dongheehand / rcan-tf Goto Github PK

I am wondering how long does it take to finish the training. I got no output during the training and i have waited for hours.

I printed out message, but got stucked on this line in mode.py.

_, losses = sess.run([model.train, model.loss], feed_dict = {model.LR : lr_batch, model.GT : gt_batch, model.global_step : count})

I doubt that it started even training since my GPU usage is still 0.

I would really appreciate it if you can help with that.

This is the command i used: python main.py --train_GT_path /data3/SR/DIV2K/DIV2K_train_HR --train_LR_path /data3/SR/DIV2K/DIV2K_train_LR_bicubic/X2/ --test_GT_path /data3/SR/DIV2K/DIV2K_valid_HR/ --test_LR_path /data3/SR/DIV2K/DIV2K_valid_LR_bicubic/X2/ --test_with_train True --scale 2 --log_freq 1000

My terminal output:

(tf-old) xliu0@area51:~/RCAN-tf$ python main.py --train_GT_path /data3/SR/DIV2K/DIV2K_train_HR --train_LR_path /data3/SR/DIV2K/DIV2K_train_LR_bicubic/X2/ --test_GT_path /data3/SR/DIV2K/DIV2K_valid_HR/ --test_LR_path /data3/SR/DIV2K/DIV2K_valid_LR_bicubic/X2/ --test_with_train True --scale 2 --log_freq 1000
WARNING:tensorflow:From /home/xliu0/anaconda3/envs/tf-old/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /home/xliu0/anaconda3/envs/tf-old/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
Build model!
2019-10-02 20:55:20.983090: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-10-02 20:55:20.986516: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3292700000 Hz
2019-10-02 20:55:20.987119: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x558d5359ab00 executing computations on platform Host. Devices:
2019-10-02 20:55:20.987159: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): ,
start training
num_imgs 800

Hi, thanks for sharing your code with us. When I utilize your pretrained model, the code does not work. It said that 'DataLossError (see above for traceback): Unable to open table file ./model/RCAN_X2: Failed precondition: model/RCAN_X2; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?'.
And I have tried the other RCAN models, it appears the same error. Could u please help me to address this issue?