shtamura / glcic Goto Github PK

Dear Shtamura-san,

Sorry to trouble you, again. Here is another issue I just have found.

Epoch 00020: saving model to ./nnmodel/glcic-stage1-20-0.02.h5
Traceback (most recent call last):
File "train.py", line 186, in
validation_steps=5)
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/keras/engine/training.py", line 2268, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/keras/callbacks.py", line 77, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/keras/callbacks.py", line 456, in on_epoch_end
self.model.save_weights(filepath, overwrite=True)
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/keras/engine/topology.py", line 2621, in save_weights
with h5py.File(filepath, 'w') as f:
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/h5py/_hl/files.py", line 312, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/ubuntu/anaconda3/envs/glcic/lib/python3.6/site-packages/h5py/_hl/files.py", line 148, in make_fid
fid = h5f.create(name, h5f.ACC_TRUNC, fapl=fapl, fcpl=fcpl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 98, in h5py.h5f.create
OSError: Unable to create file (unable to open file: name = './nnmodel/glcic-stage1-20-0.02.h5', errno = 2, error message = 'No such file or directory', flags = 13, o_flags = 242)

Should I save it to 'model/glcic-stage1-20-0.02.h5' instead?

Best,
Miao

Dear Shtamura-san,

Thank you for helping me with the first issue. However, after I ran the train stage 1, I can finish Epoch 1 but the program just stop there. Could you help me point it out what happens?

My command is: python train.py --data_dir dataset --stage 1

Here is part of my log info:
2018-06-26 14:23:14,807 INFO #[139780687619840] None
2018-06-26 14:23:14,807 INFO #[139780687619840] 0 input_masked_image:False
2018-06-26 14:23:14,807 INFO #[139780687619840] 1 input_bin_mask:False
2018-06-26 14:23:14,807 INFO #[139780687619840] 2 lambda_1:True
2018-06-26 14:23:14,807 INFO #[139780687619840] 3 lambda_2:True
2018-06-26 14:23:14,807 INFO #[139780687619840] 4 lambda_3:True
2018-06-26 14:23:14,807 INFO #[139780687619840] 5 lambda_4:True
2018-06-26 14:23:14,807 INFO #[139780687619840] 6 generator:True
2018-06-26 14:23:14,807 INFO #[139780687619840] 7 concatenate_1:True
/home/ar-jiangmiao01/anaconda3/envs/glcic/lib/python3.5/site-packages/keras/engine/training.py:2039: UserWarning: Using a generator with
use_multiprocessing=True and multiple workers may duplicate your data. Please consider using the keras.utils.Sequence class.
UserWarning(Using a generator with use_multiprocessing=True)
Epoch 1/100
99/100 [============================>.] - ETA: 0s - loss: 0.0233/home/ar-jiangmiao01/anaconda3/envs/glcic/lib/python3.5/site-packages/keras/engine/training.py:2197: UserWarning: Using a generator with use_multiprocessing=True and multiple workers may duplicate your data. Please consider using thekeras.utils.Sequence class. UserWarning('Using a generator with use_multiprocessing=True`'

Then the program just stop there. Is it due to any other reason?

Best,
Miao

Dear Shtamura-san,

Thank you for implementing the paper with Keras. I am trying to implement this, I have a question. In the instruction, there is:
python3 train_mrcnn.py --weights_path ./model/glcic-latest-stage1-xx.h5 --data_path /path/to/dataset --stage 2

I am wondering is trin_mrcnn.py in another repository?

Best,
Miao

pycharm report error
Traceback (most recent call last):
File "train.py", line 122, in
logger.info(model.summary())
File "/Users/cai/anaconda3/envs/glcic/lib/python3.7/site-packages/keras/engine/network.py", line 1320, in summary
'This model has not yet been built. '
ValueError: This model has not yet been built. Build the model first by calling build() or calling fit() with some data. Or specify input_shape or batch_input_shape in the first layer for automatic build.

While run python3 train.py --data_path /path/to/dataset --stage 1