Upload 2 files

sd_token_similarity_calculator.ipynb

@@ -41,107 +41,90 @@
         "ACTIVE_IMG = ''\n",
         "#-----#\n",
         "\n",
+        "# Define functions/constants\n",
+        "NUM_TOKENS = 49407\n",
+        "NUM_PREFIX = 13662\n",
+        "NUM_SUFFIX = 32901\n",
+        "\n",
+        "loaded_Image_A = False\n",
+        "\n",
         "#Import the vocab.json\n",
         "import json\n",
         "import pandas as pd\n",
-        "with open('vocab.json', 'r') as f:\n",
+        "\n",
+        "# Read suffix.json\n",
+        "with open('suffix.json', 'r') as f:\n",
         "    data = json.load(f)\n",
+        "_df = pd.DataFrame({'count': data})['count']\n",
+        "suffix = {\n",
+        "    key : value for key, value in _df.items()\n",
+        "}\n",
+        "# Read prefix json\n",
+        "with open('prefix.json', 'r') as f:\n",
+        "    data = json.load(f)\n",
+        "_df = pd.DataFrame({'count': data})['count']\n",
+        "prefix = {\n",
+        "    key : value for key, value in _df.items()\n",
+        "}\n",
         "\n",
+        "# Read to_suffix.json\n",
+        "with open('to_suffix.json', 'r') as f:\n",
+        "    data = json.load(f)\n",
         "_df = pd.DataFrame({'count': data})['count']\n",
+        "suffix_to_vocab = {\n",
+        "    key : value for key, value in _df.items()\n",
+        "}\n",
         "\n",
-        "vocab = {\n",
-        "    value: key for key, value in _df.items()\n",
+        "# Read to_prefix.json\n",
+        "with open('to_prefix.json', 'r') as f:\n",
+        "    data = json.load(f)\n",
+        "_df = pd.DataFrame({'count': data})['count']\n",
+        "prefix_to_vocab = {\n",
+        "    key : value for key, value in _df.items()\n",
         "}\n",
+        "\n",
         "#-----#\n",
         "\n",
-        "# Define functions/constants\n",
-        "NUM_TOKENS = 49407\n",
         "\n",
-        "def absolute_value(x):\n",
-        "    return max(x, -x)\n",
+        "# Read to_suffix.json (reversing key and value)\n",
+        "with open('to_suffix.json', 'r') as f:\n",
+        "    data = json.load(f)\n",
+        "_df = pd.DataFrame({'count': data})['count']\n",
+        "vocab_to_suffix = {\n",
+        "    value : key for key, value in _df.items()\n",
+        "}\n",
         "\n",
+        "# Read to_prefix.json (reversing key and value)\n",
+        "with open('to_prefix.json', 'r') as f:\n",
+        "    data = json.load(f)\n",
+        "_df = pd.DataFrame({'count': data})['count']\n",
+        "vocab_to_prefix = {\n",
+        "    value : key for key, value in _df.items()\n",
+        "}\n",
         "\n",
-        "def token_similarity(A, B):\n",
         "\n",
-        "  #Vector length#\n",
-        "  _A = LA.vector_norm(A, ord=2)\n",
-        "  _B = LA.vector_norm(B, ord=2)\n",
+        "#-----#\n",
         "\n",
-        "  #----#\n",
-        "  result = torch.dot(A,B)/(_A*_B)\n",
-        "  #similarity_pcnt = absolute_value(result.item()*100)\n",
-        "  similarity_pcnt = result.item()*100\n",
-        "  similarity_pcnt_aprox = round(similarity_pcnt, 3)\n",
-        "  result = f'{similarity_pcnt_aprox} %'\n",
-        "  return result\n",
-        "\n",
-        "\n",
-        "def similarity(id_A , id_B):\n",
-        "  #Tensors\n",
-        "  A = token[id_A]\n",
-        "  B = token[id_B]\n",
-        "  return token_similarity(A, B)\n",
-        "#----#\n",
+        "#get token from id (excluding tokens with special symbols)\n",
+        "def vocab(id):\n",
+        "  _id = f'{id}'\n",
+        "  if _id in vocab_to_suffix:\n",
+        "    _id = vocab_to_suffix[_id]\n",
+        "    return suffix[_id]\n",
+        "  if _id in vocab_to_prefix:\n",
+        "    _id = vocab_to_prefix[_id]\n",
+        "    return prefix[_id]\n",
+        "  return ' ' #<---- return whitespace if other id like emojis etc.\n",
+        "#--------#\n",
         "\n",
-        "#print(vocab[8922]) #the vocab item for ID 8922\n",
-        "#print(token[8922].shape)  #dimension of the token\n",
-        "\n",
-        "mix_with = \"\"\n",
-        "mix_method = \"None\"\n",
-        "\n",
-        "#-------------#\n",
-        "# UNUSED\n",
-        "\n",
-        "# Get the 10 lowest values from a tensor as a string\n",
-        "def get_valleys (A):\n",
-        "  sorted, indices = torch.sort(A,dim=0 , descending=False)\n",
-        "  result = \"{\"\n",
-        "  for index in range(10):\n",
-        "    id = indices[index].item()\n",
-        "    result = result + f\"{id}\"\n",
-        "    if(index<9):\n",
-        "      result = result + \",\"\n",
-        "  result = result + \"}\"\n",
-        "  return result\n",
-        "\n",
-        "# Get the 10 highest values from a tensor as a string\n",
-        "def get_peaks (A):\n",
-        "  sorted, indices = torch.sort(A,dim=0 , descending=True)\n",
-        "  result = \"{\"\n",
-        "  for index in range(10):\n",
-        "    id = indices[index].item()\n",
-        "    result = result + f\"{id}\"\n",
-        "    if(index<9):\n",
-        "      result = result + \",\"\n",
-        "  result = result + \"}\"\n",
-        "  return result"
+        "#print(get_token(35894))\n"
       ],
       "metadata": {
         "id": "Ch9puvwKH1s3",
-        "collapsed": true,
-        "outputId": "033c251a-2043-40e7-9500-4da870ffa7fd",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "cellView": "form"
+        "collapsed": true
       },
       "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Cloning into 'sd_tokens'...\n",
-            "remote: Enumerating objects: 20, done.\u001b[K\n",
-            "remote: Counting objects: 100% (17/17), done.\u001b[K\n",
-            "remote: Compressing objects: 100% (17/17), done.\u001b[K\n",
-            "remote: Total 20 (delta 4), reused 0 (delta 0), pack-reused 3 (from 1)\u001b[K\n",
-            "Unpacking objects: 100% (20/20), 310.37 KiB | 2.10 MiB/s, done.\n",
-            "Filtering content: 100% (3/3), 160.82 MiB | 26.64 MiB/s, done.\n",
-            "/content/sd_tokens\n"
-          ]
-        }
-      ]
+      "outputs": []
     },
     {
       "cell_type": "code",
@@ -201,11 +184,11 @@
         "\n",
         "name_A = \"A of random type\"\n",
         "if (id_A>-1):\n",
-        "  name_A = vocab[id_A]\n",
+        "  name_A = vocab(id_A)\n",
         "\n",
         "name_C = \"token C of random type\"\n",
         "if (id_C>-1):\n",
-        "  name_C = vocab[id_C]\n",
+        "  name_C = vocab(id_C)\n",
         "\n",
         "print(f\"The similarity between A '{name_A}' and C '{name_C}' is {round(sim_AC.item()*100,2)} %\")\n",
         "\n",
@@ -264,7 +247,7 @@
         "for index in range(list_size):\n",
         "  id = indices[index].item()\n",
         "  if (print_Name):\n",
-        "    print(f'{vocab[id]}') # vocab item\n",
+        "    print(f'{vocab(id)}') # vocab item\n",
         "  if (print_ID):\n",
         "    print(f'ID = {id}') # IDs\n",
         "  if (print_Similarity):\n",
@@ -285,14 +268,13 @@
         "#NUM TOKENS == 49407\n",
         "for index in range(NUM_TOKENS):\n",
         "  #print(d[f'{index}']) #<-----Use this to read values from the .db file\n",
-        "  d[f'{index}']= vocab[indices[index].item()] #<---- write values to .db file\n",
+        "  d[f'{index}']= vocab(indices[index].item()) #<---- write values to .db file\n",
         "#----#\n",
         "d.close() #close the file\n",
         "# See this link for additional stuff to do with shelve: https://docs.python.org/3/library/shelve.html"
       ],
       "metadata": {
-        "id": "iWeFnT1gAx6A",
-        "cellView": "form"
+        "id": "iWeFnT1gAx6A"
       },
       "execution_count": null,
       "outputs": []
@@ -315,20 +297,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# @title ⚡+🖼️ -> 📝 Token-Sampling Image interrogator\n",
-        "#-----#\n",
-        "NUM_TOKENS = 49407\n",
-        "import shelve\n",
-        "db_vocab = shelve.open(VOCAB_FILENAME)\n",
-        "print(f'using the tokens found in {VOCAB_FILENAME}.db as the vocab')\n",
-        "# @markdown # What do you want to to mimic?\n",
-        "use = '🖼️image_encoding from image' # @param ['📝text_encoding from prompt', '🖼️image_encoding from image']\n",
-        "# @markdown --------------------------\n",
