Fastai-Colon-Polyps_Predict.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Fastai-Colon-Polyps_Predict.ipynb","version":"0.3.2","provenance":[],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"accelerator":"GPU"},"cells":[{"metadata":{"id":"QvTTJ45fdCsj","colab_type":"text"},"cell_type":"markdown","source":["# Prediction of Colon Polyp images using resnet-50-based classifier\n"]},{"metadata":{"id":"SAfnlL_5dCsp","colab_type":"text"},"cell_type":"markdown","source":["The script is a basic aplication of the best model for colon polyp detection using **Fastai**. The model has an **accuracy of 0.99** obtained with **resnet-50** transfer learning fine-tuning: [Fastai-Colon-Polyps_ACC.ipynb](https://github.com/muntisa/Fastai-Colon-Polyps/blob/master/Fastai-Colon-Polyps_ACC.ipynb)."]},{"metadata":{"id":"5sux5oBZdCsr","colab_type":"code","colab":{}},"cell_type":"code","source":["%reload_ext autoreload\n","%autoreload 2\n","%matplotlib inline"],"execution_count":0,"outputs":[]},{"metadata":{"id":"ojwbWQQxdCs3","colab_type":"text"},"cell_type":"markdown","source":["I used preinstalled fastai and pytorch from colab:"]},{"metadata":{"id":"5QClWzzTdCs8","colab_type":"code","colab":{}},"cell_type":"code","source":["from fastai.vision import *\n","from fastai.metrics import error_rate"],"execution_count":0,"outputs":[]},{"metadata":{"id":"-8O0EdIqLDxX","colab_type":"text"},"cell_type":"markdown","source":["I connected the dataset from my google drive to colab or change the code for other source. If you will have the dataset on gdrive, you will need to authorize a link:"]},{"metadata":{"id":"xO6FeIuKhUC6","colab_type":"code","colab":{}},"cell_type":"code","source":["from google.colab import drive\n","drive.mount('/content/drive')"],"execution_count":0,"outputs":[]},{"metadata":{"id":"lMrvLRnDLpUh","colab_type":"text"},"cell_type":"markdown","source":["Now I have *My Drive* with the project folder and I will save it as *path* variable. If you have the dataset into another location, please change the path."]},{"metadata":{"id":"zyxNF3bVjsZH","colab_type":"code","colab":{}},"cell_type":"code","source":["path_test = \"/content/drive/My Drive/myAI-Projects/Colonoscopy-polyps-detection-with-CNNs/test\"\n","path = \"/content/drive/My Drive/myAI-Projects/Colonoscopy-polyps-detection-with-CNNs/data_polyps\""],"execution_count":0,"outputs":[]},{"metadata":{"id":"PdBxyVCnLy0w","colab_type":"text"},"cell_type":"markdown","source":["Definition of the list of classes used by the pre-trained model:"]},{"metadata":{"id":"PRiTnwWQsqVt","colab_type":"code","colab":{}},"cell_type":"code","source":["classes= ['non_polyps', 'polyps']"],"execution_count":0,"outputs":[]},{"metadata":{"id":"3DMnuC8CnHKU","colab_type":"text"},"cell_type":"markdown","source":["Create an empty set of data just to be able to make inference:"]},{"metadata":{"id":"Iv7SPx4Ss2Tg","colab_type":"code","colab":{}},"cell_type":"code","source":["data2 = ImageDataBunch.single_from_classes(path, classes, size=299).normalize(imagenet_stats)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"VvjM6EO6nO1D","colab_type":"text"},"cell_type":"markdown","source":["Create a learner based on **resnet-50** topology and load the best model weights from path:"]},{"metadata":{"id":"oI4j8EQUsS56","colab_type":"code","outputId":"62697d6b-ab51-4862-bf15-545e9978a615","executionInfo":{"status":"ok","timestamp":1554419423531,"user_tz":-120,"elapsed":18850,"user":{"displayName":"Cristian R. Munteanu","photoUrl":"https://lh5.googleusercontent.com/-ndtLWHZnMEE/AAAAAAAAAAI/AAAAAAAAP2o/y_loIBY9sZc/s64/photo.jpg","userId":"15479904655347951310"}},"colab":{"base_uri":"https://localhost:8080/","height":6374}},"cell_type":"code","source":["learn = cnn_learner(data2, models.resnet50)\n","learn.load(path+'/polyp-resnet50-fine-tuning_ACC-0.99')"],"execution_count":7,"outputs":[{"output_type":"stream","text":["Downloading: \"https://download.pytorch.org/models/resnet50-19c8e357.pth\" to /root/.torch/models/resnet50-19c8e357.pth\n","102502400it [00:01, 87726708.15it/s]\n"],"name":"stderr"},{"output_type":"execute_result","data":{"text/plain":["Learner(data=ImageDataBunch;\n","\n","Train: LabelList (0 items)\n","x: ImageList\n","\n","y: CategoryList\n","\n","Path: /content/drive/My Drive/myAI-Projects/Colonoscopy-polyps-detection-with-CNNs/data_polyps;\n","\n","Valid: LabelList (0 items)\n","x: ImageList\n","\n","y: CategoryList\n","\n","Path: /content/drive/My Drive/myAI-Projects/Colonoscopy-polyps-detection-with-CNNs/data_polyps;\n","\n","Test: None, model=Sequential(\n","  (0): Sequential(\n","    (0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n","    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (2): ReLU(inplace)\n","    (3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n","    (4): Sequential(\n","      (0): Bottleneck(\n","        (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","        (downsample): Sequential(\n","          (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        )\n","      )\n","      (1): Bottleneck(\n","        (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (2): Bottleneck(\n","        (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","    )\n","    (5): Sequential(\n","      (0): Bottleneck(\n","        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","        (downsample): Sequential(\n","          (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n","          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        )\n","      )\n","      (1): Bottleneck(\n","        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (2): Bottleneck(\n","        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (3): Bottleneck(\n","        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","    )\n","    (6): Sequential(\n","      (0): Bottleneck(\n","        (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","        (downsample): Sequential(\n","          (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n","          (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        )\n","      )\n","      (1): Bottleneck(\n","        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (2): Bottleneck(\n","        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (3): Bottleneck(\n","        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (4): Bottleneck(\n","        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (5): Bottleneck(\n","        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","    )\n","    (7): Sequential(\n","      (0): Bottleneck(\n","        (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","        (downsample): Sequential(\n","          (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n","          (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        )\n","      )\n","      (1): Bottleneck(\n","        (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","      (2): Bottleneck(\n","        (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","        (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","        (relu): ReLU(inplace)\n","      )\n","    )\n","  )\n","  (1): Sequential(\n","    (0): AdaptiveConcatPool2d(\n","      (ap): AdaptiveAvgPool2d(output_size=1)\n","      (mp): AdaptiveMaxPool2d(output_size=1)\n","    )\n","    (1): Flatten()\n","    (2): BatchNorm1d(4096, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (3): Dropout(p=0.25)\n","    (4): Linear(in_features=4096, out_features=512, bias=True)\n","    (5): ReLU(inplace)\n","    (6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (7): Dropout(p=0.5)\n","    (8): Linear(in_features=512, out_features=2, bias=True)\n","  )\n","), opt_func=functools.partial(<class 'torch.optim.adam.Adam'>, betas=(0.9, 0.99)), loss_func=FlattenedLoss of CrossEntropyLoss(), metrics=[], true_wd=True, bn_wd=True, wd=0.01, train_bn=True, path=PosixPath('/content/drive/My Drive/myAI-Projects/Colonoscopy-polyps-detection-with-CNNs/data_polyps'), model_dir='models', callback_fns=[functools.partial(<class 'fastai.basic_train.Recorder'>, add_time=True)], callbacks=[], layer_groups=[Sequential(\n","  (0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n","  (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (2): ReLU(inplace)\n","  (3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n","  (4): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (5): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (8): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (9): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (10): ReLU(inplace)\n","  (11): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (12): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (13): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (14): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (15): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (16): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (17): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (18): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (19): ReLU(inplace)\n","  (20): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (21): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (22): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (23): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (24): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (25): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (26): ReLU(inplace)\n","  (27): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (28): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (29): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n","  (30): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (31): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (32): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (33): ReLU(inplace)\n","  (34): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n","  (35): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (36): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (37): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (38): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (39): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (40): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (41): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (42): ReLU(inplace)\n","  (43): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (44): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (45): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (46): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (47): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (48): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (49): ReLU(inplace)\n","  (50): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (51): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (52): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (53): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (54): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (55): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (56): ReLU(inplace)\n","), Sequential(\n","  (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n","  (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (4): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (5): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (6): ReLU(inplace)\n","  (7): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n","  (8): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (9): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (10): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (11): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (12): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (13): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (14): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (15): ReLU(inplace)\n","  (16): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (17): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (18): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (19): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (20): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (21): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (22): ReLU(inplace)\n","  (23): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (24): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (25): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (26): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (27): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (28): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (29): ReLU(inplace)\n","  (30): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (31): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (32): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (33): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (34): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (35): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (36): ReLU(inplace)\n","  (37): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (38): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (39): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (40): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (41): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (42): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (43): ReLU(inplace)\n","  (44): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (45): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (46): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n","  (47): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (48): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (49): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (50): ReLU(inplace)\n","  (51): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n","  (52): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (53): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (54): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (55): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (56): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (57): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (58): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (59): ReLU(inplace)\n","  (60): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (61): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (62): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n","  (63): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (64): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n","  (65): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (66): ReLU(inplace)\n","), Sequential(\n","  (0): AdaptiveAvgPool2d(output_size=1)\n","  (1): AdaptiveMaxPool2d(output_size=1)\n","  (2): Flatten()\n","  (3): BatchNorm1d(4096, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (4): Dropout(p=0.25)\n","  (5): Linear(in_features=4096, out_features=512, bias=True)\n","  (6): ReLU(inplace)\n","  (7): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","  (8): Dropout(p=0.5)\n","  (9): Linear(in_features=512, out_features=2, bias=True)\n",")], add_time=True)"]},"metadata":{"tags":[]},"execution_count":7}]},{"metadata":{"id":"5buBXGqonlDT","colab_type":"text"},"cell_type":"markdown","source":["Now let's test one image with colon polyps from a test folder:"]},{"metadata":{"id":"nSmrfba63EEt","colab_type":"code","outputId":"b15126c7-9232-4ee3-d1a7-9bcc6a38bada","executionInfo":{"status":"ok","timestamp":1554419475894,"user_tz":-120,"elapsed":1303,"user":{"displayName":"Cristian R. Munteanu","photoUrl":"https://lh5.googleusercontent.com/-ndtLWHZnMEE/AAAAAAAAAAI/AAAAAAAAP2o/y_loIBY9sZc/s64/photo.jpg","userId":"15479904655347951310"}},"colab":{"base_uri":"https://localhost:8080/","height":305}},"cell_type":"code","source":["img = open_image('/content/drive/My Drive/myAI-Projects/Colonoscopy-polyps-detection-with-CNNs/test/29.jpg')\n","img"],"execution_count":8,"outputs":[{"output_type":"execute_result","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAYAAAAEgCAYAAAC926RRAAAABHNCSVQICAgIfAhkiAAAIABJREFU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\n","image/jpeg":"/9j/4AAQSkZJRgABAQEAZABkAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYF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\nV6KsUUxFeirFFAFeirFFAGdP/rTTKtSp5r7849qb5H+3+lAH/9k=\n","text/plain":["Image (3, 288, 384)"]},"metadata":{"tags":[]},"execution_count":8}]},{"metadata":{"id":"wqbrsV-QnwwB","colab_type":"text"},"cell_type":"markdown","source":["Predict the class and show on top of the image:"]},{"metadata":{"id":"y6ChK80kn11x","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":188},"outputId":"bacba1b1-638e-47bb-bbb7-4c1ee0919720","executionInfo":{"status":"ok","timestamp":1554419530376,"user_tz":-120,"elapsed":6799,"user":{"displayName":"Cristian R. Munteanu","photoUrl":"https://lh5.googleusercontent.com/-ndtLWHZnMEE/AAAAAAAAAAI/AAAAAAAAP2o/y_loIBY9sZc/s64/photo.jpg","userId":"15479904655347951310"}}},"cell_type":"code","source":["img.show(y=learn.predict(img)[0])"],"execution_count":9,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAM0AAACrCAYAAADFERguAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzsvVusrdtx1/mrGuP75lx7nxvx8SU+\ncWyStA+QOIk7LRA4aZNLO3EM3RKK6AeEAIkXXnjjwRIgHhIQskA8IIVHkHgEkUiQ2B1LMelOwFYc\nK3Q6gW5bIc4F40t8Lvuy5vzGqOqHGmN831x77X32Pj7bZ+/jVUdLe5015/xuc9Soqn/9q0rc3bmS\nK7mS+xZ9vS/gSq7kcZMrpbmSK3lAuVKaK7mSB5QrpbmSK3lAuVKaK7mSB5QrpbmSK3lAuVKax1ie\nf/55vvCFL7zel/ENJ1dKcyVX8oCSX+8LuJKQT37yk/zkT/4k73vf+/jFX/xFlmXhH//jf8wf/+N/\nnJ/6qZ/ik5/8JKrK+9//fv7W3/pbpJQAqLXyvve9j3/2z/4Z73nPewD4l//yX/Irv/Ir/MiP/Ag/\n//M/zzPPPMNnPvMZ9vs9//Sf/lPe9a538alPfYp/8A/+AYfDAXfnb/7Nv8kHP/jB1/MRPDZyZWke\nIfnc5z7Hd3/3d/Oxj32Mv/E3/gZ/7+/9Pf7Fv/gXfOELX+Df/bt/x7/5N/+GX/3VX+Xf/tt/Oz6T\nUuKDH/zgyd9+4Rd+gQ996EMA/Mqv/Ap/6S/9JT7+8Y/zwz/8w3zkIx8B4B/+w3/Ihz/8YX7u536O\nn/7pn+bjH//41/dmH2O5UppHSK5duzZ2+w984AP81m/9Fh/72Mf4i3/xL5JzZr/f8+f//J/nl3/5\nl08+96EPfYif+7mfw8x44YUX+I3f+A1+8Ad/EIBv//Zv53u/93sB+NEf/VE+85nPAPCmN72Jn/mZ\nn+Fzn/sc73rXu/hH/+gffR3v9PGWK6V5hOSpp55CRMbvADdu3ODpp58e73n66af5yle+cvK59773\nvUzTxKc+9Sk+8YlP8P3f//1cu3ZtvH97/JdeegmAv//3/z5nZ2f8tb/21/jABz7ARz/60Yd6b28k\nuVKaR0heeOGF8fuLL74IxELf/v2FF17g2WefveOzH/rQh/joRz/KRz/6UX78x3/8rsfsSvTss8/y\nd/7O3+GXfumX+Lt/9+/y4Q9/mJs3b77m9/RGlCuleYTk/Px8xBYf+9jH+K7v+i5+9Ed/lH/1r/4V\ntVZu3brFz/7sz/L+97//js/+uT/35/j4xz/OZz7zmZPXf/u3f5vf/M3fHMf8vu/7PpZl4S//5b/M\nF7/4RQC+8zu/k5wzqlfL4X7kCj17hOS5557j05/+NB/5yEdYloV/8k/+Cc8//zy/+7u/y4c+9CFE\nhB/7sR+7FOV6/vnneeaZZ3j++efZ7/fj7+9973v55//8n/Orv/qrXLt2jZ/+6Z9mmiZ+4id+gr/6\nV/8qAKrK3/7bf5uzs7Ov160+3uJX8kjIf/yP/9F/5Ed+5Gs6xl//63/dP/GJT4z//9f/+l/7X/kr\nf+VrvLIruShX9vgNIp/+9Kf5/d//fX7gB37g9b6UN7xcuWdvAPnwhz/Mr/3ar/GRj3zkKi75Ooi4\nX5U7X8mVPIhcbUtXciUPKK+re/aWt7zl9Tz9Q5fuKpnZXf925U69vrL9bi5Kh+QvytU3diVX8oBy\nBQR8neSiRbmyMI+GiAhmNuhL9yNX39xDFDMb5n/7+8X3XMnjJVdKcyVX8oBy5Z59neTKHXvjyNU3\neSVX8oBypTQPQVT1DstyeUxz5/vuV/z+49bHQPSxup8rpbkgr+WX98rHevUggFzK47DNMR8ngMEQ\nv9s9PXpyFdNckNfii+sWJakiQHV7FRZFudvCd7nsOuP44v31DFhT3Lsf6+stl1/7+trjIFdKM8To\nboKbMJ/tuX37JmZG9qYErQMM3CWjf4E0XqXBzW5cZPj1j10GOYvFm90dlQzoyCOoAg6I0Q9pXuJz\nmuMlcdwrq7JUTk8T9xrXbuO1/v+rA2Lg+/F7XKuScygk1U6PKasLWmsFV9KUwWT8TUQ4Sh2fyqrM\nOWG1IuaYJh51uVKaIYpg4Eq5/VUONxemaSYlQboylEs+1tbN8XhEk7Pd0cUEcFRANY4Tu6lRjxK7\nrsQi6RYCxhqLU1qc9JlnnkFEyBpbtQuk4ohL01WnsCAAIogKwro4rSmwt5OJO1Bx8aGQTm2vtf8X\nJ3EYx6ja3CiO8cR28T6zUHBQSPGsXrj15ThGScSeE1YXjLN5N+5Tj0LyPQtgmh6LBfk4XOPXRYpU\nik9cmyf+1+/5YzyRDE+JOWXM6rAyKSWQ1fKklBAHw5kTTElwSShGSrGbFzfSZlNOKSESiyvphKhR\n6hEhjpd1Pb5T6Lt/fM5jsbmS5NSySVIkJ1SV6gVJKZRDFS++HrOZvbAYsCwLqmHNuuUspZBzHvtE\nrasCllIC2PC43lKPuGXcBHen1CO4Yl6oxSn1gFWhFKMW4VArtTp45XwRRJRPfOrX+UP5I5RlVdKv\nh7j7AzMCrpSmSfaEmPHcNeEJWZhEwIysjkghScLdUFfwcGUSRsJQMVyFyZ3ZMy6GOpgvqCtqxtQW\neK2VJGm4Z2Lb8whJEzMOYogldKNtiiII3S+Ti3FSSqgoCeWoC6Ig3tyw+XK3R0SQVIey9MWTsuPu\nZJkAJelwBkmpUnHK4iRJJKm4FEihUOIFfArXVhzhGDbPw94UKuDUckTZkX3h/e99N//n//P7fGH5\n2r/Lhy3fcEqzdYMgFom74+Vl/vfvfw/5cIOUBE2GmyDiaEqIKjlNABFnSOxOswqQqNVJk+LqiMQ5\nwlMxVJziZVgmGMYKXPBZEYU9CdwpaogoqgIa56y1kkik5vOLCJIFEsNCOCXcQBVmn07iLcnxOXen\nNvNhFgBF6u6ZO96WhCaNGM0WwBAVlhbbaU6g8bewQIIRMZQkRUmUpWIY5nEvPuK0hC+GuGHFyflI\ndWfK8Gff81Z+7b98kc++pByKM2m4u4Jh5HCf70OqnAIOye/+Wt8LxMH0/uCSbzil2SqMC5RlYTdn\n/rc/8x705leZ8g5UwhKItpwLZE2Ye+z1Ykx52rgsxjRdDKLvFHUQwpfPqhixUHfzhJU1YBIR5nlm\nWdZtN6V0EqjH7xV3acd1JHcXTsa1DfCiuV/uTkoSsVspqOpp8D6WjYKU8XkzO9lw3J2kCW3H7Nev\nEhuAt5Uaxw7LqZogCbvdRK0an8NRZbiM3/fuZ+G/vsh/+eLLxPJUnIxQ7vlsT54zYHdB6O72msv9\n44vfcEoz4gMvkK+xnN/m+9/9dublBjrvqIBYQTXHbi5CMgc3FJgnAQxfDkwpoWKoCu62WZR9Vy8j\nhsiiZE0Dz1JfUODa9WuxIDXcGcmJquEunZ2dhWWoNZA0VXJeETttVsjMmFKmSBnu1TzP447dfVwb\nhKWsVjfH6f/mhrqBNQBCJA2LpGbgbYFbwHhuhtXa0IAG7LVrimvOuBspCdUdTYbimBjZYTEQlFp8\nIIN/8luv8ZYnZ37pszcQDJHSFOf+lrU4JFZrcuJZXHjtqKdb3b0g8S7fgEqTwSp5mvnWpxPv+RPv\nZC8HXFrEkJRaY4GOxV8L7s40Tc1tYizi4gU1ifc2hVGNb2mSCZdwddwK5kcMSGlCiWMvbYc2AZRY\nmBqLLo4FqSFSKU3AJufTFHZOoSDS3EcRQbTB5x5omEhcY+z8lZTDGqnqsEqqDr4BPIBaZdDnc87U\nWuP9wngvwDTFsZdloVZn1h3VK9UKHmYbs4pQyd6e9W7PrcM5tRY0wTRNnB8rRzfe8aaJH9pN/PL/\n/d+54dfY+QswXX+gb/peeZ/+WrbQd5HV2qH3BgW+oZTGXVApSJ55x7PXec/brrG323g6Q3VBkyAC\n07QfiErfpeGyPMbqNolIg5bZBCyKuCIOmhKwybU0YGALL/eFmidp+Rk/jUvEm9IqoGiqDa3Tfrp4\nnzmkUJrULENHyuI4/b6iQeBpTueV8ySj+rTGSVUDNHB35nkO5TnW9b0GIKQUFtMl47JgVtoGFC7i\ntWvXSPNEefFF3J1nn4D3/4lv4f/69c9z/uQTsJxazIclr2RpvqFoNJ7gls344TbvedvEXs+RXULT\nMlwxEcFKDWegVKQWpmlimmIX7xBlV5SEIBbu1y5lsiiJ+DtS2O0DonavY7dPKaHJURWSGKJGyqDJ\nyZMAhZRb7NEsyzRNEa8kkOwwOWk/Y1PCs+IZUhKmKeHquBUyjrox5VCIlCRADmX8C+GWxf0kzEsk\nS6Ui6i2/Y2x0d8DseCGpI3gECu1HEXISkkJOziTOlJSJCfGJSRdygn2aSKShhLdu3eJ4+5yzecec\nMtOUePOT8IE/+W6OL/zh+H4eytrYKGLfAO4m31BKYzjfJC/yF/708+xYcF195DXQhqxhDaYkJywA\nWJGqy6Tzp5JEDkVVKeVIX/j9HOMntQSf6ljE8aMXft+cLwcsl7KO1yVxctycM1lTXEdK41ouvYYL\n51CVFqM5EaHYhZ/Nc0AQN8QLSYWsaX0GHgiZmiNEHJM1McmEJicRytavJ+eMmVGPS+SNXHEMF+Ms\nVX7if/4eDofDAxXt3Y979mrkDemeuRhqypIUcWOnzsGEP/v82/kmbjDVl6iqkQ+hL1jFVYA1qO8K\nE8F++OXgJO2vS+A7zW1z6nDP1vfTFsWaFBUFIWBrXJnnWLxmERtMPqNJ8Eo43Qm8lEhcTmnEGO4y\ngIaU14AdAmI2gSwRs3TUzjl1P8I9uzzB5+5hMVOKY1glt7dUGtRs1lgNjmiAAh26TqnFZhTwwmJC\nVqV6wrJy9ITKwlydWiQs3C7is1orWhIyCUe/Sa6Vv/Bnvo1f/PRnua0zVnUAA36Bd9flXm5Wf63K\nqYt8P/KGtDSdrhL+c+Qa3v208OZ0mycnp5Rj7HCSkf70zEkWsHAWJakEjLsyvIByTwRnCx4ATJqY\nNJFFN3FOu0atqBspB2qkCfb7mZQFmSTcsEkwcYxK3s3keY2ftujYpc8AUAxRH+dWX/MSsDIatmJm\n4ZZeWHAXLVRKaRyv/4iFkmWJjWhKGghje38cI68Ah3pYnaSkHBtXvz51yCmRVJlyJqcEx1v80Hvf\nyZv3AjJhZIo0HhyhMAMSl9P/38rd/n6/8oZTGtmQJqXcJvuRP/qWZ/mf/uhzZC0cgTwR7kFas+BJ\nnCTOJJATJ+5SUou/KezyxD5PnE0zs54uJBE//X/ii8+ioaC6Ei9FHMmRs+jxDVLDPZoEkiAZLDl5\nN2MpgvstTLx1q0SkxV3h6kxJmZOyE9irspNQ4H2LX7qFWZGz1ZXLKTFJLOD13mR8pouKjIXd7zVs\nNYgdcCuoNHTQGtRgQTRNOHsKU4pYy93BG8xvPtw/r9bcQLiuERf+qe98J8fzF2ASlCNFM1Wa1WD9\n99ShDPHNe+qrVJzXtcPmw+h75mLkmjk355rd5Ie+991cs1vspJJ3meJGFg2URyAhuApJ6gi4Ndbs\ngJU7lUVEmNriWd23FRSYd6d7UKrhkyfVcAHSGlPsGnm4n7MHnzlnSlO++Gps/N4Tlx3R05zCDrav\ncDcrQqKUAmLsdrsBKx9riXgjKVYELEifXq1Z5E6BWek+tVZ0yqtiWbiAtdZIjNZw2wKODhe1jCRt\nXs9tlWWpCBmrSqG0z7UMvSuH84Vagq/WzyEkihuHQ/DRlppwO1Isns9/+vyLfParhfObN8hnT9xz\nXWx426frpbmml8kLX/7KpX9/w8U0UifO823SofBj3/1O5PhVZJ4RKm7hLgwI2cFxkgua9A5XZRss\nQ8t/ENZH5BQCXmOY9QvICqCoKEXjgyq5WTEf5+ioUKfOg58gRRd5YSttJvxx2bg13nIwKc13xijS\n3TbB8IgB2JQ5INCUcsQ6zefXTbzQrVJXsDjPBmJm5Drb3+LHN2vTxEhZcE8Ui/upSVGLz7s7tWER\nw7oCLjugsNTKu597E/v9y/ynzx8aqm0I6VLk67WsJnrDKY2mI1bgh77n25nrTSowuUE6Q9TGjp2y\njKx3zgoSAb8QlHrR1JCkNX/i7kyiZJUoLDOHKeIGUceMYQ2AUBQYoEEol6PqTFPEJNqSkJWIv1wi\ntxY1MSu6dHE3DJey/92DD8Za47NlEvQdHzp7YBoLqyvratnWv6sqUp2EYm4kTRgydudu8S5X8DRK\nvIUUFl0clWA4z2SwhpC5Yc01NgNrsDXiGMZuN3E8HhFRlnokiWBJSXXhW56cefI73sF/+O0vcbvu\nyFJIEly1h1V494ZTGjue8788/208c7zJtJuD7KcS5rmhVQC1LhtelpDwBs0G4TH87P7QG4qmwXA2\nM7S5Z67WFIVhdYZF6EqjimoE/elCLKKqVG27qAVbWkXvsC4XYe5BNO0L927VkHQMb/3NNnU2d5N+\nvvvx3vv9w2q1NpUEwUho+uibhawYSWhIglBNqBuuWxEnsbIjistInpZloUhC08Q37Zxn/CYmTxHf\nld8XHebVymOqNEpUhGWccwpnuCtvSgfe/8e+BckLWOJQjuSe6M6ZjKJJYydvScmUYheUpLHFq4zC\nsJ7QlNQsjDX2L916JCxVnILImjsJrlWiStBeXIV5CoVMzQ20Rmh0seEOSe7HXmMfWLljXTrMm5JT\nrbZjBtu6X1tfvLnBxdp8KxVlqY5poF0ubdGbIzmfVHhuKTYAWcNK1CKkOgfsLGu8B8GANivowdlJ\nwtwibtmACGIRz5gI5oqgpGSIwJIXWBQsISXAmS4pdWjckToxo1QWFl/4H7/zHdiy5z/8v5/nZTLZ\n7aEVeD+mStOpLIY3Ov3ObvPOt1zneDznWr7WmMresuBpBLtdul8+vkjf/KgP+NNaHIB5UNgb/6u7\nXNLcsa5EW8tQWxnylCakcciGMqT1YgbgMKxLIy+y5ntG34GUEEl0kuhut7vDddu6c5clYjMRD3l3\nARG2jO12lHE+aNScQQ8OstaUuvXSwCLEwII6VO6xZCdNLDhiFXIG7+5dJVvCk1Ldgyltm+tv5dUt\nm4ZjpKzUqlxTpVrlzU+fcePFAyby0KzNY6o0q+SaEclUMRaUa3km1VCQnCOpOJCnRg5zWQPevsgn\niYBdiFhBUZIqWYISoqoUq4h45HBSY/k2xKsrztY923U0TjOaastVZFJSrO2aKQXa1d0tVSVlGLFF\ni/BHvkgMTeBew2o2BXEPSDqQpzKg3x5XnJ+f88QTT8Q56L6UU6sFT+0ubthxqah5PFNAkuDlQN4l\nOPSkyBGzDD6BGKkmFq9jY6ptsXd3cpKJKcGCsng0/xB1xI25zqCwyEJp99Xvb9JEdTAvXN/tOJaF\nw+Gc/TRx++iYHLFedi01gIqNS/6arbnX9Ghfd1FKWqgo2QqpVtIUlPyc54F6rbmGFa3CC6KrlThd\nNE7OfRED9YhK5ixNmBTYZdwllMXXIDjQtLpajSRUrZgYgkceIzlFonpzlA3k069huFaNWtLvAVar\n1P9Wax1+fq9xMbMevpxA1f3eC1FH4zmSFW5xvefn58O1G+cQiY3HCpihxdmlGatrZFSNkwrTSkU8\nYbXRaKSzBZb4zvzAPO/ADJGMWQcUThFCDyBx/Y4AnQJAsOZaz3Ng97M6SzWybGuCgi3wWrPVHnOl\nuVy667QBPVlZvO0vkiPobzT6pKtCbV06VWU/7Vd0KXXKS9BmulsW7z1NbnoWtH3h05RwkTsoG9uE\n4XCF7rEx9t1765INlKqXKrc4ZitPPvkk0zSdFLZ16W5rSnduIp3AqsTjvHcmfXNNEjcS5QY1FnyD\nyZOAWW1M7mA9pO2F0PhrLQ82Gn9YK1qT7Xe7vl8VpIM3HQ5/hcLAVyOPudJsdhR39tMMEjuQeSWn\nnsmOB5rVxm6WcmJKkF1JAjoFwzenmTlXxI5MaaaTF0dx2WiI0RKbxVAii16lniy2ub2nuxadnBmv\nr7sr9IW6xi3A6Y6/QdNOGNktEQgtUevBLugqs1WArjBd8Q6HAyLCzhPLsjBLYmlxVE9u2mL4sZCl\nWalaRzJ17ScAtWzyUzlT/Yh7fEOywE4StcWHpQEEmgwv3hqEREApDUY3fHy9vZbHq1PdovBNpKUE\ntEHr202iHQ9ec9cMHnul6WQ7u/C7oHfpn9Wh4p43SQ6zJI5eyDk4Ubm3bRIDierD4R5RcRLSUKOz\neYfkQJ/yFCXMKxO6uVmdEbC9bi+heH0XZUXmHlS64qWGSCUDmpKO+94AAj2WSzmzeXyIB/XxpMZH\nFFMleYAeLkDb8YO3p5HI1NjRBww+4GULqMC0VawCnfvlKy+uPRXMOugR3+Md99oSsj1BeypfH1bY\nY6806kHF6C7R3IJadZhaIjE2bmOnGUHIktCWlzGJktdJnKklM63S4OP2I0bScAlmlORRFpxSompB\nMVAlJUVpdTKph+LEYgNEcxx/Kah49DBzsCRDebq71l3FbiW26BnEwp+jJiB4XRqbau6v942k1lGL\n0124/m9fksNquWBSqZvUvVo0Fim1klpRnDd3qn+ulILOXWEaQzk1KLJtYLVWpBpOK/s2jdinsW6C\naZFYLOg8SSZEz0koqhPL0RsC2ag8vpZUiwQw492Shkq/9outP5OHduTXSbop38YW25+oNelBdUd4\n5CToztNpDUuHiQekLJf1yWoNJFgTgifn9vCvtyzjEcvQ6DkXNs7LiqFUdaBta1P1O+Hd3sQj57zG\nXI2JvGUqn1KHDHXbwLQ6KMGpsZO3z6Jf4xa6317nReu2PqexR4zr7PeeUoAvxZZm4VdW9Pqe1Op4\nLoeUH1Z+pstjb2m2EjFA3iBS686qqqhFRaNMe9Ic1ZIihl6gvXd+GR4KZVbXXMwUbGZJiriT81qX\n7xcoKH3NpJTAjoiEou6zYpLHe5O0jgEN9aq6wuH931rrCTytqvgmjrjIX1OJLjXJhVTDbcuaqEFc\nwdpxA9AoaDLMC+qZ7E1h68Ky1Hb8aFTYV2ns+GW1WtI3DGsUoA3iZ2seq9aKs0TKRwpTztDKnRNw\nSAsJBa2IzpgFDUjUWYqh0nloKZ63ON4aG14EPy7LX70W8oZRmq4o2zqTrFF6HK6Ho62Ti4q1hSrk\n1BavLmhqpQAbFCs1uvvKDohWRO5OnjIp9y/HqQ0G7ZauJydVFdMJJgGPnpkTKxdsNHJocUi2CNpF\nhCwC1cnNtay6Ji/nKZ/stL3zZc8bmRmS0lD6ogzKTaRMBbG1224E1UccaRwwG+cScawpbq01