Spaces:
Runtime error
Runtime error
| # -*- coding: utf-8 -*- | |
| """Gradio with DocFormer | |
| Automatically generated by Colaboratory. | |
| Original file is located at | |
| https://colab.research.google.com/drive/1_XBurG-8jYF4eJJK5VoCJ2Y1v6RV9iAW | |
| """ | |
| ## Requirements.txt | |
| import os | |
| os.system('pip install pyyaml==5.1') | |
| ## install PyTesseract | |
| os.system('pip install -q pytesseract') | |
| os.environ["TOKENIZERS_PARALLELISM"] = "false" | |
| ## Importing the functions from the DocFormer Repo | |
| from dataset import create_features | |
| from modeling import DocFormerEncoder,ResNetFeatureExtractor,DocFormerEmbeddings,LanguageFeatureExtractor | |
| from transformers import BertTokenizerFast | |
| from utils import DocFormer | |
| ## Hyperparameters | |
| import torch | |
| seed = 42 | |
| target_size = (500, 384) | |
| max_len = 128 | |
| ## Setting some hyperparameters | |
| device = 'cuda' if torch.cuda.is_available() else 'cpu' | |
| config = { | |
| "coordinate_size": 96, ## (768/8), 8 for each of the 8 coordinates of x, y | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "image_feature_pool_shape": [7, 7, 256], | |
| "intermediate_ff_size_factor": 4, | |
| "max_2d_position_embeddings": 1024, | |
| "max_position_embeddings": 128, | |
| "max_relative_positions": 8, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "shape_size": 96, | |
| "vocab_size": 30522, | |
| "layer_norm_eps": 1e-12, | |
| } | |
| ## Defining the tokenizer | |
| tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased") | |
| docformer = DocFormer(config) | |
| # path_to_weights = 'drive/MyDrive/docformer_rvl_checkpoint/docformer_v1.ckpt' | |
| url = 'https://www.kaggleusercontent.com/kf/97691030/eyJhbGciOiJkaXIiLCJlbmMiOiJBMTI4Q0JDLUhTMjU2In0..ztbnfHUlYK1kHw0jKXt1QA.DfJGkOgL9TBiATpTSuKwMoaKfApiVDyncy5kMQb-8FeayksRYddv3tummbzYjPOe9bYuSf1ZSqtcfMY4t1-HenQwnxWZ9HektDmQbcuQaGN7lPwxIzIIjUk3zOkDH6UIcmAeUrPpIbMQ9ZHRIGY9LVAWx1lDctT-9QEfEpdHceS4bNTTrftxi-GBCqd4aLACNz_veXM6YqsplQulb7D9ARZYDOxgpAYl3bDL2-KwduLgCusostp7-uzCTkBeJRQ8LpdmHdRY6FmWcf47vFBcTpG9Qoeml3Sr4EUXEcBKfPKMbDbwIbknoV9TuxGLtKHAu4kyWyRCvLb_20FJ4oZSoQHko0joTeIwOHVPeKpAadT0R3soXGXs7jbcEezdoCz48NFKLU_1lkzeg43ExAgf47iE4_4ErEoi_Hs0deINAY1TunkELGjAO8AuVI4z8fctJgIq_u6rg_-_zcQPDRGqCnoe3M4jtmRWSPFsnOGznezr87jg1bb3hTF1g8RIWWyqmpzUccpMqw27x_ZUkm3UZSQ3Axg7SdqH4XuhtqcujUlH4p51UP7Iv0NlLYMcMpWEFJ630e-kcx8IpKycMVg484Pm8SzI0rTUU6FqA-csBWX1GGAOJwDQR4VYiLTMkd35zNp7byO56uXd5cLXrmcOZdxetrXN8IHAw3GxmlEmi8u-iuZlBwbdWhTx_W3hnwWT.XyPnjS0IQxQ_QlNUd36QVQ/models/epoch=0-step=753.ckpt' | |
| try: | |
| docformer.load_from_checkpoint(url) | |
| except: | |
| pass | |
| id2label = ['scientific_report', | |
| 'resume', | |
| 'memo', | |
| 'file_folder', | |
| 'specification', | |
| 'news_article', | |
| 'letter', | |
| 'form', | |
| 'budget', | |
| 'handwritten', | |
| 'email', | |
| 'invoice', | |
| 'presentation', | |
| 'scientific_publication', | |
| 'questionnaire', | |
| 'advertisement'] | |
| import gradio as gr | |
| ## Taken from LayoutLMV2 space | |
| image = gr.inputs.Image(type="pil") | |
| label = gr.outputs.Label(num_top_classes=5) | |
| examples = [['00093726.png'], ['00866042.png']] | |
| title = "Interactive demo: DocFormer for Image Classification" | |
| description = "Demo for classifying document images with DocFormer model. To use it, \ | |
| simply upload an image or use the example images below and click 'submit' to let the model predict the 5 most probable Document classes. \ | |
| Results will show up in a few seconds." | |
| def classify_image(image): | |
| image.save('sample_img.png') | |
| final_encoding = create_features( | |
| './sample_img.png', | |
| tokenizer, | |
| add_batch_dim=True, | |
| target_size=target_size, | |
| max_seq_length=max_len, | |
| path_to_save=None, | |
| save_to_disk=False, | |
| apply_mask_for_mlm=False, | |
| extras_for_debugging=False, | |
| use_ocr = True | |
| ) | |
| keys_to_reshape = ['x_features', 'y_features', 'resized_and_aligned_bounding_boxes'] | |
| for key in keys_to_reshape: | |
| final_encoding[key] = final_encoding[key][:, :max_len] | |
| from torchvision import transforms | |
| # ## Normalization to these mean and std (I have seen some tutorials used this, and also in image reconstruction, so used it) | |
| transform = transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) | |
| final_encoding['resized_scaled_img'] = transform(final_encoding['resized_scaled_img']) | |
| output = docformer.forward(final_encoding) | |
| output = output[0].softmax(axis = -1) | |
| final_pred = {} | |
| for i, score in enumerate(output): | |
| score = output[i] | |
| final_pred[id2label[i]] = score.detach().cpu().tolist() | |
| return final_pred | |
| gr.Interface(fn=classify_image, inputs=image, outputs=label, title=title, description=description, examples=examples, enable_queue=True).launch(debug=True) | |