cleaned up pytorch_to_onnx.ipynb

Author: VibhuJawa

rapids_triton_example/example_client.ipynb

@@ -189,7 +189,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.63 ms ± 71.1 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+      "2.79 ms ± 381 µs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -230,7 +230,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "16 ms ± 599 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+      "15.7 ms ± 184 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
      ]
     }
    ],
@@ -250,7 +250,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "60.9 ms ± 216 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+      "59.8 ms ± 1.13 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],

rapids_triton_example/pytorch_to_onnx/pytorch_to_trt.ipynb rapids_triton_example/pytorch_to_onnx/pytorch_to_onnx.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 1,
    "id": "1bc79bfd-5c67-4da6-acda-dc70b97981d0",
    "metadata": {},
    "outputs": [],
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 2,
    "id": "b1fa7a6e-3cc9-44db-8c59-ee824b7a6061",
    "metadata": {},
    "outputs": [],
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 3,
    "id": "561648c9-41aa-445d-a0aa-d4ed4837903b",
    "metadata": {},
    "outputs": [],
@@ -45,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 4,
    "id": "8c44b4de-2f03-4af3-a413-76baa24307ab",
    "metadata": {},
    "outputs": [],
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 5,
    "id": "8a53dc2f-2e8c-4e1e-9b45-90efb68b35ab",
    "metadata": {},
    "outputs": [],
@@ -95,15 +95,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 6,
    "id": "62ee0aed-61d1-414c-8e78-b76b8d98759c",
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight']\n",
+      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight']\n",
       "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
       "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
      ]
@@ -130,7 +130,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 7,
    "id": "5d243431-dc7a-48d0-a644-affc51ca4ae4",
    "metadata": {},
    "outputs": [],
@@ -142,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 8,
    "id": "bab6c4ec-8a14-4ef0-9103-64bf5fbed6f9",
    "metadata": {},
    "outputs": [],
@@ -171,7 +171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 9,
    "id": "9f4a66f5-83a7-4f0b-b766-3b04cbe904bb",
    "metadata": {},
    "outputs": [
@@ -181,7 +181,7 @@
        "torch.int32"
       ]
      },
-     "execution_count": 77,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -195,14 +195,15 @@
    "id": "7aca03dc-8a24-45be-a699-163c652b7f01",
    "metadata": {},
    "source": [
-    "# Optimize ONNX \n",
+    "## Optimize BERT ONNX \n",
+    "(Currently makes it slower :-( ) \n",
     "\n",
-    "https://pypi.org/project/onnxruntime-tools/"
+    "See Docs at: https://pypi.org/project/onnxruntime-tools/"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 10,
    "id": "1158ceed-0ba1-4325-88aa-18c950031a5c",
    "metadata": {},
    "outputs": [
@@ -247,16 +248,10 @@
     "    num_heads=12,\n",
     "    hidden_size=768,\n",
     "    use_gpu=True)\n",
-    "opt_model.save_model_to_file('sentimet_bert.opt.onnx')"
+    "\n",
+    "\n",
+    "opt_model.save_model_to_file('sentiment_bert.opt.onnx')"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4b7ce667-0ad4-4cb9-89b6-8d096ad2698a",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {