error in running recognition model ?

[ankur7721]

While running this command after having recognition model in my local model.pt

python translate.py -model model.pt --src_dir recognition.jpg -output pred.txt

usage: translate.py [-h] [-config CONFIG] [-save_config SAVE_CONFIG] --model
                    MODEL [MODEL ...] [--fp32] [--avg_raw_probs]
                    [--data_type DATA_TYPE] --src SRC [--src_dir SRC_DIR]
                    [--tgt TGT] [--shard_size SHARD_SIZE] [--output OUTPUT]
                    [--report_bleu] [--report_rouge] [--report_time]
                    [--dynamic_dict] [--share_vocab]
                    [--random_sampling_topk RANDOM_SAMPLING_TOPK]
                    [--random_sampling_temp RANDOM_SAMPLING_TEMP]
                    [--seed SEED] [--beam_size BEAM_SIZE]
                    [--min_length MIN_LENGTH] [--max_length MAX_LENGTH]
                    [--max_sent_length] [--stepwise_penalty]
                    [--length_penalty {none,wu,avg}] [--ratio RATIO]
                    [--coverage_penalty {none,wu,summary}] [--alpha ALPHA]
                    [--beta BETA] [--block_ngram_repeat BLOCK_NGRAM_REPEAT]
                    [--ignore_when_blocking IGNORE_WHEN_BLOCKING [IGNORE_WHEN_BLOCKING ...]]
                    [--replace_unk] [--phrase_table PHRASE_TABLE] [--verbose]
                    [--log_file LOG_FILE]
                    [--log_file_level {CRITICAL,ERROR,WARNING,INFO,DEBUG,NOTSET,50,40,30,20,10,0}]
                    [--attn_debug] [--dump_beam DUMP_BEAM] [--n_best N_BEST]
                    [--batch_size BATCH_SIZE] [--gpu GPU]
                    [--sample_rate SAMPLE_RATE] [--window_size WINDOW_SIZE]
                    [--window_stride WINDOW_STRIDE] [--window WINDOW]
                    [--image_channel_size {3,1}]

translate.py: error: the following arguments are required: --src/-src

pytorch 0.4.1 py36_cuda9.2.148_cudnn7.1.4_1

Can someone tell what could be error ? I don't know what to pass as an argument to -src I see here that -src means Source sequence to decode (one line per sequence) which is what I don't understand !!

this doesn't help either, mentioned in this issue

[ankur7721]

Has anyone tried running pretrained table recognition model ?

[rahulsinghpatel]

hi Minghao Li, can you please tell me how to use your pre-trained model for Table Structure Recognition. currently, I am using An image which contains a table and I am trying to extract table out of that. But it is giving me am an empty table.

Script to run code: OpenNMT-py admin$ python translate.py -data_type img -model model.pt -src_dir data/im2text/images -src data/im2text/src-test.txt -output pred.txt -max_length 150 -beam_size 5 -verbose

output:

can you please help me with this. I am stuck on this?

References: http://opennmt.net/OpenNMT-py/im2text.html https://github.com/OpenNMT/OpenNMT-py https://conversationhub.blob.core.windows.net/tablebank/model_zoo/Recognition_all_without_copyright/model.pt

[ankur7721]

Hi @rahulsinghpatel Can you tell me what's in data/im2text/src-test.txt ?

[liminghao1630]

@ankur7721 Follow the instruction on this link and see the help of -train_src. http://opennmt.net/OpenNMT-py/im2text.html

[liminghao1630]

hi @rahulsinghpatel , what's the meaning of empty table? can you show me the output in pred.txt? This model require the input image is a whole table without anything else.

[MuruganR96]

@ankur7721 your question, answer here. -src data/im2text/src-test.txt means the input image location give to this txtfile.

Refer here, https://github.com/OpenNMT/OpenNMT-py/issues/1533#issue-482436956

[MuruganR96]

hi @rahulsinghpatel, i am also getting poor result. not extracting the text from the source image.

my output here

[2019-08-19 17:50:44,610 INFO] Translating shard 0.
/usr/local/lib/python3.6/dist-packages/torchtext/data/field.py:359: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  var = torch.tensor(arr, dtype=self.dtype, device=device)


SENT 1: None
PRED 1: <tabular> <tbody> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdn> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdn> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdn> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdn> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdn> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdy> <tdn> </tr> </tbody> </tabular>
PRED SCORE: -1.2848
PRED AVG SCORE: -0.0111, PRED PPL: 1.0111

[the-black-knight-01]

For clarification I am giving sample output: this is generating only table markup. NO DATA Like this: <tabular> <tbody> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> </tbody> </tabular>

tbody - table body. tr - table row. tdy - cell with data. tdn - cell with no data.

Hope this is helpful.

[sanku015]

i am getting this error "AssertionError: Cannot use _dir with TextDataReader." while running translate.py

[lwd45]

For clarification I am giving sample output: this is generating only table markup. NO DATA Like this: <tabular> <tbody> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> <tr> <tdy> <tdy> <tdy> <tdy> <tdy> </tr> </tbody> </tabular>

tbody - table body. tr - table row. tdy - cell with data. tdn - cell with no data.

Hope this is helpful.

Do you know how I can turn these tags into images so that I can easily observe if there are any errors?

[kbrajwani]

@liminghao1630 @MuruganR96 hey i am also getting the empty cell. anyone have figure it out? this is my colab notebook. i have cropped only table area still model not able to get text. https://colab.research.google.com/drive/1xeOQ5IUpwjDmCU6orwHd2hP3coOaau1t?usp=sharing

[LastMonody]

我收到此错误“断言错误：无法将 _dir 与 TextDataReader 一起使用”。运行 translate.py 时

Has this been solved? I'm stuck here, too