Upload sd_token_similarity_calculator.ipynb

sd_token_similarity_calculator.ipynb

@@ -25,15 +25,6 @@
         "id": "L7JTcbOdBPfh"
       }
     },
-    {
-      "cell_type": "code",
-      "source": [],
-      "metadata": {
-        "id": "PBwVIuAjEdHA"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
     {
       "cell_type": "code",
       "source": [
@@ -228,6 +219,42 @@
       "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 = True # @param {type:\"boolean\"}\n",
+        "\n",
+        "from transformers import  CLIPProcessor, CLIPModel\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:\"' + prompt_A + '\" and B: \"' + prompt_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"
+      ],
+      "metadata": {
+        "id": "QQOjh5BvnG8M",
+        "collapsed": true
+      },
+      "execution_count": null,
+      "outputs": []
+    },
     {
       "cell_type": "markdown",
       "source": [
@@ -256,7 +283,8 @@
         "#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"
+        "id": "RPdkYzT2_X85",
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -284,7 +312,8 @@
         "_P = LA.vector_norm(A, ord=2)\n"
       ],
       "metadata": {
-        "id": "YqdiF8DIz9Wu"
+        "id": "YqdiF8DIz9Wu",
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -340,7 +369,8 @@
       ],
       "metadata": {
         "id": "oXbNSRSKPgRr",
-        "collapsed": true
+        "collapsed": true,
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -382,7 +412,8 @@
       ],
       "metadata": {
         "id": "juxsvco9B0iV",
-        "collapsed": true
+        "collapsed": true,
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -419,7 +450,8 @@
       ],
       "metadata": {
         "id": "YIEmLAzbHeuo",
-        "collapsed": true
+        "collapsed": true,
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []
@@ -440,47 +472,8 @@
       ],
       "metadata": {
         "id": "MwmOdC9cNZty",
-        "collapsed": true
-      },
-      "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 = True # @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:\"' + prompt_A + '\" and B: \"' + prompt_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",
-        "collapsed": true
+        "collapsed": true,
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []