{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-10-17T16:15:55.024178Z","iopub.execute_input":"2023-10-17T16:15:55.025407Z","iopub.status.idle":"2023-10-17T16:15:55.030765Z","shell.execute_reply.started":"2023-10-17T16:15:55.025373Z","shell.execute_reply":"2023-10-17T16:15:55.029214Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Detecting Ships using Satellite Images with Deep Learning**\n# # **Project Name: Ship Detection from Satellite Imagery**\n","metadata":{}},{"cell_type":"markdown","source":"Workflow of this notebook\n1) Introducing Dataset\n2) Quick guide on Object Detection, Image Classification and Segmentation\n3) Importing necessary libraries and modules for this notebook\n4) Exploring the Dataset\n5) Grasping the idea of Run Length Encoding and Decoding\n6) Preparing data for our model\n7) Brief introduction to UNET model\n8) Build and train UNET model","metadata":{}},{"cell_type":"markdown","source":"## Dataset & Aim<a class=\"anchor\"  id=\"h1\"></a>\n    \n<img src = \"https://eoimages.gsfc.nasa.gov/images/imagerecords/2000/2938/SinkingShip_10_15_02_lrg.jpg\" width = 35%>  \n       \n- We will be dealing with [this dataset](https://www.kaggle.com/competitions/airbus-ship-detection).\n- Search \"Airbus Ship Detection Dataset\".\n- It consists of train and test image folders along with sample_submission and train_ship_segmentation csv files.\n- Soon we will jump into more details of these files.\n- We will build and train UNET model from scratch for image segmentaion.\n\n## Image Classification, Object Detection and Semantic Segmentation <a class=\"anchor\"  id=\"h2\"></a>\n\n- If you are new to computer vision then these terms may confuse you.\n- These are some of the most common applications of machine learning in computer vision.\n- Below is a quick guide before we start exploring our data.\n\n<img src = \"https://i1.wp.com/bdtechtalks.com/wp-content/uploads/2021/05/image-classification-vs-object-detection-vs-semantic-segmentation.jpg\" width = 65%>\n\n* **Image Classificaton:-** Determines whether a certain type of object is present in an image or not.    \n* **Object Detection:-** Object detection takes image classification one step further and provides the bounding box where detected objects are located.        \n* **Semantic Segmentation:-** Specifies the object class of each pixel in an input image. This is what we are targeting in this notebook!  \n* **Instance Segmentation:-** Separates individual instances of each type of object.\n\nThe images below and above shall help you visualize these ideas.\n\n<img src = \"https://deeplobe.ai/wp-content/uploads/2021/05/SENTIMENT-ANALYSIS-1024x683.png\" width = 65%>\n\n*You can read more about it over <u>[here](https://venturebeat.com/ai/new-deep-learning-model-brings-image-segmentation-to-edge-devices/)</u>.*\n\n## Importing libraries and modules needed for this notebook <a class=\"anchor\"  id=\"h2.5\"></a>","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')\n\nimport os\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom skimage.io import imread\nfrom skimage.segmentation import mark_boundaries\nfrom skimage.util import montage\nfrom skimage.morphology import label\n\nimport gc\ngc.enable()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:15:55.032808Z","iopub.execute_input":"2023-10-17T16:15:55.033242Z","iopub.status.idle":"2023-10-17T16:15:55.043505Z","shell.execute_reply.started":"2023-10-17T16:15:55.033203Z","shell.execute_reply":"2023-10-17T16:15:55.042673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Documents of the above used libraries and modules in case you aren't familiar and want to know more about it:-**\n- [os](https://docs.python.org/3/library/os.html)\n- [numpy](https://numpy.org/doc/1.23/user/absolute_beginners.html)\n- [pandas](https://pandas.pydata.org/docs/user_guide/index.html#user-guide)\n- [seaborn](https://seaborn.pydata.org/tutorial/introduction.html)\n- [matplotlib.pyplot](https://matplotlib.org/stable/tutorials/introductory/pyplot.html)\n- [skimage.io.imread](https://scikit-image.org/docs/stable/api/skimage.io.html#skimage.io.imread)\n- [skimage.segmentation.mark_boundaries](https://scikit-image.org/docs/stable/api/skimage.segmentation.html#skimage.segmentation.mark_boundaries)\n- [skimage.util.montage](https://scikit-image.org/docs/stable/api/skimage.util.html#skimage.util.montage)\n- [skimage.morphology.label](https://scikit-image.org/docs/stable/api/skimage.morphology.html#skimage.morphology.label)\n- [gc.enable()](https://docs.python.org/3/library/gc.html)\n","metadata":{}},{"cell_type":"markdown","source":"EDA\n## Exploring the data <a class=\"anchor\"  id=\"h3\"></a>","metadata":{}},{"cell_type":"code","source":"train_image_dir = '/kaggle/input/airbus-ship-detection/train_v2'","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:55:47.282441Z","iopub.execute_input":"2023-10-17T16:55:47.282843Z","iopub.status.idle":"2023-10-17T16:55:47.287745Z","shell.execute_reply.started":"2023-10-17T16:55:47.282812Z","shell.execute_reply":"2023-10-17T16:55:47.286673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_images = os.listdir(train_image_dir)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:55:54.226945Z","iopub.execute_input":"2023-10-17T16:55:54.227371Z","iopub.status.idle":"2023-10-17T16:55:55.698430Z","shell.execute_reply.started":"2023-10-17T16:55:54.227342Z","shell.execute_reply":"2023-10-17T16:55:55.696916Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_images.sort()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:54:14.853181Z","iopub.execute_input":"2023-10-17T16:54:14.853556Z","iopub.status.idle":"2023-10-17T16:54:14.985166Z","shell.execute_reply.started":"2023-10-17T16:54:14.853528Z","shell.execute_reply":"2023-10-17T16:54:14.983754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Total of {len(train_images)}images in train directory.\\nHere is how first 5 train_images looks like:- {train_images[:5]}\") ","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:54:24.501408Z","iopub.execute_input":"2023-10-17T16:54:24.501910Z","iopub.status.idle":"2023-10-17T16:54:24.509805Z","shell.execute_reply.started":"2023-10-17T16:54:24.501846Z","shell.execute_reply":"2023-10-17T16:54:24.508729Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_ids = [file for file in os.listdir(train_image_dir) if file.endswith('.jpg')]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(image_ids)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:41:04.260674Z","iopub.execute_input":"2023-10-17T16:41:04.261098Z","iopub.status.idle":"2023-10-17T16:41:04.268629Z","shell.execute_reply.started":"2023-10-17T16:41:04.261067Z","shell.execute_reply":"2023-10-17T16:41:04.267555Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_ids[0]","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:41:18.133145Z","iopub.execute_input":"2023-10-17T16:41:18.133488Z","iopub.status.idle":"2023-10-17T16:41:18.140251Z","shell.execute_reply.started":"2023-10-17T16:41:18.133462Z","shell.execute_reply":"2023-10-17T16:41:18.139224Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"masks = pd.read_csv('/kaggle/input/airbus-ship-detection/train_ship_segmentations_v2.csv')","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:51:38.312350Z","iopub.execute_input":"2023-10-17T16:51:38.312753Z","iopub.status.idle":"2023-10-17T16:51:39.567550Z","shell.execute_reply.started":"2023-10-17T16:51:38.312723Z","shell.execute_reply":"2023-10-17T16:51:39.566141Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"masks.head()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:52:04.513894Z","iopub.execute_input":"2023-10-17T16:52:04.514272Z","iopub.status.idle":"2023-10-17T16:52:04.540059Z","shell.execute_reply.started":"2023-10-17T16:52:04.514245Z","shell.execute_reply":"2023-10-17T16:52:04.538950Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Filter the DataFrame\nfiltered_df = masks[masks['ImageId'].isin(image_ids)]","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:57:13.842251Z","iopub.execute_input":"2023-10-17T16:57:13.842654Z","iopub.status.idle":"2023-10-17T16:57:14.021056Z","shell.execute_reply.started":"2023-10-17T16:57:13.842626Z","shell.execute_reply":"2023-10-17T16:57:14.019702Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filtered_df.info()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:57:42.757820Z","iopub.execute_input":"2023-10-17T16:57:42.758231Z","iopub.status.idle":"2023-10-17T16:57:42.821078Z","shell.execute_reply.started":"2023-10-17T16:57:42.758200Z","shell.execute_reply":"2023-10-17T16:57:42.819742Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filtered_df","metadata":{"execution":{"iopub.status.busy":"2023-10-17T16:58:44.755568Z","iopub.execute_input":"2023-10-17T16:58:44.755958Z","iopub.status.idle":"2023-10-17T16:58:44.772051Z","shell.execute_reply.started":"2023-10-17T16:58:44.755929Z","shell.execute_reply":"2023-10-17T16:58:44.770592Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- Here, we can see some image ids are repeated. That is because we are given masks for each ship in one image.\n- This simply means that number of ships in train image = total of repeated image ids in this masks data frame.\n- NaN simply means that there are no ships in that image.\n- **We can combine this masks into one image for same image ids.**\n- Before that we need to make ourselves comfortable with this encoded format.\n\n## Run Length Encoding (RLE) and Decoding <a class=\"anchor\"  id=\"h4\"></a>\n- Run length encoding is a lossless compression.\n- Lossless compression allows the original data to be perfectly reconstructed from the compressed data.\n- We simply run through the data and count how many times each data point is repeated without any breaks.\n- Consider a small example below to grasp this idea:-\n\n<img src = \"https://img.api.video/1628663040-run-length.png?auto=format&dpr=1&fm=jpg&w=1370\" width = 35%>\n\n- We tend to use RLE for data that contains long runs of the same value.\n- If your data is complex without long runs then RLE can result in negative compression.\n- There are many variations to it - run accross rows, run accross columns, run until pixel changes, etc.\n- We also need to decompress the RLE data using run length decoding in order to use it.\n\n**Image example to understand it in a better way:-**    \n- Let black pixels be 1 and white pixels be 0 in 10x10 image shown below.     \n\n<img src=\"https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcScKG8WJQhjdfUJU2-BBnj7UAgaoF3tK4CZYLRvSjcqjA6H-2BwIwFa3AXRb_Bt2WR5qi4&usqp=CAU\" width = 35%>         ","metadata":{}},{"cell_type":"code","source":"row_rle = ['10 1',\n           '4 1 2 0 4 1',\n           '3 1 4 0 3 1',\n           '2 1 6 0 2 1',\n           '1 1 2 0 1 1 2 0 1 1 2 0 1 1',\n           '1 1 8 0 1 1',\n           '3 1 1 0 2 1 1 0 3 1',\n           '2 1 1 0 1 1 2 0 1 1 1 0 2 1',\n           '1 1 1 0 1 1 1 0 2 1 1 0 1 1 1 0 1 1',\n           '10 1',\n           'Total']\n","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:00:36.824616Z","iopub.execute_input":"2023-10-17T17:00:36.825021Z","iopub.status.idle":"2023-10-17T17:00:36.830372Z","shell.execute_reply.started":"2023-10-17T17:00:36.824989Z","shell.execute_reply":"2023-10-17T17:00:36.829285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pixels = [len(row.split(\" \")) for row in row_rle if row != 'Total']\nsum_pixels = np.array(pixels).sum()\npixels.append(sum_pixels)\n\ndata = {\n    'Row - RLE' : row_rle,\n    'Pixels' : pixels\n}\n\nrle_df = pd.DataFrame(data)\nrle_df.index+=1\nrle_df","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:01:04.378054Z","iopub.execute_input":"2023-10-17T17:01:04.378435Z","iopub.status.idle":"2023-10-17T17:01:04.395852Z","shell.execute_reply.started":"2023-10-17T17:01:04.378406Z","shell.execute_reply":"2023-10-17T17:01:04.394634Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Clearly we have compressed 100 data points into 84 data points.\nSome rows like 5, 8 and 14 gave more data points after encoding than it was in original.\nReason being short runs as there were multiple breaks between black and white pixels.\nWe can now apply this idea onto our data!","metadata":{}},{"cell_type":"code","source":"# Let us now see how it works for Image id:- 0005d01c8.jpg we have in the mask data frame\n\n# Original image from training set\nimg_arr = imread(train_image_dir + '/' + '0b0f83f31.jpg')\nplt.figure(figsize=(15,8))\nplt.imshow(img_arr)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:02:35.558127Z","iopub.execute_input":"2023-10-17T17:02:35.558504Z","iopub.status.idle":"2023-10-17T17:02:36.259889Z","shell.execute_reply.started":"2023-10-17T17:02:35.558478Z","shell.execute_reply":"2023-10-17T17:02:36.258046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_arr.shape","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:02:56.766837Z","iopub.execute_input":"2023-10-17T17:02:56.767262Z","iopub.status.idle":"2023-10-17T17:02:56.773641Z","shell.execute_reply.started":"2023-10-17T17:02:56.767232Z","shell.execute_reply":"2023-10-17T17:02:56.772534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Filter out all 0005d01c8.jpg image ids and respective encoded data\n# 2 ships means 2 same image ids will be there!\nrle_0 = masks.query('ImageId==\"0b0f83f31.jpg\"')['EncodedPixels']\nrle_0","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:03:23.371368Z","iopub.execute_input":"2023-10-17T17:03:23.372116Z","iopub.status.idle":"2023-10-17T17:03:23.394080Z","shell.execute_reply.started":"2023-10-17T17:03:23.372059Z","shell.execute_reply":"2023-10-17T17:03:23.392961Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Make a list of each mask shown above also visualise whats happening!\nmask_lst, ct = [], 1\nfor mask in rle_0:\n    print(f\"Mask {ct} -\\n{mask}\\n\\n\")\n    mask_lst.append(mask)\n    ct+=1","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:03:56.778610Z","iopub.execute_input":"2023-10-17T17:03:56.779186Z","iopub.status.idle":"2023-10-17T17:03:56.786558Z","shell.execute_reply.started":"2023-10-17T17:03:56.779142Z","shell.execute_reply":"2023-10-17T17:03:56.785074Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Split and Display how the first mask in the list looks like\nsplit = mask_lst[0].split()\nprint(split)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:04:23.467661Z","iopub.execute_input":"2023-10-17T17:04:23.468078Z","iopub.status.idle":"2023-10-17T17:04:23.473824Z","shell.execute_reply.started":"2023-10-17T17:04:23.468048Z","shell.execute_reply":"2023-10-17T17:04:23.472704Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- This data shows start_pixels and lenghts where we can think ship to exist in the original image.\n- For example, 56777 3 shows that pixels 56777, 56778, 56779 contributes to the ship.\n- Our target is to create an image with these pixels labeled as 1 and remaining as 0.\n- This is how we can produce a mask for respective image.","metadata":{}},{"cell_type":"code","source":"# Grab all the starting pixels and lenghts and convert it into integers using numpy\nstarts, lengths = [np.array(x, dtype = int) for x in (split[::2], split[1::2])]\nstarts, lengths","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:05:04.943288Z","iopub.execute_input":"2023-10-17T17:05:04.945464Z","iopub.status.idle":"2023-10-17T17:05:04.959368Z","shell.execute_reply.started":"2023-10-17T17:05:04.945420Z","shell.execute_reply":"2023-10-17T17:05:04.958121Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Get the ending pixels.