diff --git a/colab/B-1B Lancer Heavy Bombers at Aero India 2023.mp4 b/colab/B-1B Lancer Heavy Bombers at Aero India 2023.mp4
new file mode 100644
index 00000000..9f9cd0bb
Binary files /dev/null and b/colab/B-1B Lancer Heavy Bombers at Aero India 2023.mp4 differ
diff --git a/colab/Output_vedio201.avi b/colab/Output_vedio201.avi
new file mode 100644
index 00000000..64f471b8
Binary files /dev/null and b/colab/Output_vedio201.avi differ
diff --git a/colab/lama_Video_inpainting.ipynb b/colab/lama_Video_inpainting.ipynb
new file mode 100644
index 00000000..b6b70d74
--- /dev/null
+++ b/colab/lama_Video_inpainting.ipynb
@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","gpuClass":"standard"},"cells":[{"cell_type":"markdown","source":["**Try inpainting on video yourself**"],"metadata":{"id":"wh9TMP6ZpyzK"}},{"cell_type":"code","execution_count":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"77fdT4VTSgL7","outputId":"68c4ab08-1bcd-468e-f2c9-a41d1d64f581","executionInfo":{"status":"ok","timestamp":1681743165576,"user_tz":-330,"elapsed":783995,"user":{"displayName":"Sri Om Subham (M22AI836)","userId":"00908540382614000284"}}},"outputs":[{"output_type":"stream","name":"stdout","text":["\n","> Cloning the repo\n","Cloning into 'lama'...\n","remote: Enumerating objects: 399, done.\u001b[K\n","remote: Counting objects: 100% (128/128), done.\u001b[K\n","remote: Compressing objects: 100% (70/70), done.\u001b[K\n","remote: Total 399 (delta 76), reused 68 (delta 55), pack-reused 271\u001b[K\n","Receiving objects: 100% (399/399), 9.87 MiB | 15.06 MiB/s, done.\n","Resolving deltas: 100% (138/138), done.\n","\n","> Install dependencies\n","Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting torch==1.8.0\n"," Downloading torch-1.8.0-cp39-cp39-manylinux1_x86_64.whl (735.5 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m735.5/735.5 MB\u001b[0m \u001b[31m1.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting torchvision==0.9.0\n"," Downloading torchvision-0.9.0-cp39-cp39-manylinux1_x86_64.whl (17.3 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.3/17.3 MB\u001b[0m \u001b[31m53.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting torchaudio==0.8.0\n"," Downloading torchaudio-0.8.0-cp39-cp39-manylinux1_x86_64.whl (1.9 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m55.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting torchtext==0.9\n"," Downloading torchtext-0.9.0-cp39-cp39-manylinux1_x86_64.whl (7.0 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.0/7.0 MB\u001b[0m \u001b[31m58.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from torch==1.8.0) (1.22.4)\n","Requirement already satisfied: typing-extensions in /usr/local/lib/python3.9/dist-packages (from torch==1.8.0) (4.5.0)\n","Requirement already satisfied: pillow>=4.1.1 in /usr/local/lib/python3.9/dist-packages (from torchvision==0.9.0) (8.4.0)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from torchtext==0.9) (4.65.0)\n","Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from torchtext==0.9) (2.27.1)\n","Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->torchtext==0.9) (2.0.12)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->torchtext==0.9) (2022.12.7)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->torchtext==0.9) (1.26.15)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->torchtext==0.9) (3.4)\n","Installing collected packages: torch, torchvision, torchtext, torchaudio\n"," Attempting uninstall: torch\n"," Found existing installation: torch 2.0.0+cu118\n"," Uninstalling torch-2.0.0+cu118:\n"," Successfully uninstalled torch-2.0.0+cu118\n"," Attempting uninstall: torchvision\n"," Found existing installation: torchvision 0.15.1+cu118\n"," Uninstalling torchvision-0.15.1+cu118:\n"," Successfully uninstalled torchvision-0.15.1+cu118\n"," Attempting uninstall: torchtext\n"," Found existing installation: torchtext 0.15.1\n"," Uninstalling torchtext-0.15.1:\n"," Successfully uninstalled torchtext-0.15.1\n"," Attempting uninstall: torchaudio\n"," Found existing installation: torchaudio 2.0.1+cu118\n"," Uninstalling torchaudio-2.0.1+cu118:\n"," Successfully uninstalled torchaudio-2.0.1+cu118\n","\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n","torchdata 0.6.0 requires torch==2.0.0, but you have torch 1.8.0 which is incompatible.