Upload sd_token_similarity_calculator.ipynb

sd_token_similarity_calculator.ipynb

@@ -59,9 +59,11 @@
         "\n",
         "\n",
         "def token_similarity(A, B):\n",
-        "  #Tensor vector length (2nd order, i.e (a^2 + b^2 + ....)^(1/2)\n",
+        "\n",
+        "  #Vector length#\n",
         "  _A = LA.vector_norm(A, ord=2)\n",
         "  _B = LA.vector_norm(B, ord=2)\n",
+        "\n",
         "  #----#\n",
         "  result = torch.dot(A,B)/(_A*_B)\n",
         "  #similarity_pcnt = absolute_value(result.item()*100)\n",
@@ -70,6 +72,7 @@
         "  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",
@@ -81,11 +84,39 @@
         "#print(token[8922].shape)  #dimension of the token\n",
         "\n",
         "mix_with = \"\"\n",
-        "mix_method = \"None\""
+        "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"
       ],
       "metadata": {
         "id": "Ch9puvwKH1s3",
-        "collapsed": true
+        "collapsed": true,
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -119,6 +150,7 @@
         "  R = torch.rand(768)\n",
         "  _R =  LA.vector_norm(R, ord=2)\n",
         "  A = R*(_A/_R)\n",
+        "  name_A = 'random_A'\n",
         "\n",
         "\n",
         "mix_with = \"\" # @param {\"type\":\"string\",\"placeholder\":\"(optional) write something else\"}\n",
@@ -138,6 +170,26 @@
         "  R = torch.rand(768)\n",
         "  _R =  LA.vector_norm(R, ord=2)\n",
         "  C = R*(_C/_R)\n",
+        "  name_C = 'random_C'\n",
+        "\n",
+        "name_A = \"A of random type\"\n",
+        "if (id_A>-1):\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",
+        "\n",
+        "# Peaks feature\n",
+        "#peaks_A = get_valleys(A)\n",
+        "#peaks_C = get_valleys(C)\n",
+        "#print(f\"The elementwise top 10 highest values for A is at indices {peaks_A}\")\n",
+        "#print(\"-------\")\n",
+        "#print(f\"The elementwise top 10 highest values for C is at indices {peaks_C}\")\n",
+        "#print(\"-------\")\n",
+        "#//------//\n",
+        "\n",
+        "print(f\"The similarity between A '{name_A}' and C '{name_C}' is {token_similarity(A, C)}\")\n",
         "\n",
         "if (mix_method ==  \"None\"):\n",
         "  print(\"No operation\")\n",
@@ -145,14 +197,15 @@
         "if (mix_method ==  \"Average\"):\n",
         "  A = w*A + (1-w)*C\n",
         "  _A = LA.vector_norm(A, ord=2)\n",
-        "  print(\"Tokenized prompt tensor A has been recalculated as A = w*A + (1-w)*C , where C is the tokenized prompt  'mix_with' tensor C\")\n",
+        "  print(f\"Tokenized prompt tensor A '{name_A}' token has been recalculated as A = w*A + (1-w)*C , where C is '{name_C}' token , for w = {w}  \")\n",
         "\n",
         "if (mix_method ==  \"Subtract\"):\n",
-        "  tmp = (A/_A) - (C/_C)\n",
-        "  _tmp = LA.vector_norm(tmp, ord=2)\n",
-        "  A = tmp*((w*_A + (1-w)*_C)/_tmp)\n",
+        "  tmp =  w*A - (1-w)*C\n",
+        "  _tmp =  LA.vector_norm(tmp, ord=2)\n",
+        "  A = (_A/_tmp)*tmp\n",
+        "  #//---//\n",
         "  _A = LA.vector_norm(A, ord=2)\n",
-        "  print(\"Tokenized prompt tensor A has been recalculated as A = (w*_A + (1-w)*_C) * norm(w*A - (1-w)*C) , where C is the tokenized prompt 'mix_with' tensor C\")\n",
+        "  print(f\"Tokenized prompt tensor A '{name_A}' token has been recalculated as A = _A * norm(w*A  - (1-w)*C) , where C is '{name_C}' token , for w = {w} \")\n",
         "\n",
         "#OPTIONAL : Add/subtract + normalize above result with another token. Leave field empty to get a random value tensor\n",
         "\n",
@@ -166,14 +219,6 @@
         "  result = result.item()\n",
         "  dots[index] = result\n",
         "\n",
-        "name_A = \"A of random type\"\n",
-        "if (id_A>-1):\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",
-        "\n",
         "\n",
         "sorted, indices = torch.sort(dots,dim=0 , descending=True)\n",
         "#----#\n",
@@ -194,11 +239,11 @@
         "\n",
         "\n",
         "if (print_Divider):\n",
-        "  print('//---//') # % value\n",
+        "  print('//---//')\n",
         "\n",
-        "print('') # % value\n",
-        "print('Here is the result : ') # % value\n",
-        "print('') # % value\n",
+        "print('')\n",
+        "print('Here is the result : ')\n",
+        "print('')\n",
         "\n",
         "for index in range(list_size):\n",
         "  id = indices[index].item()\n",
@@ -207,14 +252,15 @@
         "  if (print_ID):\n",
         "    print(f'ID = {id}') # IDs\n",
         "  if (print_Similarity):\n",
-        "    print(f'similiarity = {round(sorted[index].item()*100,2)} %') # % value\n",
+        "    print(f'similiarity = {round(sorted[index].item()*100,2)} %')\n",
         "  if (print_Divider):\n",
         "    print('--------')\n",
         "\n",
         "#Print the sorted list from above result"
       ],
       "metadata": {
-        "id": "iWeFnT1gAx6A"
+        "id": "iWeFnT1gAx6A",
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -250,7 +296,8 @@
       ],
       "metadata": {
         "id": "QQOjh5BvnG8M",
-        "collapsed": true
+        "collapsed": true,
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []