.0.1 GCC 5.4.0 CUDA 9.0 what should I do to handle the error? thanks in advance.