\u001b[0m\u001b[31m\n","\u001b[0mSuccessfully installed torch-1.8.0 torchaudio-0.8.0 torchtext-0.9.0 torchvision-0.9.0\n"," Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m29.8/29.8 MB\u001b[0m \u001b[31m16.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.8/23.8 MB\u001b[0m \u001b[31m60.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.2/72.2 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m144.6/144.6 kB\u001b[0m \u001b[31m17.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m841.9/841.9 kB\u001b[0m \u001b[31m60.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m271.5/271.5 kB\u001b[0m \u001b[31m26.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.9/51.9 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m112.4/112.4 kB\u001b[0m \u001b[31m12.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m74.7/74.7 kB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m176.9/176.9 kB\u001b[0m \u001b[31m20.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m65.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.2/114.2 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m264.6/264.6 kB\u001b[0m \u001b[31m25.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.8/158.8 kB\u001b[0m \u001b[31m18.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h Building wheel for easydict (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Building wheel for scikit-image (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n","\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n","yellowbrick 1.5 requires scikit-learn>=1.0.0, but you have scikit-learn 0.24.2 which is incompatible.\n","imbalanced-learn 0.10.1 requires scikit-learn>=1.0.2, but you have scikit-learn 0.24.2 which is incompatible.\u001b[0m\u001b[31m\n","\u001b[0m Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Building wheel for wget (setup.py) ... \u001b[?25l\u001b[?25hdone\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 GB\u001b[0m \u001b[31m846.3 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.6/17.6 MB\u001b[0m \u001b[31m78.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n","torchdata 0.6.0 requires torch==2.0.0, but you have torch 1.8.0+cu111 which is incompatible.\u001b[0m\u001b[31m\n","\u001b[0m\n","> Changing the dir to:\n","/content/lama\n","\n","> Download the model\n"," % Total % Received % Xferd Average Speed Time Time Time Current\n"," Dload Upload Total Spent Left Speed\n"," 0 0 0 0 0 0 0 0 --:--:-- 0:00:01 --:--:-- 0\n","100 363M 0 363M 0 0 9843k 0 --:--:-- 0:00:37 --:--:-- 9.9M\n","Archive: big-lama.zip\n"," inflating: big-lama/config.yaml \n"," inflating: big-lama/models/best.ckpt \n",">fixing opencv\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.9/42.9 MB\u001b[0m \u001b[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h\n","> Init mask-drawing code\n"]}],"source":["#@title Run this sell to set everything up\n","print('\\n> Cloning the repo')\n","!git clone https://github.com/advimman/lama.git\n","\n","print('\\n> Install dependencies')\n","!pip install torch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 torchtext==0.9\n","!pip install -r lama/requirements.txt --quiet\n","!pip install wget --quiet\n","!pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html --quiet\n","\n","\n","print('\\n> Changing the dir to:')\n","%cd /content/lama\n","\n","print('\\n> Download the model')\n","!curl -L $(yadisk-direct https://disk.yandex.ru/d/ouP6l8VJ0HpMZg) -o big-lama.zip\n","!unzip big-lama.zip\n","\n","print('>fixing opencv')\n","!pip uninstall