DongYongFei

add classify

If I want to recognize a picture, how can I do it? Do I still want to generate LMDB format? Can you provide a predict interface? Thank you

8

If I want to recognize a picture, how can I do it? Do I still want to generate LMDB format? Can you provide a predict interface? Thank you

In attention_recognition_head.py def smape: y_prev = predicted? I can't find predicted，and why state = torch.zeros(1, batch_size, self.sDim)？

Does anyone implement the predict function inference module？

evaluate_with_lexicon

2

I changed evaluate_with_lexicon:False to True from config.py, the following question “UnboundLocalError: local variable 'embeds_' referenced before assignment" appeared, evaluators.py `class Evaluator(BaseEvaluator): def _parse_data(self, inputs): input_dict = {} if global_args.evaluate_with_lexicon: imgs,...

ROW 7.189716071422623 Traceback (most recent call last): File "G:\DataGenerator\SynthText_Chinese_version\synthgen.py", line 623, in render_text regions = self.filter_for_placement(xyz,seg,regions) File "G:\DataGenerator\SynthText_Chinese_version\synthgen.py", line 396, in filter_for_placement res = get_text_placement_mask(xyz,seg==l,regions['coeff'][idx],pad=2) File "G:\DataGenerator\SynthText_Chinese_version\synthgen.py", line 261, in...

Are the parameters of swinTransformer trained during fine-tuning?

2

Are the parameters of swinTransformer trained during fine-tuning?

run simple.py

1

Dear Author： ```shell $ python3 simple.py Traceback (most recent call last): File "simple.py", line 25, in svg = to_svg(img, seg) File "/usr/local/lib/python3.8/dist-packages/pixel_to_svg-0.1.0-py3.8.egg/pixel_to_svg/pixel_to_svg.py", line 35, in to_svg File "/usr/local/lib/python3.8/dist-packages/pixel_to_svg-0.1.0-py3.8.egg/pixel_to_svg/pixel_to_svg.py", line 121,...

test code

2

There seems to be a problem with the test code, and the training phase is fine