mMYt\n52PVyE3Bu8t72Oz386SoQfHoAbdYpR6dnGaWaq1XQEvINpw5ZQXSCPB7abmVGm2jWEhpohTCfSvL\nyHtd3j/4VIm+FgV6wyjNZdIXR05tMSrDAkRJcuzyIgJaT6wNrFQZPHoAGAq92fgI9lu/L20o3CVf\nhgJFjXRJ04pBpLzDBV+5YuMvLWbY3t+rlc4FOz0fRJARxWK9USKsMLUSzdzVTz++jb3Oz89JrfbB\nzPDSyi5cqA5S60jWXsYs7xdYjUvRr967rZRykqC+02V+OPKGU5otM9iTUxORvRdDpzzikjTFg3cc\nTYwCsdihY3fbzRm3Bc1OkQWRxG4XcLZKh5OluV1O2iQptZUFALgIWiPwN1tp96Ox34Xvejk6SAJP\nrbJxzRk5FfeCu1FkTfIB0YGzBcrb/mvAcKOA4catdTKOEgG+eGTkzQ3NQHZKUcriuCmldZapFVLe\nJCJb5v54PIYr2dwqN2MhDEieMpIEbgk5C7UueO00nFYjZPEco54mWkCpOqXYYEPU0hncK8t7t9uN\na7gf5bkXzeiV5A2nNFvpViXQ53AbRHofsW3m+OJud7rH9zyPto79OM19CBm5GV3ffzE43gbPfWEP\npMy5Ax4Oaj1wByO5fdmpJwvvbW62/KstsLD1/4fF2hxKRVo/1+i3oOrY0tgNIghrKcJWpmlinufR\n0tc1XMqtiMQkgagpWkETUMQKVmr0GpB+jtYeuMdIqUZupyjznFiOxq0bNwNB+zoYm8deafpi67FL\noC9RSThnXXlkKZGn2rL21twDPdl9V6qJRRlvs1iSFqYpt8z+NJKCKaXR39jdRw4I1p29f9GjSUdn\nC7hDtWAF+8IkK8nSe3NABaYU7cI9PJVU1wWWXMNtbDGBeCQ6p5SYGoDReygfLCyumaHVEduOMwwX\n03HmtsCt1SeXYq2s2zlnhcRrrY0sWRFRtJYNodOhxXXLsjQmgQbPkyiTcK/ggqY4dy0JIZqblGqY\nBEu5sxhUo4K2llBY8YyKQTJqqmiblnDqsp6yQC6TXnn6IBbnsVeaLl15tjt6l8i5CNt45SIU7YO5\nfLq4o9eYrQFwrUH2hEENaVcwFPDEqmThIooTrtOqTFaiyfiAcTfuxUU7o5JJmii+NKSKdiU9t8P4\nt59LRILXbA6lhOv3YE83Gl+kDgw4SMWq4hboY3T/XMYzKBvYXe5ZvrM+v+3fxA0hTH7PeLl35kBw\n1oLGFGmEWRK3b543S9qV5aoI7Z6yTf71xKBqboxkAy2ozrHIJRE9gtfPzrupwc2pZeY3tfmqA8qt\nRK8BpLUx8r5IT5UQQDQ6V+a8WrShGH3ujKzK7CbBYG6uSNBJTvusVfFA23wKJCkZ0l3QJdjNViu+\n8fcCeSpQwsJE8jLikGqQxCOmI6yR+jqfRmShmiHkYW3bvoFUg2pYMeqUkGlau8mwUEpc29RYA1ZW\nJExVocZGYbVtOA5aNK6TTHanekVroHSLhFutqmDHyOeUI45hFn0fIt/WZ/o8HHldleZrCca6dEZA\ntxJzL/SacvQkEyNZIpPIZPBKnhaSNFCgkSyDrVVjvkuOuMfdWuZ/Xvse+9pkfJqmkT8J4me4fil1\nly/d9d563AKsEHGLF6pA6YOk6ikqlDfunVsJJCun4ToCHA6HkazVofArQNAz5737TEqR27KGEiKM\nphw5z4iEC5MU1DMqUcrtDdSoxZAlYGWkMk2Jg61EVvOEe4nqp5SGGyc5odVaMTQcj0uwBDTcP3Np\nRW3hSprbuIec4ztZlnU0ovambCc1Qa+98rxhLM02W9x924QwKTiyTg6TaPbXAQLffA56EB90mnht\nDehVNZp3q95h2XrnmMv4UtsdNmNvAAAgAElEQVTjD8YuKwUELlD+N39LKZ9aGovBUm425uTk1kqq\nQVsjCVobheaOZ3Xi+xv37t9s0bUnCbY0YECjitVSu9+UKEskikX7czg9xvZZde85cjBx/lJ6U4zS\nzhFK2TuWXpyRUesy6EMgHJaHzQNY5XVVmq81Q+sCamFpjglmXaFZEUGzR+GZO64VSbvGIVtaFSVY\nCWsEG1qJFWiNNYai5dxKCKYB5w72rXv49BuEp1/D5moBBg1nMNg93K2oyI5RHO6NA2c23L6uuLM4\nKoWF0tzI9Rl2KBnarquKiyHJkBKDlXrHTGBYya3CbkVEwjq3OThZwx01s1Y/07PwFpMRPKDrWhRp\nUHkwq52ctbG4DdQRE9wm3I+YlWaRTpOPNQkVAU14hVQrFUEqKDuqHxAmohXpMpK7D1see0szSpK7\nL72JKVY4c1XQXj8TQ2lp1Y93cqXWE0S9B8SEsy3JcQvhRoPz9WMX6/oHm/cSQ2SspSS2eVNK+a6L\noPdnvrvcnSk8Luk+k6MRfje6vli7l9WibC/xcGhI1/7iUfqs0Lg2FwHNG6QjzrKlDkF8t+UY2X5v\n7sTS5nXaBmCI5HLeHOsbAAh40PjmpG+v9914Dd4lZfI0oVJHQdOkh5jeRUzrGnkSTcRol4hwIwfi\nDXHz7gPQWxxtd34gWgq5ME87tgDC6npJS/CvMO+2JqbzqfoodNs0Zrc2YGqgYy4by9DcGI+d3Kzg\nUpEUfQAGHJ9SixUYcLGIINmizr4Ve4VCtHvt7y+9kXuhK2B3T51IsmpKJBWqORmlWqGWFKMNW6OS\nmKTmrQhtAqkcyqFdT2NHF4e0rVhVvKwxY+0xZxJqiWd8PB7XDfEOL/PhxDSPLcs5knYaZQHOCE76\nYs4JrC4oEZDqppHFtgFGd8m2jTXgTkrGRQby9liokvK6866VmLouyEs+t54jdsVe53Mv2TKTVaP5\nYeRpV3ZyTJvePKsOOyvjPLdu3IzJAunyeGY8l0b9b0ca9xW1R5s+zW10obaqV2uMAy8y7vDygrBg\nVgdJ6fIFvnoB23RBXON+vz9hXF8sHX8Y8khYmgdNLm0+Gb15Bc4qeEpYnpmSk/1AmhRrtTQiadDk\nzWJmS6+kDF+8K1t88b21EUAmOnCKQ1VvDf0CNjU/jrhGNltdzhnz6K027yIwn/KaqDut9W8UEW1M\nY5mHm3LWmgpiBtWbq9hKIDTCr5yi5zFmSOt9vIiRphwwrwrJjaUswco2ONy6zTPXnwwnqyuqx2Ls\nlqgTKDsCl3KHqeO+3KZGIQo3MBjhUZyWECgJd6VMxBBYK+CG17UWxuqCeLAN1DN9SQaieTrBLWY0\nxOwc30DxPZE8TTuGdRG7wK177eSRgZwfxD3rk3jVoKpyVoTbO0GT80SK6VpKYmpgZiT3NjSanKN4\nLJLUsWsN6ouB5tHJJaWEqVM98hZzUqwuzDlmZJLWbje9XDmUaC1LSCm10YMydmZVA1o2Os8s1m5M\nEkKbsZmUPiTJW3l0kmksuO6yQaPFdJdQhLMcTfPISq2l0T/X3stv+ea3RP4lCVbL2LjEJ5I19oGF\nm4ZXaqmkSXn5xsuc7a+jIkwpJi/XRsD0GiPQ0zyxmFMcjrcOLEsmZyXJ3MYLFpYl4pRlWcAER5nm\nHYuEC+dmg6c3AnxrkY+BpkTVGARVF2Pa7ymL4X1FP4Qy5y6PhKX52kQRU6qGixPFSUrKlzCK0xQ8\nyNahxKWBBLL6vsEOOBWRVqQWpPlWkBi7WZ9zCSuBcYy22GwAo8Q4bac0N1djyqQNm33b3EI4haNj\nMbQ4xO1ecf4d0o/bHttQYhPQQoxYb+2WtLl4Vhfa9F7EhDkFzN17vAgW7WQbC05xtEX30no0TzpR\nW/urixL3tRYB1o0lPelsSneZ6wlvzt3R3BgaMqCf8XwfhjwSMc29YMJ7QogSCuLpNizXG+xbUSpJ\niDgjBwUkZSFRSV5JBDig1oq0WnnAutvGCPQptYlircRgblw1b8nUeY4eazPKPk8RyHKak9lSa/rf\nIlaYEJnIeR8MXk55aVvofIvUqRyZM0zJ6bNytkVvUYXa6CZEDcsWkepWsfv+Zkau0UFUTfByCj8X\nDy5cTJ028i6sRvGCSIOS1Sm2cLSFtL/GwRT3dX5oypUkFaohVTkulWogZDRNuEq0EJ7yugf4CriU\nUoa1qe745nm4x5xP3Eheyb7Glg9LHk9L0/IqtOFNAR9HwJ1VAyFLMfk4aWp8LBiArsvasimOdLJQ\nxpCi9rvkhIqeWIvx3h6kmkdQfhlqvYGze7Xj9nzh2t39dk9qRpxmTe9cGH2q9NaZvwzAuCuMbWv5\nVu9yIxINLFyjja8O1p1vYHQjTXDoIzg0jwpTAGmtrmp1zDqTLFyyPpXgUA7UktahTBeeH4zcbcRY\nCMfbB+Z5bu53xbj8ubzW8sgrzWUxzuk62KJiE2NMt2tAyWmbbGxluNPU4oZN7YUYScPVMi8k6TBx\nvCYaVI/by0JC2F/bk+cdy60bI4OfGvPAlsqs2kaBd4sTLsU0tVjDE71hTt0UtoFFwwwUt4rU1tll\nJKKk5UWUaeqIUnMZdR13MZKcKeKdWSMRmTUWL9XQDeLY3+8ccE84udUKTQM96+4i0CasJc7Pz1FV\nrl97gsPtm9TqTDlzqIdhtd0yEXIdKXUhV22sZ+NoE8iE4CSpTCbRdVOl1Q6t1xj1MyAScZqZnQwQ\ndver0oC7yyYLTpTdSkuaqabGyA1XZbguSTbWptxXZi96SqylA+7OW9/2LG9++7fwB3/wRWYxjrde\n5S3IlkbT72f7jdu4hu313Cl331lf6RbXuMlWV6/9dzgu5LTHVZt1bBy37h5V4VBi2NLZ2fVw8yZl\nnnZUX5kJsehXy+wuoz2ztKS0EPtTFQZxFDdq8Q1VZu3F5u4cDuWEIqQdzfmaI47LWNeXv+ORkbXD\nyvr/F2XkU9q4bsFifiOFPNGqHSXaMrWfGTA/BvNYjAllQtlLZrKYPwxtt88pCImtqMmWFD0GpPDN\nf+zbeduf/iHe9N3vo/hyaRyeN9n6Hpes9es9RxP0kxEce7Cc3dJQpoifBNNW3dlQxvWZGOYL5kvQ\nhDYVlBp1nCRXZplOYO6egxmoXy1gFa8Fr0ZdCn1kX08yqirVoLhQqhM9NwMiTmlicWO+PsPkHMpt\nbEociIkBx3p7cMXc2jweNxYMWp9ow/EpcaSPFwy/Tch48xq0TVroNTWqijX4+khmcWGx7Sb0YOIu\n8bOJyS6TR9bSXKY4J2iUgJiy7eEamfN4MZjDvrE0qXX8bxC3RzslSY0YyWpRtMVFg8E8LSQziinX\nv/VP8aWbT/HWtz/P8Uuf5XjjsxSLuGeXZEDVujlWnHPtWnNxI0ib6V9RuhCLv+d0ts+hu1SlFHJD\n0QbLoLkuOWW80/CDMjCUNtyY/jxpI9tXF60nV/t5Y7xF71zTk4jRJ6BKJeXMoRopTVgVXr5xm+Vo\nZHesJ0at5WhIY5NIKXE8HlmW1mXHKiIZFaH2jUEzQjyH6rAshhmUes6160+N+zYDLRYurLz6mEZ6\n4wS5N5jwyCrNK8lw8U8CPxs7aeyOGwTqwudVo7GfRznhyG63V9eA1D0acGTn2777e1iyoEu4MC/e\nuE0NPicqjNHjF9kEF3uCvZKYX95N5cIdELGRDzelHuoAMcbgjAuW++Q8J5fZwYnLrtXaA492S+5L\nm8bQrVYE9sfD6pKNjW5zLfGaUOvd72/Ebt1aeJQu1OOxIZaJcsnH60l7wJ7cfHUJ81eSR849ux/Z\njrS2NnIvssLpJA9iyfHJqGosuvYx7oq00l3SYBNDNOjOAmeTsktg5Zwnn3uOZ77teepRMDnnD778\n//HSH3yWbKwDnzZ8MndHloofS4yp2MDIF61HzwP13d5qxmpmWXws+oFkNXdM1VhYOHJkKQd8OQ73\nr3dp6Yv3xo0bJzC4isfkt94105UsMzSXS4hMP1KgWoPdE+4LzoL7wn4/jxoeVeVw+xw7Hpqbty48\nEWGxA05c87y7fFLDaAQyAjdDOEYKQZWkO3a7M4QJlf14Lh2K3kukBqaNsj0seWwtzWWyDXxjkUTc\n4G0XUp1OYo3TXdXH34U2Oax9udOTz/Bd3/8D1LO38t+/8BK3//A/I1/+PZ7M11C/c1R4l1HF6Csn\nOCBZPdkJ++zPuAwFamv/FYk/Nm5YD9gRxzv03hjbyDonp+/00zRxdnb2Ck9OcY8m59XDavSOPN6u\nMbUYx0d3URuEyf1+D02x1aON3/r5YAoE3HDE7e5ctzssYkBvdCDBTViW49j0xvclQr0/bOc1kUde\naS6t89gwnEcbVQFJSvIaaFpdSKokaw/YQKeNwiigCc251fqHPxx+/wZ1U+Wb/4fvwHbv4GZNvPyf\n/w/Syy/wwgsvMbvAZFhtHfXL2jZJVfEUSltEGm9qhYODm9asjCd8qSR3oEZTP4c0K5RCShJsX9UB\nWJRSYgyiFWrLwU+1s6odfEEFrBypy21kir5vZoZbxA21hnJqWruDWqnNBXO8Vlzi+SxmgxQr7hxv\nnyN5wqtxrEcO5UDSedD1bYlgP0oxdq3RoGLUaCxoiWoZTws1SSjsEgOCh3tNwMylRF3