I met a error in the training... about imagecaptioning.pytorch

[ruotianluo]

This is because I didn't consider situation when language_eval is false. You can comment this line put.

[weiweili123]

Thanks! It's work

[makaaay]

sorry. I met the same question ,but I don't know how to fix it

[ruotianluo]

@makaaay check my reply above.

[makaaay]

emmmm,comment " assert args.language_eval == 0 or args.language_eval == 1" in opts.py ? sorry,I am a new learner in Shanghai.

[ruotianluo]

comment out line 152 and line 153 in train.py

[makaaay]

yeah~it works now !
my mate help me in lines150-161.
if tf is not None and isinstance(lang_stats, dict):
add_summary_value(tf_summary_writer, 'validation loss', val_loss, iteration)
for k,v in lang_stats.items():
add_summary_value(tf_summary_writer, k, v, iteration)
tf_summary_writer.flush()
val_result_history[iteration] = {'loss': val_loss, 'lang_stats': lang_stats, 'predictions': predictions}

        # Save model if is improving on validation result
        if opt.language_eval == 1 and isinstance(lang_stats, dict):
            current_score = lang_stats['CIDEr']
        else:
            current_score = - val_loss

it also works!

thank you very much ! happy new year in US and have a bright future in phd.

[TalenWang-AIcv]

@weiweili123 Hi, It seems that you have successfully run @ruotianluo 's code, but I got such an Error as followed, can you give me some help or advice? Thank you very much.

DataLoader loading json file: ./data/cocotalk.json
vocab size is 9487
DataLoader loading h5 file: ./data/cocotalk_fc ./data/cocotalk_att ./data/cocotalk_label.h5
max sequence length in data is 20
read 123287 image features
assigned 113287 images to split train
assigned 5000 images to split val
assigned 5000 images to split test
F:\Miniconda\lib\site-packages\torch\nn\modules\rnn.py:54: UserWarning: dropout option adds dropout after all but last recurrent layer, so non-zero dropout expects num_layers greater than 1, but got dropout=0.5 and num_layers=1
"num_layers={}".format(dropout, num_layers))
Traceback (most recent call last):
File "F:/Research/ImageCaptioning.pytorch-master/train.py", line 211, in
train(opt)
File "F:/Research/ImageCaptioning.pytorch-master/train.py", line 105, in train
data = loader.get_batch('train')
File "F:\Research\ImageCaptioning.pytorch-master\dataloader.py", line 135, in get_batch
ix, tmp_wrapped = self._prefetch_process[split].get()
File "F:\Research\ImageCaptioning.pytorch-master\dataloader.py", line 263, in get
self.reset()
File "F:\Research\ImageCaptioning.pytorch-master\dataloader.py", line 242, in reset
collate_fn=lambda x: x[0]))
File "F:\Miniconda\lib\site-packages\torch\utils\data\dataloader.py", line 193, in iter
return _DataLoaderIter(self)
File "F:\Miniconda\lib\site-packages\torch\utils\data\dataloader.py", line 469, in init
w.start()
File "F:\Miniconda\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "F:\Miniconda\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "F:\Miniconda\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "F:\Miniconda\lib\multiprocessing\popen_spawn_win32.py", line 65, in init
reduction.dump(process_obj, to_child)
File "F:\Miniconda\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'BlobFetcher.reset..'
Terminating BlobFetcher
Traceback (most recent call last):
File "", line 1, in
File "F:\Miniconda\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "F:\Miniconda\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input <