├── .gitignore ├── ImageDataset.py ├── ImageModel.py ├── LICENSE ├── Readme.md └── train.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | 49 | # Translations 50 | *.mo 51 | *.pot 52 | 53 | # Django stuff: 54 | *.log 55 | local_settings.py 56 | 57 | # Flask stuff: 58 | instance/ 59 | .webassets-cache 60 | 61 | # Scrapy stuff: 62 | .scrapy 63 | 64 | # Sphinx documentation 65 | docs/_build/ 66 | 67 | # PyBuilder 68 | target/ 69 | 70 | # Jupyter Notebook 71 | .ipynb_checkpoints 72 | 73 | # pyenv 74 | .python-version 75 | 76 | # celery beat schedule file 77 | celerybeat-schedule 78 | 79 | # SageMath parsed files 80 | *.sage.py 81 | 82 | # dotenv 83 | .env 84 | 85 | # virtualenv 86 | .venv 87 | venv/ 88 | ENV/ 89 | 90 | # Spyder project settings 91 | .spyderproject 92 | .spyproject 93 | 94 | # Rope project settings 95 | .ropeproject 96 | 97 | # mkdocs documentation 98 | /site 99 | 100 | # mypy 101 | .mypy_cache/ 102 | -------------------------------------------------------------------------------- /ImageDataset.py: -------------------------------------------------------------------------------- 1 | import cv2 2 | import os 3 | import numpy as np 4 | # import tensorflow as tf 5 | 6 | 7 | class ImageDataSet(object): 8 | 9 | # 0 letter 10 | # 1 form 11 | # 2 email 12 | # 6 scientific publication 13 | # 9 news article 14 | # 11 invoice 15 | # 14 resume 16 | # 15 memo 17 | 18 | def __init__(self, base_path): 19 | 20 | self.base_path = base_path 21 | 22 | self.label2idx = {0: 0, 1: 1, 2: 2, 6: 3, 9: 4, 11: 5, 14: 6, 15: 7} 23 | self.idx2label = {value: key for key, value in self.label2idx.items()} 24 | self.label_onehot = np.identity(len(self.label2idx)) 25 | 26 | self.image_size = (1000, 745, 3) 27 | 28 | def read_image(self, image_path): 29 | im = cv2.imread(image_path) 30 | return im 31 | 32 | def read_label_files(self, label_file_path): 33 | image_dict = {} 34 | lines = open(label_file_path, 'r') 35 | for line in lines: 36 | path, label = line.split() 37 | image_path = os.path.join(self.base_path, "images", path) 38 | image_dict[image_path] = label 39 | return image_dict 40 | 41 | def build_dataset(self, batch_size, *argv): 42 | 43 | if ("test" in argv): 44 | label_path = os.path.join(self.base_path, "labels/test.txt") 45 | elif ("val" in argv): 46 | label_path = os.path.join(self.base_path, "labels/val.txt") 47 | else: 48 | label_path = os.path.join(self.base_path, "labels/train.txt") 49 | image_dict = self.read_label_files(label_path) 50 | images = [] 51 | labels = [] 52 | i = 0 53 | 54 | for path, label in image_dict.items(): 55 | if int(label) in self.label2idx: 56 | image = self.read_image(path) 57 | # print(path) 58 | # print(str(i)) 59 | images.append(cv2.resize(image, (224, 224))) 60 | index = self.label2idx[int(label)] 61 | labels.append(self.label_onehot[index]) 62 | i += 1 63 | if i != 0 and (i % batch_size == 0): 64 | yield np.array(images), np.array(labels) 65 | 66 | 67 | def main(): 68 | imageDataset = ImageDataSet( 69 | "/Volumes/My Passport/abhishek/Datasets/Image Dataset/rvl-cdip/dataset") 70 | batches = imageDataset.build_dataset(20, "train") 71 | 72 | for batch in batches: 73 | images = batch[0] 74 | labels = batch[1] 75 | print(images.shape) 76 | print(labels.shape) 77 | # for image in images: 78 | # print(image.shape) 79 | 80 | 81 | if __name__ == "__main__": 82 | main() 83 | -------------------------------------------------------------------------------- /ImageModel.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | from datetime import datetime 3 | import os 4 | 5 | 6 | class ImageModel(object): 7 | def __init__(self, num_labels, image_height, image_width): 8 | # Inputs and Labels 9 | self.num_labels = num_labels 10 | 11 | self.image_input = tf.placeholder( 12 | shape=(None, image_height, image_width, 3), dtype=tf.float32, name="image_input") 13 | print("Image Input Placeholder : " + str(self.image_input.shape)) 14 | 15 | self.labels = tf.placeholder( 16 | shape=(None, self.num_labels), dtype=tf.int32, name="labels") 17 | print("Image labels Placeholder : " + str(self.labels.shape)) 18 | 19 | # self.resize_image = tf.image.resize_image_with_crop_or_pad( 20 | # image=self.image_input, target_height=image_height, target_width=image_width) 21 | # print("Image Resize : " + str(self.resize_image.shape)) 22 | 23 | def conv2d(self, input, scope, in_channels, out_channels, alpha=0.3): 24 | with tf.variable_scope(scope): 25 | conv_weights = tf.get_variable(name="conv_weights", shape=( 26 | 3, 3, in_channels, out_channels), initializer=tf.truncated_normal_initializer()) 27 | 28 | conv = tf.nn.conv2d(name="conv", input=input, filter=conv_weights, strides=( 29 | 1, 2, 2, 1), padding="SAME") 30 | 31 | bias_weights = tf.get_variable( 32 | name="bias_weights", shape=out_channels, initializer=tf.zeros_initializer()) 33 | 34 | bias = tf.nn.bias_add(conv, bias_weights) 35 | 36 | lrelu = tf.nn.leaky_relu(bias, alpha=alpha, name="lrelu") 37 | 38 | tf.summary.histogram('lrelu', lrelu) 39 | return lrelu 40 | 41 | def maxpool(self, input, scope): 42 | with tf.variable_scope(scope): 43 | maxpool = tf.nn.max_pool(name="maxpool", value=input, ksize=(1, 2, 2, 1), strides=(1, 2, 2, 1), 44 | padding="SAME") 45 | tf.summary.histogram('maxpool', maxpool) 46 | return maxpool 47 | 48 | def flatten(self, tensor): 49 | output_shape = tensor.shape[1] * tensor.shape[2] * tensor.shape[3] 50 | flatten = tf.reshape( 51 | tensor=tensor, shape=[-1, output_shape], name="flatten") 52 | tf.summary.histogram('flatten', flatten) 53 | return flatten 54 | 55 | def dense(self, tensor, name, output_size): 56 | with tf.variable_scope(name): 57 | weights = tf.get_variable(name="dense_weight", shape=( 58 | tensor.shape[-1], output_size), initializer=tf.truncated_normal_initializer()) 59 | 60 | bias = tf.get_variable( 61 | name="dense_bias", shape=output_size, initializer=tf.zeros_initializer()) 62 | 63 | dense = tf.add(tf.matmul(tensor, weights, 64 | name="matmul"), bias, name="add_bias") 65 | 66 | dropout = tf.nn.dropout(dense, keep_prob=0.5) 67 | tf.summary.histogram('dropout', dropout) 68 | return dropout 69 | 70 | def build_model(self): 71 | 72 | # Layer 0 73 | conv_0_1 = self.conv2d(self.image_input, "conv_0_1", 74 | self.image_input.shape[-1], 20) 75 | conv_0_2 = self.conv2d(conv_0_1, "conv_0_2", 20, 20) 76 | maxpool_0 = self.maxpool(conv_0_2, "maxpool_0") 77 | dropout_0 = tf.nn.dropout(maxpool_0, keep_prob=0.5, name="dropout_0") 78 | print("Layer 0 : " + str(dropout_0.shape)) 79 | 80 | # Layer 1 81 | conv_1_1 = self.conv2d(dropout_0, "conv_1_1", 20, 64) 82 | conv_1_2 = self.conv2d(conv_1_1, "conv_1_2", 64, 64) 83 | maxpool_1 = self.maxpool(conv_1_2, "maxpool_1") 84 | dropout_1 = tf.nn.dropout(maxpool_1, keep_prob=0.5, name="dropout_1") 85 | print("Layer 1 : " + str(dropout_1.shape)) 86 | 87 | # Layer 2 88 | conv_2_1 = self.conv2d(dropout_1, "conv_2_1", 64, 128) 89 | conv_2_2 = self.conv2d(conv_2_1, "conv_2_2", 128, 128) 90 | maxpool_2 = self.maxpool(conv_2_2, "maxpool_2") 91 | dropout_2 = tf.nn.dropout(maxpool_2, keep_prob=0.5, name="dropout_2") 92 | print("Layer 2 : " + str(dropout_2.shape)) 93 | 94 | # Layer 3 95 | conv_3_1 = self.conv2d(dropout_2, "conv_3_1", 128, 256) 96 | conv_3_2 = self.conv2d(conv_3_1, "conv_3_2", 256, 256) 97 | conv_3_3 = self.conv2d(conv_3_2, "conv_3_3", 256, 256) 98 | maxpool_3 = self.maxpool(conv_3_3, "maxpool_3") 99 | dropout_3 = tf.nn.dropout(maxpool_3, keep_prob=0.5, name="dropout_3") 100 | print("Layer 3 : " + str(dropout_3.shape)) 101 | 102 | # Layer 4 103 | conv_4_1 = self.conv2d(dropout_3, "conv_4_1", 256, 512) 104 | conv_4_2 = self.conv2d(conv_4_1, "conv_4_2", 512, 512) 105 | conv_4_3 = self.conv2d(conv_4_2, "conv_4_3", 512, 512) 106 | maxpool_4 = self.maxpool(conv_4_3, "maxpool_4") 107 | dropout_4 = tf.nn.dropout(maxpool_4, keep_prob=0.5, name="dropout_4") 108 | print("Layer 4 : " + str(dropout_4.shape)) 109 | 110 | # Layer 5 111 | conv_5_1 = self.conv2d(dropout_4, "conv_5_1", 512, 512) 112 | conv_5_2 = self.conv2d(conv_5_1, "conv_5_2", 512, 512) 113 | conv_5_3 = self.conv2d(conv_5_2, "conv_5_3", 512, 512) 114 | maxpool_5 = self.maxpool(conv_5_3, "maxpool_5") 115 | dropout_5 = tf.nn.dropout(maxpool_5, keep_prob=0.5, name="dropout_5") 116 | print("Layer 5 : " + str(dropout_5.shape)) 117 | 118 | flatten = self.flatten(dropout_5) 119 | print("Flatten : " + str(flatten.shape)) 120 | 121 | dense_1 = self.dense(flatten, "dense_1", 4096) 122 | dense_2 = self.dense(dense_1, "dense_2", self.num_labels) 123 | logits = tf.nn.dropout(dense_2, keep_prob=0.5, name="logits") 124 | print("Dense : " + str(logits.shape)) 125 | 126 | predictions = tf.nn.softmax(logits=logits) 127 | print("Softmax : " + str(predictions.shape)) 128 | 129 | tf.summary.histogram('predictions', predictions) 130 | return logits, predictions 131 | 132 | def loss(self, logits): 133 | with tf.name_scope("loss"): 134 | loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=self.labels, logits=logits)) 135 | tf.summary.scalar('loss', loss) 136 | return loss 137 | 138 | def optimizer(self, cost, learning_rate=0.00001): 139 | with tf.name_scope("optimizer"): 140 | # opt = tf.train.AdamOptimizer().minimize(loss) 141 | 142 | optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate) 143 | gvs = optimizer.compute_gradients(cost) 144 | capped_gvs = [(tf.clip_by_value(grad, -1., 1.), var) for grad, var in gvs] 145 | train_op = optimizer.apply_gradients(capped_gvs) 146 | 147 | return train_op 148 | 149 | def accuracy(self, predictions): 150 | with tf.name_scope("accuracy"): 151 | correct_predictions = tf.equal(tf.argmax(predictions, axis=-1), tf.argmax(self.labels, axis=-1)) 152 | acc = tf.reduce_mean(tf.cast(correct_predictions, "float32"), name="accuracy") 153 | 154 | tf.summary.scalar('accuracy', acc) 155 | return acc 156 | 157 | def train_model(self, imageDataset, batch_size=20, epochs=20): 158 | logits, predictions = self.build_model() 159 | loss_ = self.loss(logits) 160 | optimizer_ = self.optimizer(loss_) 161 | accuracy_ = self.accuracy(predictions) 162 | 163 | logdir = "/Volumes/My Passport/abhishek/Datasets/Image Dataset/rvl-cdip/log_dir" + '/' + datetime.now().strftime( 164 | '%Y%m%d-%H%M%S') + '/' 165 | 166 | # Operation merging summary data for TensorBoard 167 | summary = tf.summary.merge_all() 168 | 169 | # Define saver to save model state at checkpoints 170 | saver = tf.train.Saver() 171 | 172 | init = tf.global_variables_initializer() 173 | with tf.Session() as sess: 174 | sess.run(init) 175 | summary_writer = tf.summary.FileWriter(logdir, sess.graph) 176 | for i in range(epochs): 177 | print("Epochs : " + str(i)) 178 | 179 | batch_count = 0 180 | hasNext = True 181 | while hasNext: 182 | batches = imageDataset.build_dataset(batch_size, "train") 183 | if batches: 184 | batch = next(batches) 185 | images = batch[0] 186 | labels = batch[1] 187 | feed_dict = {self.image_input: images, self.labels: labels} 188 | batch_count += 1 189 | _, loss, acc = sess.run([optimizer_, loss_, accuracy_], feed_dict=feed_dict) 190 | print( 191 | "Batch : {0} \t ---- Loss : {1:.2f} \t ---- Accuracy : {2:.2f}".format(batch_count, loss, 192 | acc)) 193 | 194 | # Saving Summary 195 | summary_str = sess.run(summary, feed_dict=feed_dict) 196 | summary_writer.add_summary(summary_str, i) 197 | 198 | if batch_count % 50 == 0: 199 | checkpoint_file = os.path.join(logdir, 'checkpoint') 200 | saver.save(sess, checkpoint_file, global_step=i) 201 | print('Saved checkpoint') 202 | else: 203 | hasNext = False 204 | 205 | 206 | def main(): 207 | model = ImageModel(8, 1000, 754) 208 | model.build_model() 209 | 210 | 211 | if __name__ == "__main__": 212 | main() 213 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /Readme.md: -------------------------------------------------------------------------------- 1 | Document Image Classification 2 | 3 | Paper : https://arxiv.org/pdf/1801.09321.pdf 4 | -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- 1 | from ImageDataset import ImageDataSet 2 | from ImageModel import ImageModel 3 | 4 | 5 | def main(): 6 | imageDataset = ImageDataSet( 7 | "/Volumes/My Passport/abhishek/Datasets/Image Dataset/rvl-cdip/dataset") 8 | 9 | model = ImageModel(8, 224, 224) 10 | model.train_model(imageDataset, batch_size=50) 11 | 12 | 13 | if __name__ == "__main__": 14 | main() 15 | --------------------------------------------------------------------------------