opencv-python-headless -y --quiet\n","!pip install opencv-contrib-python-headless==4.4.0.46 --quiet\n","#!pip install opencv-contrib-python-headless==4.1.2.30\n","\n","\n","print('\\n> Init mask-drawing code')\n","import base64, os\n","from IPython.display import HTML, Image\n","from google.colab.output import eval_js\n","from base64 import b64decode\n","import matplotlib.pyplot as plt\n","import numpy as np\n","import wget\n","from shutil import copyfile\n","import shutil\n","import cv2 as cv\n","\n","\n","canvas_html = \"\"\"\n","\n","\n","\n","\n","\n","\n","\n","\"\"\"\n","\n","def draw(imgm, filename='drawing.png', w=400, h=200, line_width=1):\n"," display(HTML(canvas_html % (w, h, w,h, filename.split('.')[-1], imgm, line_width)))\n"," data = eval_js(\"data\")\n"," binary = b64decode(data.split(',')[1])\n"," with open(filename, 'wb') as f:\n"," f.write(binary)"]},{"cell_type":"code","source":["# print the mask and mask*image\n","def show_image(frame1, mask):\n"," plt.figure(figsize=(18,6))\n"," plt.subplot(131)\n"," plt.imshow(mask, cmap='gray')\n"," plt.axis('off')\n"," plt.title('mask')\n"," \n"," plt.subplot(132)\n"," img = np.array(plt.imread(frame1)[:,:,:3]) # image is defined\n"," plt.imshow(img)\n"," plt.axis('off')\n"," plt.title('img')\n","\n"," plt.subplot(133)\n"," img = np.array((1-mask.reshape(mask.shape[0], mask.shape[1], -1))*plt.imread(frame1)[:,:,:3]) # image with mask is defined\n"," _=plt.imshow(img)\n"," _=plt.axis('off')\n"," _=plt.title('img * mask')\n"," plt.show()"],"metadata":{"id":"ZPzCaW-rhxtD","executionInfo":{"status":"ok","timestamp":1681743165577,"user_tz":-330,"elapsed":26,"user":{"displayName":"Sri Om Subham (M22AI836)","userId":"00908540382614000284"}}},"execution_count":2,"outputs":[]},{"cell_type":"code","source":["def run_impainting():\n"," print('Run inpainting')\n"," !PYTHONPATH=. TORCH_HOME=$(pwd) python3 bin/predict.py model.path=$(pwd)/big-lama indir=$(pwd)/data_image outdir=/content/output dataset.img_suffix=.png > /dev/null\n"],"metadata":{"id":"qRgig-vrzUbp","executionInfo":{"status":"ok","timestamp":1681743165578,"user_tz":-330,"elapsed":23,"user":{"displayName":"Sri Om Subham (M22AI836)","userId":"00908540382614000284"}}},"execution_count":3,"outputs":[]},{"cell_type":"markdown","source":["Predefined video : uncomment any line,\n","Local file: leave the vname = None"],"metadata":{"id":"llvXLQLFTy02"}},{"cell_type":"code","source":["shutil.rmtree('./data_for_prediction', ignore_errors=True) # remove any previously present folder/directory\n","!mkdir data_for_prediction # creating the folder/directory\n","\n","vname = None\n","vname = 'colab/B-1B Lancer Heavy Bombers at Aero India 2023.mp4' # <-in the example \n","shutil.copy(vname, './data_for_prediction/B-1B Lancer Heavy Bombers at Aero India 2023.mp4')\n","vanme = f'./data_for_prediction/B-1B Lancer Heavy Bombers at Aero India 2023.mp4'\n","\n","# un-comment the below lines for uploading the video\n","# if vname is None:\n","# from google.colab import files\n","# files = files.upload() # create option to upload the file\n","# vname = list(files.keys())[0] # saves the file in 'vname'\n","\n","\n","# #coping the video file in directory 'data_for_prediction'\n","\n","#copyfile(vname, f'./data_for_prediction/{vname}') # copying the file in the created folder\n","#os.remove(vname) # removing the instance of the file from 'fname'\n","#vname = f'./data_for_prediction/{vname}' # reading the file form the folder"],"metadata":{"id":"CmuULiPQTxQi","executionInfo":{"status":"ok","timestamp":1681744006105,"user_tz":-330,"elapsed":10,"user":{"displayName":"Sri Om Subham (M22AI836)","userId":"00908540382614000284"}}},"execution_count":14,"outputs":[]},{"cell_type":"code","source":["# video details \n","def video_fps():\n"," video = cv.VideoCapture(vname);\n"," # Find OpenCV version\n"," (major_ver, minor_ver, subminor_ver) = (cv.__version__).split('.')