-        "use_token_padding = True # param {type:\"boolean\"} <---- Enabled by default\n",
-        "prompt = \"photo of a banana\" # @param {\"type\":\"string\",\"placeholder\":\"Write a prompt\"}\n",
-        "#-----#\n",
-        "prompt_A = prompt\n",
-        "#-----#\n",
+        "# @title 🖼️ Upload an image\n",
         "from google.colab import files\n",
         "def upload_files():\n",
         "  from google.colab import files\n",
@@ -338,28 +307,58 @@
         "  return list(uploaded.keys())\n",
         "#Get image\n",
         "# You can use \"http://images.cocodataset.org/val2017/000000039769.jpg\" for testing\n",
-        "image_url = \"http://images.cocodataset.org/val2017/000000039769.jpg\" # @param {\"type\":\"string\",\"placeholder\":\"leave empty for local upload (scroll down to see it)\"}\n",
+        "image_url = \"\" # @param {\"type\":\"string\",\"placeholder\":\"leave empty for local upload (scroll down to see it)\"}\n",
         "colab_image_path = \"\" # @param {\"type\":\"string\",\"placeholder\": \"eval. as '/content/sd_tokens/' + **your input**\"}\n",
         "# @markdown --------------------------\n",
+        "\n",
+        "image_path = \"\"\n",
+        "\n",
         "from PIL import Image\n",
         "import requests\n",
         "image_A = \"\"\n",
         "#----#\n",
-        "if(use == '🖼️image_encoding from image'):\n",
-        "  if image_url == \"\":\n",
-        "    import cv2\n",
-        "    from google.colab.patches import cv2_imshow\n",
-        "    # Open the image.\n",
-        "    if colab_image_path == \"\":\n",
-        "      keys =  upload_files()\n",
-        "      for key in keys:\n",
-        "        image_A = cv2.imread(\"/content/sd_tokens/\" + key)\n",
-        "        colab_image_path = \"/content/sd_tokens/\" + key\n",
-        "    else:\n",
-        "      image_A = cv2.imread(\"/content/sd_tokens/\" + colab_image_path)\n",
+        "if image_url == \"\":\n",
+        "  import cv2\n",
+        "  from google.colab.patches import cv2_imshow\n",
+        "  # Open the image.\n",
+        "  if colab_image_path == \"\":\n",
+        "    keys =  upload_files()\n",
+        "    for key in keys:\n",
+        "      image_A = cv2.imread(\"/content/sd_tokens/\" + key)\n",
+        "      colab_image_path = \"/content/sd_tokens/\" + key\n",
+        "      image_path = \"/content/sd_tokens/\" + key\n",
         "  else:\n",
-        "    image_A = Image.open(requests.get(image_url, stream=True).raw)\n",
+        "    image_A = cv2.imread(\"/content/sd_tokens/\" + colab_image_path)\n",
+        "else:\n",
+        "  image_A = Image.open(requests.get(image_url, stream=True).raw)\n",
         "#------#\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "ke6mZ1RZDOeB"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# @title ⚡+🖼️ -> 📝 Token-Sampling Image interrogator\n",
+        "#-----#\n",
+        "NUM_TOKENS = 49407\n",
+        "import shelve\n",
+        "db_vocab = shelve.open(VOCAB_FILENAME)\n",
+        "print(f'using the tokens found in {VOCAB_FILENAME}.db as the vocab')\n",
+        "# @markdown # What do you want to to mimic?\n",
+        "use = '🖼️image_encoding from image' # @param ['📝text_encoding from prompt', '🖼️image_encoding from image']\n",
+        "# @markdown --------------------------\n",
+        "use_token_padding = True # param {type:\"boolean\"} <---- Enabled by default\n",
+        "prompt = \"photo of a banana\" # @param {\"type\":\"string\",\"placeholder\":\"Write a prompt\"}\n",
+        "#-----#\n",
+        "prompt_A = prompt\n",
+        "if(image_path != \"\") : image_A = cv2.imread(\"/content/sd_tokens/\" + image_path)\n",
+        "#-----#\n",
+        "\n",
         "from transformers import AutoTokenizer\n",
         "tokenizer = AutoTokenizer.from_pretrained(\"openai/clip-vit-large-patch14\", clean_up_tokenization_spaces = False)\n",
         "from transformers import  CLIPProcessor, CLIPModel\n",
@@ -652,8 +651,7 @@
       ],
       "metadata": {
         "collapsed": true,
-        "id": "fi0jRruI0-tu",
-        "cellView": "form"
+        "id": "fi0jRruI0-tu"
       },
       "execution_count": null,
       "outputs": []