RsdxuvLdg\nVAuZPiXb3UbjkFfLCHBPnQl8z/c9tu7ZZRIzSvIdzN0tM/hu/X9P339al//2d30bv/PikRtf/RLn\nX/xvKEq+Ay6+u/SmhfcrPS6JOUmnrk4/XrxP17HkHYS7wPYeGfN7XFt/X7CSHalB/BQnAIVSSZtn\n5u4sx3A9FaEcDIpixdfj9U3twqZnjWjjbZO7uLRHHsgJ6yR3xoipU5ek18y8VglN2yyOxwhyvih3\ng5zv+FvLXHd0Zm3HtDYK1+pMaAxldTZokuOSUMnkNGMtvrl16xZvfe5b0D/yLNPx9/iDT/4iz15/\nmpdv38JTYtENe8BO62xEBPUd1IkRQG/qWwazQGWDArXrdCKWMEiS12usUXwm5mQXpBjUQN+yrD0B\nTlE7PaHM9NZRrSUCVFiWipggFv2et/c06vObZTIzDocDiFGO5xxuHfCDkGyP1oC404Z7V2tlKpmd\nn3GM3h4UqVQBU2k9CGTNVLVzT5GsoVilurdhWluaUcV9Ce6ghiKX4/I1lQb0SXbxc/ed9ZF1z16J\n7dzvqSpUj/d3blgsnHW0xFqXX6jR34W0CUazKJJiBaWsg3917do1zvYz//U//Hv+2+/9Dm9+07P8\n9y99lYkUM2lEBm1DJerbI3dg1GpI7otYwSszaYV+bXUrkMhNSNvOew7C3Sl1LSVYWJjbXhzK1QdW\nNYqPxZfuEnN3OngArY+yE51qassbqUKNGZ1WKmme8GPBSsubVENaHgSJUfGSotdaLU6WmeqO1QOl\nBNPg4qQ1VaUmBilUUY4tB6LJwGJitAdztjGr4YhhNaHWU59rs/XtxrQ9z1pe/XDlkVWaV5Lueo5+\nZ/fhdg3pc1O8uelC7GTt873H2VNPPcXh1m3OX/4Kb37yGez8nKn3Ofbth/s/W5AhciQnym+nF3g3\nV/EUVNCT95+KjddFJOBzUlPk0zdf5KB1axbKF/Mzy+EYNH1brZ6UmNCWRDk296WPDXEXJKY8xXVs\nrrvHnWaGtckA6pcMt2rcs5bLJHswA6JFbo8xTr2NbjG3SjPnidILDn25pDf2ayePnNK8umK0kCBv\nBvSrotBBAlsb6UEvessnVH0h+BzJlCKVPAX1/qsvvcCc9pTbC8fjAuKYH6JpX1p3PedOEmb/qt19\nDFtSNp9pm+hF5M27r95cse3L5bC20xVfrU6c03EKQlBfRCPoTylRl4AQvIYi2EYx3CPvZHXBqw43\nLKUY+Zc0GBGyLHhRPO9xmcecy1odSY551MrgQp7mzVgQo9iCZ0clIWUDWLC6yQEaGFYDKXMJOlQp\nldCqsDZJ1iRyB1WYUmwaU3qoCgOPoNLcr2x33R4rbEuWZVBsGuWCaP+69fe3kqwrXQ8GjWM5kLNy\nOA8qu4mSpDC6qtyz9dGpPFgPhDVjv41HgFbH0ug4Xoc/fyLbzHjQBIKh0AAJdyd5q7Ks8Xp8bK0l\n6uNCpjZ/p9ba3EjlaIRf7KsrdCwHtn3e7twIaBtEpS+7i3ma9d4vcsg2btiFJ9XzW25GfbWdaGS1\n2Pcjj4zS3IGyvMIi2yKDgyOlKxUGFFJuqQ4ZzSpGMwttPjXBYCa1jIiU6KIviaRQDyW4X9bbHQHo\nHfFSHLx3dgzMOL764B3cjcvkXvG6LqIAB9Ycx8X7nzODtNirGQe3rTf1MGuxQFtEVsNlMaAGXaVS\ncaKhudUJaO5YivLpeT/HYkxtApoZamdhpUuh1kMgaJ6opTW7qLW1psqnE6pr9JzrLZq6gqgquVZE\nWu/mpZB0in4Om/W/tUh9bViNMoLe2603c+wgwcjjwCtja65bvXzFTz0ySvNayTRN7aGtdIzBAtDW\n9G7zPLYMgq0C9MRdxDc2Kgsvwp8nXXHa+S6+Z31fwLJ+4qO3ndkE8z6lefXXewXqOKav9P8YS2Wj\nElUbE3jEVP1eCH5WrUGdt1KHC7YFC+ZdhhRxxzRNkRNq9KJaK3meo0T6eOQs59Y7OXF+e2m8tDvh\nX1VtTPHLA855nse1fPmrf8izb3rb5tVNzOhBizoej8zzzLGxDnLOwTMkuGzbOh7uuJr7lXt/6pFR\nmteqyZv5sVmRwCJPs/XROHueE9GVW4c/DQy/erujQSN4bhRm22BPLdL9irBUMIlCuNo4a/1zpXSW\nc1voY0JrTCrDV+QvyRof1VJjhMQGMTqh9DsxEhFw1h7Qag7EIgOw2tsoMRKZtVaqLZydZVQyc1Zu\nVhDNERmpoK1lblKNKs6s7HMwDK6LURZhWRbOb+WWwJSmoGsNjrd4Ma4jJr0Bw1KYx7N5+umngyLV\nmz56GTHZcgwFqsW5XW9jPpHyzDS3bqLt+/qG6UZzmbwaQGAtD45/p1aA1h+kpoxKb1mrJElQrGXa\nV+nKMpTIY++ZVMcYjL6IR/MNd2ZNESdY2I+qfuKKeFkQrdEOF8FrxCQkQZJQ6ygeGefQHOjR1MZa\ndHcs3DMQt6HAXiLYt1pZvEZ8lpScEqUKyRPzfheN01Uby3hBpsw0RbHZE9fOIk/lxqEsw/XJOSM1\nekyPZ5TOmLLwREq8fPPLRFOQoP7UWtnv9xwOh3C9OsqZoDZ0Uh0KQkGopZKnM0wTooIulcUKxTKY\nt8Iz2O+vNb5ZjKDvz7csl5dpPAx5ZJXmtRPnbq7BK8kW1XklFb6MIXxngG4DmvYSbVi3TTZCjL4t\nB3p19zkV0qtL+++1Lc5WEAbaivESqcVNtVZkznhOTFPCSmZuDdDnnJCUO3BOxqMbjbT6nCx4XZ+J\nWY8hnXmXOR5A20SDqsumX9qpxHNRTIzi4TbSSp+rSDRSH89kfR54HkF7eAsyCJuv7hu+24N9TNyz\nu8mD9kS7yCK+1/tG4M2p5VhrSdaGfqqKlQieVVtDDndqbmP3lkqeE1VapxvzEQxva1jMIuUt4iR1\n8EKSjFk0t+hu/Eq4jFiqLM3daYiXu1FbM8Re0WgW1YyaJlIOvm+3st7KB5KF9ekuXwbcltXl0x1i\niquhaQemK0iooLmN6APk2CeqaZA23ShLWNKJdaKCoyf35BT6PKDOdpim1hILWTeTOiMWhFtNYVEP\nSyTnkmasjd0wszEUS8qrd/PdG4B0jwI0eAyU5vWWkySaK+oldmIP6Nd7hlQM9cjN9P7SOqzAJq5y\nD6JlG0PYQ2S9m29RLdy49vHeWkk9wIOtCdx2xWSXMcIVArDGgHZvJE1dv/pi68YhkpqStFa2pHVx\n12gL25+HNfezd7cxu8UFGKqhmptF2Fjccb5QOIhp1nqhYUnWxvhuz666kUxZrLQiPx9gRkJH6fSr\nF70vwuYjqzT3KnnubVe1daQBxo6lVBSPLjQtwDxB/EeepneE7MVSgRKp9I5eNtqfeMpUDwZu/CGs\niwnIsZCmCU9K6ZSaKYO1ehCPKtDSPrdeA4i0+S0X8gRbjtVFF6eyIERf40mi6G1MW9M9aZpidCB7\nRDM+ZUyjP5u359R7KnfpS7VD10ut7KZgXhsZTQmpRplD0fNieDV0D/VwICVFzhemacfRFty0TUnr\n/ZljqkCctI/RSJhlcMEtUDdHcF03qXmXqOd1hHmT9mb1mepOqTZGivg0sdRKTZ1E+1qROO+UR1Zp\nHob0XTh2LufuyckLSopFjwA21BcP2o15Z+SuAOlYkKMehqEwY57NybtfgWfXDwckWua7WrM4Ptyg\nPE1Mu30wj6cdmhM+z6DtM4Q7lXuft+V0pLh1YqQE4OEmKBOiimslmYA5JkdMV0AiwJd4bt6rJpvU\nWtGs4x6ilVPFTIHu/nZkcgMxE5hINEeJ+MysRoWgC8fzw8lojnBRna+t+CxYGOP3u8hjpTQj/9DX\n2SX31SHjlVrSejdPE+pBrQlq+b1Kik/zNl5jcK1YDQvTqyiXpgTmVKvoPOMCC4ZKhNI9ESm5BeYD\nAo9Eaa1AizvG4m1Faaprvb+V2rKvBanGpBLK0RbtlDKWnCKKTDuKOPNuwiVRmda8VXJKrzvZtaSg\nFfJIDDoyz9EX289JHg3e3QSvhUkTdd5jy4K0Vr1+WNgl5XbqeZqY0NZzJnUpMOU7gJFanOpHpnn9\nvmzznuoLMjmUGA+fWhvSUgrFFmpdOD/f9tJ2jsv55ht8MIlndM8BocBjpjSjgURzz2KrXf3xLYUj\nKPG911k80D5JWFOhXMjoi0elh7iN5OcYCyiRZUajWApWBTaCQbzND2zJkaPiUmQE9dvkW3yu+fY9\ncSk6LBhtHuWaQNXWPjaudacZzsJdybpDU8aZKH4ke8I0U1HmaS2OK6WMe8sZ6nKOpBgL54eCLcGY\nxhPmiWpGShnLcF7bnBpNZBSfBStg+Uje77Dby2hKHwz0GHgVaZvO9cvgcKx19KjeZv2tFbzVauQ0\ncagxyNc9YdWxpVAPxuFYIWfSHHmjKFZrcPw3EmHztZAtKgYrj+reu8jKJVuVL1wG6fNiLik6O+Fa\nySkA0CUQpFeSC5l0b8e548u3hsCB1niDNLi7TJk0JywltCSmaUeRhLmifaKBM5oidqm96YJv82Nh\nGUVbYz8X8rTj6IXeLUO8omKnjTM6x0zW+DFmS9smvo4YLiDzy1d39DIQihcGa6LB9KUeWc4PHI+V\n/MQOE4VaNmXjjT/o+lCim6/FAXzdpAfKHW7c8sD637c9xuBOcuDUAIIpJaaUTqyO14WskNVIUpE2\ndi+OnSMQrX5S7x5FZ0H87Au+J1svmwFzt74Cl8mwsCK4TkzTjlRrqPluR5r25PwE07xDdEY0szu7\nFolYzUy7mQKclwI546JonoLOmjKSp+DpSQAarrHMxSpMTnIj72aeeO5tnD11jeyF3T6YCP36SrEx\nYGnN44QFXqxS3LAkLASLIMaqx4zO7XPo7iwiaM2k44TGlC0sCTduH3n5tnOsld1+os//KcU238m6\nrB8GHPBYKs1rKcuyRFb8hC8Wfvlpgq3t/B6InUpuCnRK1bm4b17GQ9vK3YYqXZTOEfN54giQU0z+\nUqGYg05065AkUV0CjRIIKidj3McwLH2j9yhBlpTxtN7TpAmnUBCeesd3kN/xTp547luBPZieGAkR\n4XBYWc9bSos0Plux047/YdQuX9ZmhhfBWlN5F1hKoSxGKR7Pv8Ho6rRSBzhd0ve5vB+wV9pj6Z6Z\nGeZKLOw9kFpv4YVdmht/izbWrkPRBBAAqAvVg1k7pTvrL8KvjjxCty79vLHpbSxdTxo6pN1MEhnV\ng14b70siTnFqW9ArSBG78hQNKaRblLiOCMwLR1H2b38n6clneO7Nb+W8vsTv//pneLI6mmYOdiRN\nR1J6EkNjzu71a1hOLOcHdjkhUwzBrEnbl77OzxERcqN+YpVSK54SdVLkWMl54cVbt7j9u7c4/s7n\n2Z0X0k5IXqnHA3MybiyldQelZe5v4d4mNttCEh1WpHiKgb8GONQSjQDneY6eb405XcSQqQ2SOi4c\nbp1z86WXscWZnrpOTaHYpRQWi3Hqi9uYknffcgfL+d7yWCrNvWQbUKqu2f2L7lBOgvcYJryBk6YO\nEAs96elI9IsiTVncBd1PTPsz7HA7XJWlTUWWPnRJWz/kdYhVSNBruqthmwmsVTO7J78Jvf4M8sSz\nlKe/mUmf5ey5W9Tf+yyalCmfRcykORYjKRjVEszqrfRsvgLSyoPnFJQUjFZFuVrN6nAmia/8zn9m\nt7/O8sIf8sTZjqUUpvacluocDm2DsHoCBW9rVeZ55ngoWG0wvlnESc2tW5aFxZpFbSCPs/Yn+MpX\nvoLKTMXYBR7d8H2lVKdUH/0fUPsa4ee7yxvKPes5kBXJagjXqFDcjOzzqKPPFlail/+qRy5E3GNs\nR+OdZVUwozYYtcdPswpqjvjCoTpHFNmfsXvqaXT/DDLNQZpsFPZaa8QM7ZzRsziaObgHSoT5iAtq\nceb9dUzOeOKb3sZLnrmxXGf/lrfjKceuLIrLBJqCnTzvqCLhas0TNedIpJqhHlT9KtpQMMFUqSJU\ncXyaIs4h5vGkBEdPPDVdZy7GtaevY/Me9T0sUBanSuJwjObzIgKyABVVR1MrlOvmXAx3pSyC+2p9\nvKFsVnfU0qpBmzu8HCuH84VahMUr6am5sXuaFaqVBWOpAccP9sRDSnC+YSzN+uCl9R9ecFe87eo5\nZ0wcS80F6uW8VsfsGehBd7RCxSOzLaO3ViyyZVnY7/fN1dhRpx1v+47vID0ZSnLjpRc4lsLkzpNP\nPM0XP/sb6AtfBDYctmZZvNpJC1yIGEDateRJMW6zezpxSDNWM3MW6q2baHKOy4Eimd316xScPOU2\nyCmPbjI7UZZyTrp2Lej7NVEl5ve4KSpr4nPKAp64/fJNntidkSxRlyNQkayckbDbt2Lz0FiwX/ri\nl1sj8hbEey8tV6y26bqU0yoAACAASURBVNTZRhJ2ntc+2S8fDjgSI1ESyBy9o+cpU61SKhzKwle+\n+jKy2zFNMzlnpjyPeNQMlpuV47KweJBW+xDjh9FA8A2jNKsEdHzSJqklFYOCcoF6