\n"," \n"," fps = video.get(cv.CAP_PROP_FPS)\n"," return fps\n","\n"," video.release()\n","\n","def frame_size():\n"," vcap = cv.VideoCapture(vname) \n"," \n"," if vcap.isOpened(): \n"," # get vcap property \n"," width = int(vcap.get(3)) # float `width`\n"," height = int(vcap.get(4)) # float `height`\n","\n"," return [width, height]"],"metadata":{"id":"6XIizns9EQHL","executionInfo":{"status":"ok","timestamp":1681744021999,"user_tz":-330,"elapsed":552,"user":{"displayName":"Sri Om Subham (M22AI836)","userId":"00908540382614000284"}}},"execution_count":15,"outputs":[]},{"cell_type":"markdown","source":["Draw a Mask, Press Finish, Wait for Inpainting"],"metadata":{"id":"HPUVXxD3DMLX"}},{"cell_type":"code","source":["shutil.rmtree('/content/lama/data_image', ignore_errors=True) # remove any previously present folder/directory\n","!mkdir data_image # creating the folder/directory\n","i = 0\n","cap1 = cv.VideoCapture(vname) # path of the first inferenced video\n","\n","while True:\n"," ret1, frame1 = cap1.read() # reading the video 1\n"," \n"," if not ret1: # break for last frame.\n"," break\n","\n"," # push the first frame to draw function\n"," if (i==0):\n"," i = i+1\n"," plt.imsave(\"frame1.png\",frame1) # save the mask in the directory\n","\n"," frame = '/content/lama/frame1.png'\n","\n"," image64 = base64.b64encode(open(frame, 'rb').read()) # converting the file into string of base 64 format\n"," image64 = image64.decode('utf-8') # decoding from string format to utf-8 format\n"," \n"," print(f'Will use {frame} for inpainting')\n"," img = np.array(plt.imread(frame)[:,:,:3]) # reading the image from the folder, converting it into numpy array format.\n"," \n"," draw(image64, filename=\"frame1_mask.png\", w=img.shape[1], h=img.shape[0], line_width=0.04*img.shape[1])\n"," \n"," with_mask = np.array(plt.imread(f\"frame1_mask.png\")[:,:,:3])\n"," mask = (with_mask[:,:,0]==1)*(with_mask[:,:,1]==0)*(with_mask[:,:,2]==0) # mask is defined\n"," \n"," plt.imsave(\"frame1_mask.png\",mask, cmap='gray') # save the mask in the directory\n"," \n"," show_image(frame, mask) # displating mask, image , image*mask\n"," \n"," # saving images and masks for runing impainting\n"," plt.imsave(f\"./data_image/frame{i}.png\",frame1)\n"," mask = plt.imread('/content/lama/frame1_mask.png')\n"," plt.imsave(f\"./data_image/frame{i}_mask.png\", mask, cmap='gray')\n"," i = i+1\n"," \n","cap1.release()\n","run_impainting()\n","print ('Impainting completed')\n","\n","# make video form the images\n","print ('combining frames to make video')\n","out = cv.VideoWriter('Output_video_su30mki.avi', cv.VideoWriter_fourcc(*'MJPG'), video_fps(), (frame_size()[0], frame_size()[1])) \n"," # put output video name\n","for i in range(1, len(os.listdir('/content/output/'))):\n"," img = cv.imread(f'/content/output/frame{i}_mask.png') \n"," out.write(img)\n","out.release()\n","shutil.rmtree('/content/lama/data_image', ignore_errors=True) \n","shutil.rmtree('/content/output', ignore_errors=True)\n","print ('Video formation done')\n","\n","vname = None"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"hkwxUeG7zUkg","outputId":"783a0707-4f7f-4080-9ad1-5e7e8905ad06","executionInfo":{"status":"ok","timestamp":1681744639635,"user_tz":-330,"elapsed":615526,"user":{"displayName":"Sri Om Subham (M22AI836)","userId":"00908540382614000284"}}},"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["Will use /content/lama/frame1.png for inpainting\n"]},{"output_type":"display_data","data":{"text/plain":[""],"text/html":["\n","\n","\n","\n","\n","\n","\n","\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":[""],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Run inpainting\n","100% 796/796 [08:04<00:00, 1.64it/s]\n","Impainting completed\n","combining frames to make video\n","Video formation done\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"YIF8ERwYqF1o"},"execution_count":null,"outputs":[]}]}
\ No newline at end of file