Upload sd_token_similarity_calculator.ipynb

sd_token_similarity_calculator.ipynb

@@ -55,10 +55,8 @@
         "def absolute_value(x):\n",
         "    return max(x, -x)\n",
         "\n",
-        "def similarity(id_A , id_B):\n",
-        "  #Tensors\n",
-        "  A = token[id_A]\n",
-        "  B = token[id_B]\n",
+        "\n",
+        "def token_similarity(A, B):\n",
         "  #Tensor vector length (2nd order, i.e (a^2 + b^2 + ....)^(1/2)\n",
         "  _A = LA.vector_norm(A, ord=2)\n",
         "  _B = LA.vector_norm(B, ord=2)\n",
@@ -69,6 +67,12 @@
         "  similarity_pcnt_aprox = round(similarity_pcnt, 3)\n",
         "  result = f'{similarity_pcnt_aprox} %'\n",
         "  return result\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",
         "\n",
         "#print(vocab[8922]) #the vocab item for ID 8922\n",
@@ -86,7 +90,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# @title Tokenize prompt into IDs\n",
+        "# @title 📝 -> 🆔 Tokenize prompt into IDs\n",
         "from transformers import AutoTokenizer\n",
         "tokenizer = AutoTokenizer.from_pretrained(\"openai/clip-vit-large-patch14\", clean_up_tokenization_spaces = False)\n",
         "\n",
@@ -95,6 +99,23 @@
         "tokenizer_output = tokenizer(text = prompt)\n",
         "input_ids = tokenizer_output['input_ids']\n",
         "print(input_ids)\n",
+        "\n",
+        "\n",
+        "#The prompt will be enclosed with the <|start-of-text|> and <|end-of-text|> tokens, which is why output will be [49406, ... , 49407].\n",
+        "\n",
+        "#You can leave the 'prompt' field empty to get a random value tensor. Since the tensor is random value, it will not correspond to any tensor in the vocab.json list , and this it will have no ID."
+      ],
+      "metadata": {
+        "id": "RPdkYzT2_X85"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# @title 🆔->🥢 Take the ID at index 1 from above result and get its corresponding tensor value\n",
+        "\n",
         "id_A = input_ids[1]\n",
         "A = token[id_A]\n",
         "_A = LA.vector_norm(A, ord=2)\n",
@@ -108,36 +129,20 @@
         "  A = R*(_A/_R)\n",
         "\n",
         "#Save a copy of the tensor A\n",
-        "id_P = input_ids[1]\n",
-        "P = token[id_A]\n",
-        "_P = LA.vector_norm(A, ord=2)\n",
-        "\n",
-        "#The prompt will be enclosed with the <|start-of-text|> and <|end-of-text|> tokens, which is why output will be [49406, ... , 49407].\n",
-        "\n",
-        "#You can leave the 'prompt' field empty to get a random value tensor. Since the tensor is random value, it will not correspond to any tensor in the vocab.json list , and this it will have no ID."
+        "id_P = id_A\n",
+        "P = A\n",
+        "_P = LA.vector_norm(A, ord=2)\n"
       ],
       "metadata": {
-        "id": "RPdkYzT2_X85",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "e335f5da-b26d-4eea-f854-fd646444ea14"
+        "id": "YqdiF8DIz9Wu"
       },
       "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "[49406, 8922, 49407]\n"
-          ]
-        }
-      ]
+      "outputs": []
     },
     {
       "cell_type": "code",
       "source": [
-        "# @title Take the ID at index 1 from above result and modify it (optional)\n",
+        "# @title 🥢 -> 🥢🔀 Take the ID at index 1 from above result and modify it (optional)\n",
         "mix_with = \"\" # @param {type:'string'}\n",
         "mix_method = \"None\" # @param [\"None\" , \"Average\", \"Subtract\"] {allow-input: true}\n",
         "w = 0.5 # @param {type:\"slider\", min:0, max:1, step:0.01}\n",
@@ -193,7 +198,7 @@
       "cell_type": "code",
       "source": [
         "\n",
-        "# @title Find Similiar Tokens to ID at index 1 from above result\n",
+        "# @title 🥢->🧾🥢 Find Similiar Tokens to ID at index 1 from above result\n",
         "dots = torch.zeros(NUM_TOKENS)\n",
         "for index in range(NUM_TOKENS):\n",
         "  id_B = index\n",
@@ -233,7 +238,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# @title Print Result from the 'Similiar Tokens' list from above result\n",
+        "# @title 🥢🧾 -> 🖨️ Print Result from the 'Similiar Tokens' list from above result\n",
         "list_size = 100 # @param {type:'number'}\n",
         "print_ID = False # @param {type:\"boolean\"}\n",
         "print_Similarity = True # @param {type:\"boolean\"}\n",
@@ -264,7 +269,7 @@
       "cell_type": "code",
       "source": [
         "\n",
-        "# @title Get similarity % of two token IDs\n",
+        "# @title 🆔 Get similarity % of two token IDs\n",
         "id_for_token_A = 4567 # @param {type:'number'}\n",
         "id_for_token_B = 4343 # @param {type:'number'}\n",
         "\n",
@@ -280,6 +285,45 @@
       "execution_count": null,
       "outputs": []
     },
+    {
+      "cell_type": "code",
+      "source": [
+        "# @title 💫 Compare Text encodings\n",
+        "\n",
+        "prompt_A = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Write a prompt\"}\n",
+        "prompt_B = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Write a prompt\"}\n",
+        "use_token_padding = False # @param {type:\"boolean\"}\n",
+        "\n",
+        "from transformers import  CLIPProcessor, CLIPModel\n",
+        "\n",
+        "\n",
+        "processor = CLIPProcessor.from_pretrained(\"openai/clip-vit-large-patch14\" , clean_up_tokenization_spaces = True)\n",
+        "\n",
+        "model = CLIPModel.from_pretrained(\"openai/clip-vit-large-patch14\")\n",
+        "\n",
+        "ids_A = processor.tokenizer(text=prompt_A, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "text_encoding_A = model.get_text_features(**ids_A)\n",
+        "\n",
+        "ids_B = processor.tokenizer(text=prompt_B, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "text_encoding_B = model.get_text_features(**ids_B)\n",
+        "\n",
+        "similarity_str =  'The similarity between the text_encoding for A and B is ' +  token_similarity(text_encoding_A[0] , text_encoding_B[0])\n",
+        "\n",
+        "\n",
+        "print(similarity_str)\n",
+        "#outputs = model(**inputs)\n",
+        "#logits_per_image = outputs.logits_per_image # this is the image-text similarity score\n",
+        "#probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities\n",
+        "\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "QQOjh5BvnG8M"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
     {
       "cell_type": "markdown",
       "source": [
@@ -316,7 +360,11 @@
         "\n",
         "Source: https://huggingface.co/docs/diffusers/main/en/using-diffusers/weighted_prompts*\n",
         "\n",
-        "So TLDR; vector direction = “what to generate” , vector magnitude = “prompt weights”"
+        "So TLDR; vector direction = “what to generate” , vector magnitude = “prompt weights”\n",
+        "\n",
+        "/---/\n",
+        "\n",
+        "Read more about CLIP here: https://huggingface.co/docs/transformers/model_doc/clip"
       ],
       "metadata": {
         "id": "njeJx_nSSA8H"