r3nDxteT4rUB\ndXptWWmau5E4HA7sdju++Vu/FX/yCa6//W186WDk/XWeefZZqsFXvvIlbjBjz3wTvPjFE/5BL+y6\nCBR05e/n1pqo5+ekWjmbn8TdWW7f4Eu/93me8opMuSX3ZIW8R5xmo0NLPnsGfeYaduuI37jRmooI\nsAwrXEtQXCRCG2r1gH0BVaeWJapgm+U+1gM3br48iJZb6TFFkhzzMzev9UQqFtbJIUZsyDpGUFPi\naJVlKZyfH8Py5OZG+noN0p4ZnlmOpVGS+jXc75p5MHnDKU031/v9nmrRq1Q0mLKnBUoG3hbJSKzE\nTjm1IqsVEZsbalbRvvTdWY5H9Hpm9/a38vKSSWc7bhvYLcccds+8jeQ3ufEFjy/dyknBW6/FSaIs\nxyO7/T5GiY8mtlCWGywvHHnh1ud4+UsL+XriD377v/BH9EBNlZQCxYuFtofSaoo0huX+/+2dy49l\nWXbWf2vvfc69kY+qarurS7IAIws8YoSMmDVThkwYIZCAAfwBZsBDTBiCJQNDLAYWyAPEBCQPEWpk\nGsk2xqK7jdRtt/tVdndldmVWRNx7z36sxWDt84jIyK6MdJW7qvouKRRSxH2dc/faez2+71u1NNIg\n2G7Pw8c/wxSuuPrgfVKAZVPohYtdStCOaJ4YUOrxkmG8YB9S10arnjPUTFLj+0+ecXV57BuPO02Z\n0dh9TIk1pYbOHJ1VPGOjqp9qQ+8DterNyzTMPRzjeHlJq5FpuiYml3maixcWhIajno+nQi2VXYy9\nhLYt6330uc1nzmm2apreRfbdLNwimoXgMa8/1vFPK/jiJoByfU5H0vauc50y7epIi5FnxdgTHcoe\nXFDdcuHJk+9z+YP3eLMzISGA1F6x8UJFMNAY14kD276FOFltevpH1OdP2e2F4eo5+7fexBZE8ox3\n8+Q/xeTvY35CBEmo1j6+T9fS+Xxd/bdZox5OBKpXHzG0ej+otUqg0aZMmTJtykyTTzujh8BeTl5L\nxPNv3fzQ766JkptiwcNgRw2s+LM5fHv2/nOnMKSE9bzQq6dKM6Vty81VXzxdPoZiwKfTaWYy1+YG\nLd1n7bu0QByGjoqdQ6sNpku8lLyGR2snXMQ8HJlH8Nngipe9yjQviN1uxze/+ns8vHrK23/5i1wx\nkDr+KkTjj7/1B1x96/d5h4YkfIyEGSreWI3SlV7w0GNeWDHEJWQaojMsH++EFBQ5TIRhIIohHelg\nYrRaqfmAXFzw+T/3Dpb2DCTeffcPQJR8OKI//CNOp6PTpGumdSh9Rgk1E0JFckYMTsW5+M0yg8Ko\nxunqmsPhwPX1dZ8Z43K3TT2vmL+DWitrzKvEOKJN+xRt79dYU2IKqKZexVRiApOdl5BL4+rJcywb\nSELijjQMS7hp1ZCSaKcTOhmae1hrs1bB/J1+9MWAT6fT2JxvzDfkxeA10Gku2458sK7VFQh3ADuB\nxVFmNLP13MBNliZKCE4teGs/cvjuH3F4+5vEn3vL31l89N30nf/HY4FGQCT1WTph+b25IG6inW9e\nzw0kcp9oPV8jG07J2z/38wwP36IMkQcPH3N8fo2RiE1JHDk+z05ZEChthaeEXkG0Ygy1EdSwCmNU\npv5xylT44IMPOBwOCxBzVQPSzr58EXkBDvbUPrlhhtc4GtuYDNiUqOdc73A4cZgyIY6UUhnHi40I\nihcHWjamUsi5MtXKOGzUgT6GsGy2T6XTBE9ECJaYF/ScI4gaJl1gItpS0QkhODNSVnjLDMPZ2lLR\nUiWZD7aYTyvvQbCwDEOMKEYbYbSKBqO2xoUo0+mSizLxuUdvkFtF8uAhnarzgLq5Q3i1aebOpICH\nbhI51oYlfFx5qT5GECVWwUYfCqsW2e0GLt56g/r4HY7v/5Dn7z3h2bMPeNQUaUZIFTGHxmjP4ZIq\nlispKO14pJVr9OhgziFG6nQi2ERtcH01cTxktAmhn5DoBAhiDcGnNc8szKxeWhbbUVuhbaA1KskR\nArVh1m4wZIueKHUi54KFgVMxdg/fIOwuqDQHtQ6RUCJX+dLRECkiMfaSfWUz0upjWH2fEqd5oak4\nb2aiBMYlZwnBcVNDSr44q8+5p2kHEdrmC+rzVHoCGzFCmlVn1jidW3Tr7W4Hvmvud49566ff4pu/\n/SVCbjy5vuJiGHkcRqapUFKEiwfspsKuTsh+cMJv7Uos/XpMhBQCBUf4hhBhctybingpN0jfjQuB\ncQ0h08C3v/Z/YPcNZBjZxcAb00QcBlpQoiWsNCegFUVag1ZAG+X9p5TphGjz/AfFaiHXzNXlRGvW\nyV7rBgWdut3n+CAJ7QBSd5aE6zQf/f9BnKrdYS/WlBgipBFs5tgop9Z4+v4l2oSpGo/f/BxxSKg2\nqkqfUVN4/vx6qfC13CBJ3xw/8uX3gn0qnOaldg/4Q9DAtvDpzrJR2+yd5G0i6fCZm7ybBS3QnTRH\nnz/57d/9GvnZJQ8f7XmogBVs2BOGwBBHHn7+TZ7+4bfZI5DMawE9L1vVM1lm7Swo447UNRyG8+I9\nECwEzIQ3987cvMoTUS6ccGACEjCdS8sCtRBaRixTDh9QpiOUxmAC0ZVFtUHOGa0uPrgNV9fTuYMu\nzTb3bW4ed8KD0UPauUDgBQqZL9PE5c07A/NwOrkDZWP38BEypmWTNBVyzstG0Xrex0xTZhP0/iRP\nQrtTJGNbCBBlmXjWsWLOFvzRlzb7mrbGmAaXGeqnSusDiBYm4iwBxSwRtdEe00REsasjwz6iNP9c\nTalaKZqY4ok3fvYdptDYD9FBiJsRe6VrTptA08asrVLKRA6VFCJSq6v837iGSrAKXRutlESuR0zM\nm5kWXF85+6SEYA1KI9oV1Ew7ZvLlc9rku3wYR47Xvmhr9QUZ00hpjRADVld0hSvlrHNiSlOqGaEz\nBGuXlqqdnyQA4kGcpeQM1KZYMnJpZGsYkQ9++D6SduhgXOz2zFrXqg0xoebMdKocrqfe54oQlTSM\nSFPaXP3s1IBzyflOsw1K9dVj2IAszbHbz/MQbKYCiPM1+qPCXKWbaQQz7z8pUcUF1HvJ2qyRdMCq\ncvXdJ+ybj2nPImuEOb/OpkSLgQWBNhfAjaGjjttmNijNRQdDHCh5IrGjiWf1Ut15rTocSMpACIVk\nmdPhmnzw00VPdRkNmHPmeJwWnJ6ZvYBdWz6z+fk3Z2gSvIPlZL2IarmBaJ7vK/iMGoCQIhqtSzYF\ncq6YCSVn0sXDfi9W8Q1tjdPpRMmQ0kgIutFQcEdZ1Et/kk6ahRH5oxQ3b4dlFmitNw7FE0ukLU1L\nkeCCDQ1PV4NgYn1sur9Q6vnMVmVzLhbYRiPaSVVObKutzXh0h+Ikb7gtbFDZgRo7UaYffI+UIpMI\nVDDtUBlrzKMFtxJH9OG2o0Vf1FEoGDGMSEreQY8jhjh+DsXshDRlbJGMkoiE4gjjbJe0rORpIl8f\nnX+Cj83ItfbLUITBhTG0EsKwLMqt2qiZoeYwmqCBqoEQvQJYCl7+Dv5qtRZgIMa0OFGMaami5ZyZ\npkotcDgcUU2kMbmAYdxRcu1ohcbVtY9bL5OfbNbHPYYQyNqcSbqgKeaY7nWc50eXqj9xTvO6FmMk\n9cZmxMAKIYxdmKHLvXrpbPOsu9iankyGtHqlLX0ef77hHW+Za6j+AoilG1JM4nuvJ8zz3+bvsv8s\nRwtruds2iIAXbPDpaY6rciyc0JuHraFWiSiDVaIpAeknytF1pHNmnilqpcu59iFPIc5Tr19827l4\nMu9WDiad+1jrWBEXGQlA6yiKhIosECI/vejXa5TSyLlyfT2Rp0rYDaRhcGrCRtS8VuVwnb3iRnAt\nAVlzS/SOfO+17UdHLJ8Yp7mdu7yyQKAo9HwEEQZRkgSHmGtbRgGaOYYqdm0vs4qqMLdw5qnLEaFo\nJoW0fmnzidPZh1hAg7CC7L3ypdrY6olJr9Cp+UwVx3vNp8mtCoasCOxatb9OQEJFZJ4zOQvn9Z5S\ngBikD5GFoKWHSMXLBiXTasOyOm4M1zMQYq9WzW/d33dqXSfPblwH3Oy/zJK2QZ13RIM2VIfNWPR9\nSf0E6BMSF8EMh/j4vW9VqA1KNnIuhJAYEsgwohG0FloTplPmdCq0Oks+VUISLEUsBErPs8b9CFy/\n2rr5E9gnxmlme5U5Li8bVBt736UGD59iMNdNNiXhEI9gwb/ETULvZDD//5BGmjUqngTPA1WtQ25i\n2C8yqmBYiO5EXqRC5pJ2EDSXpbgALIIWjpZu1OJ6zKVs+DPNixopAVLY7YfNhLaBMqh/tn6y3rx3\ntdMclHy4Xspds9O1VtZeia6TEKbakeDjjpAGCLIKp89gztZ8vIX55mAaKVrYXzzmdMjkaT4tC8M4\n9tOqX1dIaK2IeCRQWiOIh36ny2taab7pmDHsH/SytHBVG9fHA1eXJ06HDDJgGMN+R+2i76X4eMXd\nbkdrH//oQPgEOs2r2IvjLTw8MWDWB/DffSKarCXmJVcRcQWWbim4tnDo6pLE5LlQj+hs84YRWTTI\nNN4UqZDgBQAfDRFuNO5mfTQR6ZCZpb7s/1/yK09yJUDYEOD85yaC4dZdABwdKRhB1YsYt+i8c7PW\nmtLUhywNw27tpm/yAHc0Pz2azZ/Xwy/FOJXMKU8Q5gnSbcHQLeDU6iewQ5w8l3OoTIFWsWbUqSLD\nSAiJWn1w1uF05Hg8knPzk6qr/lT1mTQmEGrgdDr5+7WPKET7tGg5vyzx/zAt55nIlRDGEIkRhuGm\nqMbt54sIGoQgMwxfsCEQLJKp7EMiSESDrHGzuPh2M0GTf644xKVIABAkeXIdE2KCoA6mlgDSlse2\n1ohViUSqKq2zFmd9NpHGMHjjsklzzFyMLneEL07TQBzk5r1TD12snQjD4JTtpsCA0pA49zyMUGEC\njIE0asfFefJuuvJrTGMPJcPmRxGJpDTSql93te4kEn149CbHqGLe/wzSITyNUpSpThxa6EO1lIcP\n9pzyCTUfens4HKkFWlVi2i80gGEYuL6+JvaTcgh3bSD3t8+8lvN2Ctp25orvErYmiNx0mvnvErnx\n/1kW2eVs6UNwtTfj+mllgZpCP9G8qRi2JVlZ5YoWZ4tdrX9WblmS4OLVcnOWKKxoAyeJel4T4xpK\nbs21w/RGN9aXtFLbRAgPUNbm7IyCNnzxWhCCJA8vY11g/MLtQoDncA7KnKtK/tufD366OBXBm53r\nZ1VVrINco7jKf2mVqkZTkDiQc2UcfTOIKVGnwvHgk9ZKFzyXFKFPOMs5r6Idm/eRRVPujkrGK1lv\nkn4IEedPAXTwavYytf+7/rbtaSSrfBA+B035rf/7dWDvp4ApPh6v+KCnqKQB0hBuiGM4DXkk0EgR\nPxGs0Wp22SaMJoZ6IYikjb1EYrjA5AEMOxh2WBqxGIhjhOisQUuBFoA0dO21Tm8GNAjVGqULFLiY\n4HBDxNxp8AND2CEMCMPiVGZt+XJnyoJxAowgY6dyV5+qpo1gSrDKEAS0YGQkNIbBiV+zRFVWz+ey\nNpeAGhQbjIoLWMyde98Q1u9IW8HwRV1aQcNAsUCxgCyhGahVWoVa8FyoNMIQCEPCojFNE5eX1zx9\n+hyrO8rkfJtaphtN5dSp1fPyHhuE8AaH05ZI+PHYp/akma1KYiRTrfD160f893cjX/z8kYtHO0jR\nnScmnFcSCMm85BpnnWA8f5CIhNAlZzuEpec0krruVue6qAQkypLbQAd6yqbJJzfAu3dY6CGR60TP\ngoYximPO4MauuZTEN89/oTRqTi8IaUCrl4hvjwhcn/vhC8t1l30IrKpResjl/S16GNMhLaaoCpTa\nS+Ltpl5bLya0KpxOB3I10sVImWpvFvu0s+Oh8vzZFULilCfSODqVoTvIHKKpfxVe2LHAgYGvfO/7\nXGcliLwmVFN5FS3nT8xJM1d07muD+Ri9YRg4HCf++a99iS99ZyTHR6hmCC7jFGNEo1Kt0aikJIgo\nwRU1uqCeEYdESCNp3BPTCGlAwoDZQG2uRmnWqGSmcFw+h4hQzStbhc4sDO5Eg3cxe+WpE89kIHaq\ndUowjoGU6FK6stEnXndXR26PWBz9NyvQ0ZuFETUhh0gGVAKaEsR1b2ytIQykODrqIbalQmas8zpn\n3opOXrIONRBT8h4KXkI+HZVW57k2iWYRiwmJw6aRGT0EJaFNwITcKo8fv+niIuItgFYDJcPzZxlt\ngzsEK/1gDqGbeEm6afF7knY0Bv73997jVOYyw+uZiCHS+s/LNxWxV5V5/BjsC1/4wkf6eia+qJs8\nZHj2TX7jl/46n//cjmeHI4/jBW2Ykz0fWLTw9GMgDHuIvfIVL1yqFXVllrkvYjOXpS+slJiWqlbw\nsRKbfUhCQ6fiXJXs1OuZi6Jtve3zZnF7XqTvrtXZmF3JxpuuSogDqi72bR0wKX0cYOyLdlbob60h\n6uVYl5IaKMWHQMU4UBdVmMapemlSraHNaJo7QiC4hpl5szbnCWy3fP5jazQi1lzDLOzW+2LB53BO\np0xrwnvPL1EJVDqhzAwtgafvP+Pq6DmYWMCiUa1yMV6QW8Vqc+RGbVhKkIWryfjN734LkYevdbrM\nlJK70oBnT57e+ZxPzEnzUZhjBRsP2on6+Av8o3//FT7QtxnIS6c/RmGIni9YnwgmG8HAgDcqLSYk\njK7i2B835xszRTnays0BT85vqG7CLJHcP58gBMS2ErdrifzOa0ornGfWRQPQWz0JFYdppTQCNwsH\nt8UQVb2BLrIS7/yk5xYIzkXk56llc6jXmodU85Ro35QVoZ+imzK8D5+qtFYwE6ZTWXIxFQ+La61c\nXl9xPEzM5QwjeOU/OgQKGlFgiIlxHEkZnuXK73zvj0njT3We0WomfGjp+HXtM+U04AtZpbIT4398\n78Tf/Gf/kSn+BSSeCJaIYQfDAyCyk0QKidTHeZsE2nBBk45wDkajUUOghkCLkaLCMF4QLy6wNN4I\nKV3mVZfxfJA8DCJStDFZLzuPiZh6tz/44zV6OKey9ppmPn+SsPxeEMbNZSpaa0QFydVPzBBoKDGA\naEFbYdgsKN9ZK0aj1tzzDMhTo5ZVF9uLJAGzSFx6MJ5HqIo3OpOjmasYpskrJYBQkDBAGGgSKUSO\npXGqjUPxytcQR5J4yHY6Np69f+2vQc/frDkS2vBht2rE/UgVY8pXvDsFfvub76ESaWV6gZowa6Z9\nHPaZc5qgqS/egOnEd9tP8zf+8a/xPP3ZXsLtLL80UOOAxoQOgzffQsJCF8uLroYZksfpFj3XqSlS\nU6LEQB3CpkwcfGJYPzFWzS13HumnCqE3RuN8eghpTMReCJC4sknXUR/yQs4396BcjXKdNWlmiwCh\nj0BXn7PJ/Fm6Msx8uvR2ip9MN0vFPvJixZrNf2tVaM1zme3nYAFMzvgz57zUWsmtcioVxUPBqoWp\nFqZp4uryxHRqxLhbv8cUF/WapU1glWNRyvAWX/32u4y7C6TJLQna1zhd7nkifaZymrtsXnStNb78\n7/4O7/CESuAw7BnCDG3XBWkM0EJX0Z81yMZHgMN0fDwdTlqL66wXX2B9l8MXi+TcoR2B2JVSZq6M\nxUz5wTMOhyve+dk/73LrM7ylL9QYI6UeQOoSSnld3Bf9ToRW8saZ1i8/T8fl/aIEWm5LeHXKjVza\nCjvajDVsFmi6cosmLWhVjJE2ndAmlOy5W+v9MNFGDrsuGOhFhZNBCCOtGsfSOEynpThQqUwn7798\n5/uXHE7TBhnufaEQPWcsC55PmUrm3fev+M7717R2E4mxtdtI+aUkf0eNoGIvLUC9LKf51JecP8zm\nhV9r5Rf+9r/mN37lF/nCg+ceWoQuriFyY2yGaiecdQRxFY/NQ4xYYNUNkESLBiEh4ryPGSdm0Efx\ndaX+oN6ki/4YQai7HW8+fIiMI1I9JxD0jqGGwWfKyEyy6iZeAJjxbNtO/rb5i6wnixPMqjdxl1xs\nRXiv0HpvYmp1tqd2Leo5QzMzQuwFBBXH6zV3UII4uqIqtTaOxxNV17K3tkBplelw5HTKvXncT5Xk\nOs5mvcTdlCiVKsbv/+AD3vvhJTXu6XPgeNVg6WV4xdexz1x4dtvmL2oYBnZvfp6/8nf/Dd/TP0No\nR8Y4UAm09AiJe2J6RIgPCWnnMBTxJSxxbVQ2E1IakTggKfbE24sAIt65DkOCGGAYsTTQhoE07Pzv\ndBh/2LN/52fgzZ8ip4EpuL5yM1k4LCveLKBWO3xfHF0QFFUfsOSs04qYYs1/RwRRcV1qFdQm1LKz\nKNV7TDQWCMriUMWVZVo/UYLuiDb0+aL1Zg5nDbWAtkguRjElW3NlTBSCUDpvx2x12jwp5ag8fXLl\nJ1Nvinr/pWGxIaNRqpBMiUw8PzZ+cAk2PCZKIAZuILG39+r23z7yNfVZD89um+Agxl/5F3+Lv/rz\nD5B2JO4e+Vhw8RBqLi07EjiQWTFP1vMd1Gimy4QxVRa6tUjskJQ1ZNs6ArgzDz2hL60RTWnThOYj\nKXtlbCbTgVKKgxSRyV/PFGnVq3gBam4LhXpenHO4V0pB80TOmXHcU/GZNt5wrOTm4z6mU0Hi/sap\nMDNhcs6UPHNgvKx9mGo/1QKkQBgHSnNm5iE3rq4cph9kJDd3OFPh+88uefb+FdaEuqk+ApAiqY/l\nGGKF8JD/+bXvcB0T6aU9mNuSWK9uinV8Hn2Wz2o/ESXnVzEVj2//wT/5D/z6//pjWtyhHZ5C8DKz\n//bEvmmPieeJauIl6ZDmAoCXmb2jn5bdz4Q++GnFt21/JBgm4qLfMZHEhb23ANAVyRyWitnsCMEc\nitOCK01uNQfm3sMMeanmI8xjdFjQTIOYuT0uZF4AofXTRGHRTXCukpeknbbUG5qWliTcrPmMG4XS\nxNV0JAFG1T6Uthqn04njcaLWRtO7p8G14NcwpT1f+t1vUOUBYaaQ3+k3r7+MZ5zhfZA3P3FOEzqt\nV0X5p//qP/Nv/9PvwW5g3CX2Y8KCkSSQ0tgh+r4wogWSRR8M1cSRt93BCIlmK+0Aegcbo1jzkyum\n5YeYkPEhRQRLF9RYqakiuwFJAw2HicyJ9oyRC8GVYZxZbOzMqc5tKr3nsfZSUCMQaUXh1NAQIV3Q\nYkSJXdsg+nRpc8KbqSAVkgmjCbG3gnJumKbeEJ1zHCNTaVF8PHqKHEumaqHUiVorU3VHLC3TTDlN\nletDIU/Ww1m7cb/mMDQWGMc9X/7qd2n7N2ih9ELIHbKz9zTrqIIOTqAJ1ECnZ7+afeYLAbfNdypH\ns05h5Ff/65c5Ho/84t//Ig8fPsQs05YJaAFrjkcDqLGDD2FVlKRTBsS6XN7Nvg1G75/4eD+RztmM\nAXqRIMqA1UptShhGJHli30xpur7mfMLMQH1ThXqTwLbM4uk9F7rw4QeHA6UU3n77bf9QHZc2nQpx\nNzjEZbOH3hDFsIDNqwyWbu0y0U0CtShZjaZCaUZpPm8m18xUMq1GDqeJw6FQ8opLow/NWmA3+4DY\nwO/8wbto3CHm0iJBX3bK3M/m/u0yIfw17Ccup3mZ/aW/+Da/+sv/kM89hKtjQWQeq20MfeR2znkJ\nmZYvfUPjrbX2kISVgm19cOt4k6YQ0gPA5VWjGHo6gWVCy+jVNZInaJlYnEE5I4uRSjIfJNVaWeAy\nqopVWxwn5+zNz14SL2IL5aC02vszieMhY8EoNTi8v7moxqJ42RK5KmilalgEOFozrouX8lNKTPlI\nE7g8FIoFWlBqMawal8fM9fWRWoQ8VQ5d8G8YIsQ9QSJpiJQpc0gDX/n6H9LSI6dgUJeez8dhcyh7\nlz19endOc3aabruHj/iZofLr/+WXuMrfZZcuetwemGaIzQJlWZ0m5q79LELrOgPbcRozMnc+PZbn\n97Hk3uEXNE9omQilYIcryAXqhOVDhwcJrVR3quK9nBKVpqtWm1YDVUprWC87H05HLnZ7ZAx9yGul\nNK+itSqoCietHWXcy8wLLwWqjUuZWiy4qqUWz08s0JrD9A8nd5rTVMkqTHVCW2CaCh8cJ3ItCCNX\nVwdyE2YFEhFxRIQCEvjNb/0QM4c5/WnY6zjNT1x49jI7Ha74Vhn5hb/29/jSf/uXjKOPp1Ar7MNc\nVhZaK56Ud0i8DFDnRWYZM1d1cWcIG0WVRIgJowt4JJ8eLQKtHEkRkjlQkcFJdUrF2sQQhVwr+33A\npglokCvSXIE/aqBqI/SpaqModHbp1eE90u5zaG6EBiFHdlI6QHP0zr4qqoVoRgvZHdoiZhHTA1HA\ndCIyoPisaBXIrfjEsc55aa2SxKjlSFIouRJrw7rAR+yKoTFsJjwnKCbIg5/it776DSTtkY8gDPs4\n7XzS3DDFSAQmgmRUjEBdMFXwoj7BjcRU1nmPOocULxGvux2fexOy5yy2Pk/uIOWEnlTIHUH+8v6b\n0xEcobA8ZtnGN4jsDvmxzWDZG59bdL2m7TWYLGKndwkL3pB776+lN9iVPRMU7gzDXoFI+SeybT51\n2548eXLn388nzWK+WIKpz0ixCzCn/r6wNl/2Jd719w997BzAwSyPNledlcDLWhM/KineLvsFUiJ3\nOc3Lnrk+drtJvLB4xcUGZ53SpatvG6fdOHGw+T1uv87Nqpi5/unyki+DwPy47MfqNPft1s4wj61s\n6l2v+bL/fcin8fcQgIrMi0zWL/5ltgVVvqr5Lh0WOD3wwucOdGSzbK6dlZi2vNbmvsy24K6WE863\nbG1GChtFz82KvPP5GxzXTATz/4XF8QPczEG2j5mvZb6sjb5yiE5R4PbpfcuxPk6HuX3fXsV+rE7z\nOkzND3ve676m27zLrkr12Byy/IjPs8DQlTXwuIs2u9nF58VsUPXlu2k2bpxWOr/CC7s+i8iH6hpI\nLcHRfHqJonOYxfA2rgAAANRJREFUtPGnsHkfXfN0mE+NcPMxt6/tlW/7AqYOqOkd+cvrd/f/tOzH\nmtOc7WyfRvtku/TZzvYJtLPTnO1s97Sz05ztbPe0s9Oc7Wz3tLPTnO1s97Sz05ztbPe0s9Oc7Wz3\ntLPTnO1s97Sz05ztbPe0s9Oc7Wz3tLPTnO1s97Sz05ztbPe0s9Oc7Wz3tLPTnO1s97Sz05ztbPe0\ns9Oc7Wz3tLPTnO1s97Sz05ztbPe0s9Oc7Wz3tLPTnO1s97Sz05ztbPe0s9Oc7Wz3tLPTnO1s97T/\nD6FsNXgSNtiqAAAAAElFTkSuQmCC\n","text/plain":["<Figure size 216x216 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"metadata":{"id":"LeZJGwMVn94n","colab_type":"text"},"cell_type":"markdown","source":["Let's see some details:"]},{"metadata":{"id":"xcMDZhoiuhGz","colab_type":"code","outputId":"c83349c7-ee07-4ec3-a43d-134a6e0ab5db","executionInfo":{"status":"ok","timestamp":1554419580303,"user_tz":-120,"elapsed":617,"user":{"displayName":"Cristian R. Munteanu","photoUrl":"https://lh5.googleusercontent.com/-ndtLWHZnMEE/AAAAAAAAAAI/AAAAAAAAP2o/y_loIBY9sZc/s64/photo.jpg","userId":"15479904655347951310"}},"colab":{"base_uri":"https://localhost:8080/","height":35}},"cell_type":"code","source":["pred_class, pred_idx, outputs = learn.predict(img)\n","print(\"* Predicted class:\",pred_class)"],"execution_count":10,"outputs":[{"output_type":"stream","text":["* Predicted class: polyps\n"],"name":"stdout"}]},{"metadata":{"id":"-Q3a_2gH0Pud","colab_type":"code","outputId":"74e67e13-508c-4943-f712-37abce51322f","executionInfo":{"status":"ok","timestamp":1554419623043,"user_tz":-120,"elapsed":619,"user":{"displayName":"Cristian R. Munteanu","photoUrl":"https://lh5.googleusercontent.com/-ndtLWHZnMEE/AAAAAAAAAAI/AAAAAAAAP2o/y_loIBY9sZc/s64/photo.jpg","userId":"15479904655347951310"}},"colab":{"base_uri":"https://localhost:8080/","height":54}},"cell_type":"code","source":["print('* List with classes:', classes)\n","print('* Prediction probabilities by class:',outputs)"],"execution_count":11,"outputs":[{"output_type":"stream","text":["* List with classes: ['non_polyps', 'polyps']\n","* Prediction probabilities by class: tensor([0.0905, 0.9095])\n"],"name":"stdout"}]},{"metadata":{"id":"fQnBdxjP218R","colab_type":"text"},"cell_type":"markdown","source":["Have fun with DL!\n","\n","@[muntisa](https://sites.google.com/site/muntisa/)"]}]}