NuiMrme

Same Analyzer detects entity in text but not in image

4

**Describe the bug** same Analyzer detects LOCATION entity token in text but fails to detect the same token in an image **To Reproduce** ```py analyzer=AnalyzerEngine(nlp_engine=nlp_engine_with_french, log_decision_process="true",supported_languages = ["fr","en"]) print(analyzer.analyze(text='VALENCE', language...

Enhancing the log by adding an entity_text and creating a new line for every case

4

## Change Description The log by default contains information about the entity_type, start, end and the score in addition to the analysis explanation. Added an entity_text too pin point the...

Enhancing the decision process text when working with images

8

**Is your feature request related to a problem? Please describe.** The decision process output prints out the entity_type, start_position, end_position and the score. When working with longer sequences of texts...

all capital letters names are not detected

1

**Describe the bug** When the name is all capital letters, PERSON entity is not detected **To Reproduce** ```py print(analyzer.analyze(entities = ["PERSON"],text='SOPHY SANTINO', language ="en")) print(analyzer.analyze(entities = ["PERSON"],text='Sophy Santino', language ="en"))...

License confusion

1

Thanks for sharing this. There is a confusion about the license. If I'm not missing something here, Emu is based on llama 1 and commercial use is prohibited but Emu2...

Error "input lengths of input ids is 0"

2

Hello, The only thing that is different from the instruction of the installation is I used Vicuna v.1.5, it downloads the weights locally from HF. In the bliva_vicuna7b.yaml, llm_model: I...

runtime error when executing the default example

11

**Describe the bug** after `pip install screenai` a runtime error is produced in the `from screenai.main import ScreenAI` line in the default example : RuntimeError: mat1 and mat2 shapes cannot...

error because coordinate right is less than left ??

1

I'm parsing some pdfs with openparse which uses unitable. This error occured and I have no idea what it even means , I would appreciate any insights _image_to_tensor(image.crop(bbox), size=(112, 448))...