\n'''Examples:-\n56010 1 ---> Starts at 56010 and ends at 56010\n56777 3 ---> Starts at 56777 and ends at 56779\n57544 6 ---> Starts at 57544 and ends at 57549'''\nends = starts + lengths - 1\npd.DataFrame({\n    'Starts' : starts,\n    'Lengths' : lengths,\n    'Ends' : ends\n}).head(10)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:05:23.673493Z","iopub.execute_input":"2023-10-17T17:05:23.673893Z","iopub.status.idle":"2023-10-17T17:05:23.707424Z","shell.execute_reply.started":"2023-10-17T17:05:23.673849Z","shell.execute_reply":"2023-10-17T17:05:23.706057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create 1s in place of these pixels and rest should be 0\nimg = np.zeros(768*768, dtype = np.uint8)\nfor start, end in zip(starts, ends):\n    img[start:end+1] = 1","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:05:49.403977Z","iopub.execute_input":"2023-10-17T17:05:49.404365Z","iopub.status.idle":"2023-10-17T17:05:49.411758Z","shell.execute_reply.started":"2023-10-17T17:05:49.404337Z","shell.execute_reply":"2023-10-17T17:05:49.410320Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Check how output looks\nimg[408756:408762] # Should output 0, 1 , 1, 1 ,0 as we know 56777, 56778, 56779 ---> 1 and 5676, 56780 ---> 0","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:06:15.868259Z","iopub.execute_input":"2023-10-17T17:06:15.868708Z","iopub.status.idle":"2023-10-17T17:06:15.876362Z","shell.execute_reply.started":"2023-10-17T17:06:15.868666Z","shell.execute_reply":"2023-10-17T17:06:15.874822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Copy-Paste this idea for another ship in the image\nsplit_1 = mask_lst[0].split()                                                                # Split the mask into start_pixels and lengths\nstarts, lengths = [np.array(x, dtype = int) for x in (split_1[0:][::2], split_1[1:][::2])]   # Generate arrays from only starts and lengths\nends = starts + lengths - 1                                                                  # Start pixel to end pixel will be start - 1 + length\nimg1 = np.zeros(768*768, dtype = np.uint8)                                                   # 1D array containing all zeros\nfor start, end in zip(starts, ends):                                                         # For each start to end pair\n    img1[start:end+1] = 1                                                                    # Convert the values from 0 to 1","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:06:41.852473Z","iopub.execute_input":"2023-10-17T17:06:41.852916Z","iopub.status.idle":"2023-10-17T17:06:41.863037Z","shell.execute_reply.started":"2023-10-17T17:06:41.852842Z","shell.execute_reply":"2023-10-17T17:06:41.860895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Reshaping both the ship masks and combining it to form the final mask!\nimg = img.reshape(768, 768)\nimg1 = img1.reshape(768, 768)\nfinal = img+img1\nprint(final, '\\n\\n', final.shape, '\\n\\n', final.ndim)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:07:05.250958Z","iopub.execute_input":"2023-10-17T17:07:05.251373Z","iopub.status.idle":"2023-10-17T17:07:05.261585Z","shell.execute_reply.started":"2023-10-17T17:07:05.251344Z","shell.execute_reply":"2023-10-17T17:07:05.259673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Expand dimension of this array to have only 1 channel in the mask and visualise original and final mask\nfinal = np.expand_dims(final, -1) # -1 means the last available dimenstion, in this case it is 2. Hence, on axis = 2 we will get 1.\noriginal = imread(train_image_dir + '/' + '0b0f83f31.jpg')\nplt.figure(figsize=(15, 8))\nplt.subplot(1, 2, 1)\nplt.title(f\"Original - Train Image, {original.shape}\")\nplt.imshow(original)\nplt.subplot(1, 2, 2)\nplt.title(f\"Mask generated from the RLE data for each ship, {final.shape}\")\nplt.imshow(final, cmap = \"gray\")\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:07:26.189694Z","iopub.execute_input":"2023-10-17T17:07:26.190126Z","iopub.status.idle":"2023-10-17T17:07:27.373816Z","shell.execute_reply.started":"2023-10-17T17:07:26.190097Z","shell.execute_reply":"2023-10-17T17:07:27.372429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- Oh, something is off!\n- Our mask needs to be transposed.","metadata":{}},{"cell_type":"code","source":"# Copy Paste the code from the prev cell with one change - Transpose!\nimg = img.reshape(768, 768).T     # Transpose the first ship mask\nimg1 = img1.reshape(768, 768).T   # Transpose the second ship mask\nfinal = img+img1                  # Generate the final mask with two ships\nfinal = np.expand_dims(final, -1)\nplt.figure(figsize=(15, 8))\nplt.subplot(1, 2, 1)\nplt.title(f\"Original - Train Image, {original.shape}\")\nplt.imshow(original)\nplt.subplot(1, 2, 2)\nplt.title(f\"Mask generated from the RLE data for each ship, {final.shape}\")\nplt.imshow(final, cmap = \"Blues_r\")\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:08:11.539935Z","iopub.execute_input":"2023-10-17T17:08:11.541088Z","iopub.status.idle":"2023-10-17T17:08:13.018725Z","shell.execute_reply.started":"2023-10-17T17:08:11.541030Z","shell.execute_reply":"2023-10-17T17:08:13.017942Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- So this is how the EncodedPixels data for one image id looks like!