使用StyleText批量生成图像结果不成功

[yiyi99]

使用StyleText批量生成图像结果不成功，执行：python tools/synth_dataset.py -c configs/dataset_config.yml dataset_config.yml文件内容： Global: output_num: 10 output_dir: output_data use_gpu: false image_height: 32 image_width: 320 standard_font: fonts/en_standard.ttf TextDrawer: fonts: en: fonts/en_standard.ttf ch: fonts/ch_standard.ttf ko: fonts/ko_standard.ttf StyleSampler: method: DatasetSampler image_home: datas/bg label_file: with_label: false CorpusGenerator: method: FileCorpus language: ch corpus_file: datas/text/unit.txt Predictor: method: StyleTextRecPredictor algorithm: StyleTextRec scale: 0.00392156862745098 mean:

• 0.5
• 0.5
• 0.5 std:
• 0.5
• 0.5
• 0.5 expand_result: false bg_generator: pretrain: style_text_models/bg_generator module_name: bg_generator generator_type: BgGeneratorWithMask encode_dim: 64 norm_layer: null conv_block_num: 4 conv_block_dropout: false conv_block_dilation: true output_factor: 1.05 text_generator: pretrain: style_text_models/text_generator module_name: text_generator generator_type: TextGenerator encode_dim: 64 norm_layer: InstanceNorm2D conv_block_num: 4 conv_block_dropout: false conv_block_dilation: true fusion_generator: pretrain: style_text_models/fusion_generator module_name: fusion_generator generator_type: FusionGeneratorSimple encode_dim: 64 norm_layer: null conv_block_num: 4 conv_block_dropout: false conv_block_dilation: true Writer: method: SimpleWriter 结果只在StyleText目录下生成了三个文件：

[weisy11]

如果使用的style_image的输入没有标签，label_file需要输入一个图片列表文件，详见： https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/StyleText/README_ch.md#%E5%BF%AB%E9%80%9F%E4%B8%8A%E6%89%8B

[yiyi99]

[root@localhost StyleText]# python3 tools/synth_dataset.py -c configs/dataset_config.yml [2020/12/22 15:20:23] srnet INFO: load pretrained model from style_text_models/bg_generator [2020/12/22 15:20:25] srnet INFO: load pretrained model from style_text_models/text_generator [2020/12/22 15:20:25] srnet INFO: load pretrained model from style_text_models/fusion_generator [2020/12/22 15:20:25] srnet INFO: using FileCorpus [2020/12/22 15:20:26] srnet INFO: generate image: output_data/images/0/0.png [2020/12/22 15:20:26] srnet WARNING: corpus length exceed limit: METABOLIC: CALCIUM [2020/12/22 15:20:27] srnet INFO: generate image: output_data/images/0/1.png Traceback (most recent call last): File "tools/synth_dataset.py", line 31, in synth_dataset() File "tools/synth_dataset.py", line 27, in synth_dataset dataset_synthesiser.synth_dataset() File "/PaddleOCR/StyleText/engine/synthesisers.py", line 60, in synth_dataset style_data = self.style_sampler.sample() File "/PaddleOCR/StyleText/engine/style_samplers.py", line 44, in sample origin_height = image.shape[0] AttributeError: 'NoneType' object has no attribute 'shape'

image_list.txt文件内容： b0.jpg
b1.jpg
b2.jpg b3.jpg b4.jpg

请问是哪里有问题？是对图像文件有尺寸要求吗？

[cxy86121]

可能是图片路径问题，建议把图片路径打印出来看一下

[paddle-bot-old[bot]]

Since you haven\'t replied for more than 3 months, we have closed this issue/pr. If the problem is not solved or there is a follow-up one, please reopen it at any time and we will continue to follow up. It is recommended to pull and try the latest code first. 由于您超过三个月未回复，我们将关闭这个issue/pr。 若问题未解决或有后续问题，请随时重新打开（建议先拉取最新代码进行尝试），我们会继续跟进。