Skip to content

Commit

Permalink
Merge pull request #2 from kungfuai/pwang_cv
Browse files Browse the repository at this point in the history
  • Loading branch information
zzsi authored Nov 1, 2023
2 parents befcffe + eea888a commit b729406
Show file tree
Hide file tree
Showing 7 changed files with 490 additions and 5 deletions.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
462 changes: 462 additions & 0 deletions course1-image-classification/intro.html

Large diffs are not rendered by default.

8 changes: 7 additions & 1 deletion course1-image-classification/intro.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,13 @@ At the end of the course. we hope you feel prepared to work on a practical proje

**How to use the course materials and organize your work**

You can run the code in each course project using Colab notebooks, whenever you see a rocket-shaped launch button in the top right corner of the page. This is a quick way to get started, without needing to install CUDA drivers and other dependencies. Alternatively, you can create a repo and accumulate source code as you evolve it in the course. Either way works.
You can run the code in each course project using Colab notebooks, whenever you see a rocket-shaped launch button in the top right corner of the page.
<p align="center">
<img src="./colab_launch_button.png" width="500" title="click on the rocket to launch Colab">
</p>

This is a quick way to get started, without needing to install CUDA drivers and other dependencies. Alternatively, you can create a repo and accumulate source code as you evolve it in the course. Either way works.


The earlier projects of the course are more like code labs, and focus on a step by step guide to set up the code base and modules to perform model training experiments. You are tasked with filling out code blocks or functions to make the system work. This likely resembles the *development* phase of a practical project, where the emphasis may be put on code quality and readability.

Expand Down
2 changes: 1 addition & 1 deletion course1-image-classification/p1_dataset_key.ipynb

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion course1-image-classification/p2_training.ipynb

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion course1-image-classification/p2_training_key.ipynb

Large diffs are not rendered by default.

19 changes: 18 additions & 1 deletion course1-image-classification/p3_dataloader.ipynb
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "Xe_2wpJ_Pe9q"
Expand All @@ -14,6 +15,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "f-WrxgnmdUyP"
Expand Down Expand Up @@ -68,6 +70,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "-OxkRLtfdt-z"
Expand All @@ -77,7 +80,13 @@
"\n",
"First we profile the dataloader for its speed in scanning data, without considering moving data to GPU for training.\n",
"\n",
"How many examples can the dataloader scan per second? How does parameters `batch_size`, `shuffle` and `num_workers` impact throughput?\n"
"How many examples can the dataloader scan per second? How does parameters `batch_size`, `shuffle` and `num_workers` impact throughput?\n",
"- batch_size (int, optional): how many samples per batch to load (default: 1)\n",
" \n",
"- shuffle (bool, optional): set to True to have the data reshuffled at every epoch (default: False).\n",
"\n",
"- num_workers (int, optional): how many subprocesses to use for data loading. 0 means that the data will be loaded in the main process. (default: 0)\n",
" \n"
]
},
{
Expand Down Expand Up @@ -312,6 +321,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "Rh3ao7A_bRWn"
Expand Down Expand Up @@ -472,6 +482,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "NM_m1B2xebqY"
Expand All @@ -487,6 +498,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "CcKb_Y-NfEwe"
Expand Down Expand Up @@ -575,6 +587,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
Expand Down Expand Up @@ -633,6 +646,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
Expand All @@ -648,6 +662,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "HVCbFLzPe4xj"
Expand Down Expand Up @@ -713,6 +728,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "t4Cptlm4v8E4"
Expand Down Expand Up @@ -951,6 +967,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
Expand Down

0 comments on commit b729406

Please sign in to comment.