\n- We can build a function that can quickly generate such masks for all the EncodedPixels wrt to its ImageId.","metadata":{}},{"cell_type":"code","source":"# Define functions to do these tasks for all the training images\ndef rle_decode(mask_rle, shape=(768,768)):\n    '''\n    Input arguments -\n    mask_rle: Mask of one ship in the train image\n    shape: Output shape of the image array\n    '''\n    s = mask_rle.split()                                                               # Split the mask of each ship that is in RLE format\n    starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]     # Get the start pixels and lengths for which image has ship\n    ends = starts + lengths - 1                                                        # Get the end pixels where we need to stop\n    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)                                  # A 1D vec full of zeros of size = 768*768\n    for lo, hi in zip(starts, ends):                                                   # For each start to end pixels where ship exists\n        img[lo:hi+1] = 1                                                               # Fill those values with 1 in the main 1D vector\n    '''\n    Returns -\n    Transposed array of the mask: Contains 1s and 0s. 1 for ship and 0 for background\n    '''\n    return img.reshape(shape).T\n\ndef masks_as_image(in_mask_list):\n    '''\n    Input -\n    in_mask_list: List of the masks of each ship in one whole training image\n    '''\n    all_masks = np.zeros((768, 768), dtype = np.int16)                                 # Creating 0s for the background\n    for mask in in_mask_list:                                                          # For each ship rle data in the list of mask rle\n        if isinstance(mask, str):                                                      # If the datatype is string\n            all_masks += rle_decode(mask)                                              # Use rle_decode to create one mask for whole image\n    '''\n    Returns -\n    Full mask of the training image whose RLE data has been passed as an input\n    '''\n    return np.expand_dims(all_masks, -1)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:09:04.719194Z","iopub.execute_input":"2023-10-17T17:09:04.719584Z","iopub.status.idle":"2023-10-17T17:09:04.730512Z","shell.execute_reply.started":"2023-10-17T17:09:04.719546Z","shell.execute_reply":"2023-10-17T17:09:04.729311Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Preparing Train and Validation Data","metadata":{}},{"cell_type":"code","source":"masks = filtered_df","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:12:24.349962Z","iopub.execute_input":"2023-10-17T17:12:24.350539Z","iopub.status.idle":"2023-10-17T17:12:24.357017Z","shell.execute_reply.started":"2023-10-17T17:12:24.350503Z","shell.execute_reply":"2023-10-17T17:12:24.355474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''Note that NaN values in the EncodedPixels are of float type and everything else is a string type'''\n\n# Add a new feature to the masks data frame named as ship. If Encoded pixel in any row is a string, there is a ship else there isn't.\nmasks['ships'] = masks['EncodedPixels'].map(lambda c_row: 1 if isinstance(c_row, str) else 0)\nmasks.head(9)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:12:42.187558Z","iopub.execute_input":"2023-10-17T17:12:42.187938Z","iopub.status.idle":"2023-10-17T17:12:42.396528Z","shell.execute_reply.started":"2023-10-17T17:12:42.187897Z","shell.execute_reply":"2023-10-17T17:12:42.395578Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Making a new data frame with unique image ids where we are summing up the ship counts\nunique_img_ids = masks.groupby('ImageId').agg({'ships': 'sum'}).reset_index()\nunique_img_ids.index+=1 # Incrimenting all the index by 1\nunique_img_ids.head(25)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:13:23.152455Z","iopub.execute_input":"2023-10-17T17:13:23.153034Z","iopub.status.idle":"2023-10-17T17:13:23.367586Z","shell.execute_reply.started":"2023-10-17T17:13:23.152997Z","shell.execute_reply":"2023-10-17T17:13:23.366465Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Adding two new features to unique_img_ids data frame. If ship exists in image, val is 1 else 0. And it's vec form\nunique_img_ids['has_ship'] = unique_img_ids['ships'].map(lambda x: 1.0 if x>0 else 0.0)\nunique_img_ids.head(25)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:13:46.440091Z","iopub.execute_input":"2023-10-17T17:13:46.440456Z","iopub.status.idle":"2023-10-17T17:13:46.494798Z","shell.execute_reply.started":"2023-10-17T17:13:46.440430Z","shell.execute_reply":"2023-10-17T17:13:46.493736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Also, retrive the old masks data frame\nmasks.drop(['ships'], axis=1, inplace=True)\nmasks.index+=1\nmasks.head()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:14:05.251930Z","iopub.execute_input":"2023-10-17T17:14:05.252283Z","iopub.status.idle":"2023-10-17T17:14:05.281341Z","shell.execute_reply.started":"2023-10-17T17:14:05.252257Z","shell.execute_reply":"2023-10-17T17:14:05.279862Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- Now, its the time to use the train_test_split.\n- Stratify to split the dataset into train and test sets in a way that preserves the same proportions of examples in each class as observed in the original dataset.","metadata":{}},{"cell_type":"code","source":"# Train - Test split\nfrom sklearn.model_selection import train_test_split\ntrain_ids, valid_ids = train_test_split(unique_img_ids, test_size = 0.01)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:15:41.562456Z","iopub.execute_input":"2023-10-17T17:15:41.562918Z","iopub.status.idle":"2023-10-17T17:15:41.881741Z","shell.execute_reply.started":"2023-10-17T17:15:41.562854Z","shell.execute_reply":"2023-10-17T17:15:41.880382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create train data frame\ntrain_df = pd.merge(masks, train_ids)\n\n# Create test data frame\nvalid_df = pd.merge(masks, valid_ids)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:16:04.429242Z","iopub.execute_input":"2023-10-17T17:16:04.429858Z","iopub.status.idle":"2023-10-17T17:16:04.776603Z","shell.execute_reply.started":"2023-10-17T17:16:04.429820Z","shell.execute_reply":"2023-10-17T17:16:04.774723Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"There are ~\")\nprint(train_df.shape[0], 'training masks,')\nprint(valid_df.shape[0], 'validation masks.')","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:16:25.219473Z","iopub.execute_input":"2023-10-17T17:16:25.219897Z","iopub.status.idle":"2023-10-17T17:16:25.225606Z","shell.execute_reply.started":"2023-10-17T17:16:25.219845Z","shell.execute_reply":"2023-10-17T17:16:25.224514Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Parameters\nBATCH_SIZE = 4                 # Train batch size\nEDGE_CROP = 16                 # While building the model\nNB_EPOCHS = 5                  # Training epochs\nGAUSSIAN_NOISE = 0.1           # To be used in a layer in the model\nUPSAMPLE_MODE = 'SIMPLE'       # SIMPLE ==> UpSampling2D, else Conv2DTranspose\nNET_SCALING = None             # Downsampling inside the network\nIMG_SCALING = (1, 1)           # Downsampling in preprocessing\nVALID_IMG_COUNT = 400          # Valid batch size\nMAX_TRAIN_STEPS = 200          # Maximum number of steps_per_epoch in training","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:16:50.518598Z","iopub.execute_input":"2023-10-17T17:16:50.519024Z","iopub.status.idle":"2023-10-17T17:16:50.525222Z","shell.execute_reply.started":"2023-10-17T17:16:50.518995Z","shell.execute_reply":"2023-10-17T17:16:50.524125Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Image and Mask Generator\ndef make_image_gen(in_df, batch_size = BATCH_SIZE):\n    '''\n    Inputs -\n    in_df - data frame on which the function will be applied\n    batch_size - number of training examples in one iteration\n    '''\n    all_batches = list(in_df.groupby('ImageId'))                             # Group ImageIds and create list of that dataframe\n    out_rgb = []                                                             # Image list\n    out_mask = []                                                            # Mask list\n    while True:                                                              # Loop for every data\n        np.random.shuffle(all_batches)                                       # Shuffling the data\n        for c_img_id, c_masks in all_batches:                                # For img_id and msk_rle in all_batches\n            rgb_path = os.path.join(train_image_dir, c_img_id)               # Get the img path\n            c_img = imread(rgb_path)                                         # img array\n            c_mask = masks_as_image(c_masks['EncodedPixels'].values)         # Create mask of rle data for each ship in an img\n            out_rgb += [c_img]                                               # Append the current img in the out_rgb / img list\n            out_mask += [c_mask]                                             # Append the current mask in the out_mask / mask list\n            if len(out_rgb)>=batch_size:                                     # If length of list is more or equal to batch size then\n                yield np.stack(out_rgb)/255.0, np.stack(out_mask)            # Yeild the scaled img array (b/w 0 and 1) and mask array (0 for bg and 1 for ship)\n                out_rgb, out_mask=[], []                                     # Empty the lists to create another batch","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:17:21.281989Z","iopub.execute_input":"2023-10-17T17:17:21.283478Z","iopub.status.idle":"2023-10-17T17:17:21.293738Z","shell.execute_reply.started":"2023-10-17T17:17:21.283403Z","shell.execute_reply":"2023-10-17T17:17:21.292712Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Generate train data\ntrain_gen = make_image_gen(train_df)\n\n# Image and Mask\ntrain_x, train_y = next(train_gen)\n\n# Print the summary\nprint(f\"train_x ~\\nShape: {train_x.shape}\\nMin value: {train_x.min()}\\nMax value: {train_x.max()}\")\nprint(f\"\\ntrain_y ~\\nShape: {train_y.shape}\\nMin value: {train_y.min()}\\nMax value: {train_y.max()}\")","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:17:48.955074Z","iopub.execute_input":"2023-10-17T17:17:48.955452Z","iopub.status.idle":"2023-10-17T17:18:00.296491Z","shell.execute_reply.started":"2023-10-17T17:17:48.955423Z","shell.execute_reply":"2023-10-17T17:18:00.294502Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Visulaising train batch\nmontage_rgb = lambda x: np.stack([montage(x[:, :, :, i]) for i in range(x.shape[3])], -1)\nbatch_rgb = montage_rgb(train_x)                                                   # Create montage of img\nbatch_seg = montage(train_y[:, :, :, 0])                                           # Create montafe of msk\nbatch_overlap = mark_boundaries(batch_rgb, batch_seg.astype(int))                  # Create bounding box around ships in img\ntitles = [\"Images\", \"Segmentations\", \"Bounding Boxes on ships in Images\"]          # Titles for subplot\ncolors = ['g', 'm', 'b']                                                           # Colors to be used for title\ndisplay = [batch_rgb, batch_seg, batch_overlap]                                    # What to display in subplot\nplt.figure(figsize=(25,10))                                                        # Generate figure\nfor i in range(3):                                                                 # For i = 0, 1, 2, 3\n    plt.subplot(1, 3, i+1)                                                         # Create subplot\n    plt.imshow(display[i])                                                         # Display\n    plt.title(titles[i], fontsize = 18, color = colors[i])                         # Title\n    plt.axis('off')                                                                # Turn off the axis\nplt.suptitle(\"Batch Visualizations\", fontsize = 20, color = 'r', weight = 'bold')  # Add suptitle\nplt.tight_layout()                                                                 # Layout for subplot","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:18:30.853675Z","iopub.execute_input":"2023-10-17T17:18:30.855048Z","iopub.status.idle":"2023-10-17T17:18:35.001311Z","shell.execute_reply.started":"2023-10-17T17:18:30.854986Z","shell.execute_reply":"2023-10-17T17:18:34.999968Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Prepare validation data\nvalid_x, valid_y = next(make_image_gen(valid_df, VALID_IMG_COUNT))\nprint(f\"valid_x ~\\nShape: {valid_x.shape}\\nMin value: {valid_x.min()}\\nMax value: {valid_x.max()}\")\nprint(f\"\\nvalid_y ~\\nShape: {valid_y.shape}\\nMin value: {valid_y.min()}\\nMax value: {valid_y.max()}\")","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:19:50.034164Z","iopub.execute_input":"2023-10-17T17:19:50.034952Z","iopub.status.idle":"2023-10-17T17:20:06.143241Z","shell.execute_reply.started":"2023-10-17T17:19:50.034862Z","shell.execute_reply":"2023-10-17T17:20:06.141790Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Augmenting Data using ImageDataGenerator\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# Preparing image data generator arguments\ndg_args = dict(rotation_range = 15,            # Degree range for random rotations\n               horizontal_flip = True,         # Randomly flips the inputs horizontally\n               vertical_flip = True,           # Randomly flips the inputs vertically\n               data_format = 'channels_last')  # channels_last refer to (batch, height, width, channels)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:20:29.205334Z","iopub.execute_input":"2023-10-17T17:20:29.205689Z","iopub.status.idle":"2023-10-17T17:20:38.456837Z","shell.execute_reply.started":"2023-10-17T17:20:29.205663Z","shell.execute_reply":"2023-10-17T17:20:38.454901Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Generate batches of tensor image data with real-time data augmentation.","metadata":{}},{"cell_type":"code","source":"image_gen = ImageDataGenerator(**dg_args)\nlabel_gen = ImageDataGenerator(**dg_args)\n\ndef create_aug_gen(in_gen, seed = None):\n    '''\n    Takes in -\n    in_gen - train data generator, seed value\n    '''\n    np.random.seed(seed if seed is not None else np.random.choice(range(9999)))  # Randomly assign seed value if not provided\n    for in_x, in_y in in_gen:                                                    # For imgs and msks in train data generator\n        seed = 12                                                                # Seed value for imgs and msks must be same else augmentation won't be same\n\n        # Create augmented imgs\n        g_x = image_gen.flow(255*in_x,                                           # Inverse scaling on imgs for augmentation\n                             batch_size = in_x.shape[0],                         # batch_size = 3\n                             seed = seed,                                        # Seed\n                             shuffle=True)                                       # Shuffle the data\n\n        # Create augmented masks\n        g_y = label_gen.flow(in_y,\n                             batch_size = in_x.shape[0],\n                             seed = seed,\n                             shuffle=True)\n\n        '''Yeilds - augmented scaled imgs and msks array'''\n        yield next(g_x)/255.0, next(g_y)","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:29:19.431377Z","iopub.execute_input":"2023-10-17T17:29:19.431782Z","iopub.status.idle":"2023-10-17T17:29:19.439858Z","shell.execute_reply.started":"2023-10-17T17:29:19.431755Z","shell.execute_reply":"2023-10-17T17:29:19.438979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Augment the train data\ncur_gen = create_aug_gen(train_gen, seed = 42)\nt_x, t_y = next(cur_gen)\nprint('x', t_x.shape, t_x.dtype, t_x.min(), t_x.max())\nprint('y', t_y.shape, t_y.dtype, t_y.min(), t_y.max())","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:29:41.587127Z","iopub.execute_input":"2023-10-17T17:29:41.587516Z","iopub.status.idle":"2023-10-17T17:29:42.537087Z","shell.execute_reply.started":"2023-10-17T17:29:41.587489Z","shell.execute_reply":"2023-10-17T17:29:42.535969Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Final display before passing data into model\nfig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize = (25, 10))\nax1.imshow(montage_rgb(t_x), cmap='gray')\nax1.set_title('Images', fontsize = 18, color = 'g')\nax1.axis('off')\nax2.imshow(montage(t_y[:, :, :, 0]), cmap='Blues_r')\nax2.set_title('Masks', fontsize = 18, color = 'r')\nax2.axis('off')\nax3.imshow(mark_boundaries(montage_rgb(t_x), montage(t_y[:, :, :, 0].astype(int))))\nax3.set_title('Bounding Box', fontsize = 18, color = 'b')\nax3.axis('off')\nplt.tight_layout()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:30:34.568439Z","iopub.execute_input":"2023-10-17T17:30:34.568837Z","iopub.status.idle":"2023-10-17T17:30:37.704403Z","shell.execute_reply.started":"2023-10-17T17:30:34.568807Z","shell.execute_reply":"2023-10-17T17:30:37.702579Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gc.collect() # Block all the garbage that has been generated","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:30:59.563569Z","iopub.execute_input":"2023-10-17T17:30:59.563977Z","iopub.status.idle":"2023-10-17T17:31:00.834359Z","shell.execute_reply.started":"2023-10-17T17:30:59.563942Z","shell.execute_reply":"2023-10-17T17:31:00.833314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**A brief introduction on U-NET architecture**\n\n![image.png](attachment:9660d910-4d61-4331-9eb0-385c58c84472.png)\n\nThe name U-NET itself is due to the shape of its architecture.\n- Each blue box corresponds to a multi-channel feature map.\n- The number of channels are denoted on top of the box.\n- The x-y size is provided at the lower left edge of the box.\n- The arrows shows the respective operations as mentioned on the bottom right of the image.\n- This architecture consists of three sections: The contraction, The bottleneck, and the expansion section.\n- But the heart of this architecture lies in the expansion section.\n- This action would ensure that the features that are learned while contracting the image will be used to reconstruct it.","metadata":{},"attachments":{"9660d910-4d61-4331-9eb0-385c58c84472.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"![image.png](attachment:5f8ac227-ce4f-4a8e-95d9-062436bb85e4.png)","metadata":{},"attachments":{"5f8ac227-ce4f-4a8e-95d9-062436bb85e4.png":{"image/png":"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"}}},{"cell_type":"code","source":"# Build U-Net model\nfrom keras import models, layers\n\n# Conv2DTranspose upsampling\ndef upsample_conv(filters, kernel_size, strides, padding):\n    return layers.Conv2DTranspose(filters, kernel_size, strides=strides, padding=padding)\n# Upsampling without Conv2DTranspose\ndef upsample_simple(filters, kernel_size, strides, padding):\n    return layers.UpSampling2D(strides)\n\n# Upsampling method choice\nif UPSAMPLE_MODE=='DECONV':\n    upsample=upsample_conv\nelse:\n    upsample=upsample_simple\n\n# Building the layers of UNET\ninput_img = layers.Input(t_x.shape[1:], name = 'RGB_Input')\npp_in_layer = input_img\n\n# If NET_SCALING is defined then do the next step else continue ahead\nif NET_SCALING is not None:\n    pp_in_layer = layers.AvgPool2D(NET_SCALING)(pp_in_layer)\n\n# To avoid overfitting and fastening the process of training\npp_in_layer = layers.GaussianNoise(GAUSSIAN_NOISE)(pp_in_layer)                       # Useful to mitigate overfitting\npp_in_layer = layers.BatchNormalization()(pp_in_layer)                                # Allows using higher learning rate without causing problems with gradients\n\n\n## Downsample (C-->C-->MP)\n\nc1 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (pp_in_layer)\nc1 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (c1)\np1 = layers.MaxPooling2D((2, 2)) (c1)\n\nc2 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (p1)\nc2 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (c2)\np2 = layers.MaxPooling2D((2, 2)) (c2)\n\nc3 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (p2)\nc3 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (c3)\np3 = layers.MaxPooling2D((2, 2)) (c3)\n\nc4 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (p3)\nc4 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (c4)\np4 = layers.MaxPooling2D(pool_size=(2, 2)) (c4)\n\n\nc5 = layers.Conv2D(128, (3, 3), activation='relu', padding='same') (p4)\nc5 = layers.Conv2D(128, (3, 3), activation='relu', padding='same') (c5)\n\n## Upsample (U --> Concat --> C --> C)\n\nu6 = upsample(64, (2, 2), strides=(2, 2), padding='same') (c5)\nu6 = layers.concatenate([u6, c4])\nc6 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (u6)\nc6 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (c6)\n\nu7 = upsample(32, (2, 2), strides=(2, 2), padding='same') (c6)\nu7 = layers.concatenate([u7, c3])\nc7 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (u7)\nc7 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (c7)\n\nu8 = upsample(16, (2, 2), strides=(2, 2), padding='same') (c7)\nu8 = layers.concatenate([u8, c2])\nc8 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (u8)\nc8 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (c8)\n\nu9 = upsample(8, (2, 2), strides=(2, 2), padding='same') (c8)\nu9 = layers.concatenate([u9, c1], axis=3)\nc9 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (u9)\nc9 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (c9)\n\nd = layers.Conv2D(1, (1, 1), activation='sigmoid') (c9)\nd = layers.Cropping2D((EDGE_CROP, EDGE_CROP))(d)\nd = layers.ZeroPadding2D((EDGE_CROP, EDGE_CROP))(d)\n\nif NET_SCALING is not None:\n    d = layers.UpSampling2D(NET_SCALING)(d)\n\nseg_model = models.Model(inputs=[input_img], outputs=[d])\n\nseg_model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-10-17T17:45:25.397739Z","iopub.execute_input":"2023-10-17T17:45:25.398193Z","iopub.status.idle":"2023-10-17T17:45:26.113131Z","shell.execute_reply.started":"2023-10-17T17:45:25.398164Z","shell.execute_reply":"2023-10-17T17:45:26.111603Z"},"trusted":true},"execution_count":null,"outputs":[]}]}