Skip to content

Commit

Permalink
Merge pull request #762 from jaelgu/image-obj-readme
Browse files Browse the repository at this point in the history
Fix typo in image object detection README
  • Loading branch information
SS authored Oct 11, 2021
2 parents 01474b7 + 7a56423 commit 71e99ce
Showing 1 changed file with 8 additions and 8 deletions.
16 changes: 8 additions & 8 deletions solutions/reverse_image_search/object_detection/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ The following is the system diagram.

## Data source

This demo uses the PASCAL VOC image set, which contains 17125 images with 20 categories: human; animals (birds, cats, cows, dogs, horses, sheep); transportation (planes, bikes,boats, buses, cars, motorcycles, trains); household (bottles, chairs, tables, pot plants, sofas, TVs)
This demo uses the PASCAL VOC image set, which contains 17125 images with 20 categories: human; animals (birds, cats, cows, dogs, horses, sheep); transportation (planes, bikes, boats, buses, cars, motorcycles, trains); household (bottles, chairs, tables, pot plants, sofas, TVs)

Dataset size: ~ 2 GB.

Expand All @@ -26,9 +26,9 @@ As shown in the architecture diagram, the system will use Milvus to store and se

- **Start Milvus v2.0**

First, you are supposed to refer to the Install [Milvus v2.0-rc5](milvus.io) for how to run Milvus docker.
First, you are supposed to refer to the Install [Milvus v2.0](https://milvus.io/docs/install_standalone-docker.md) for how to run Milvus docker.

> Note the version of Milvus.
> Note the version of Milvus should be consistent with pymilvus version.
- **Start MySQL**

Expand All @@ -38,9 +38,9 @@ $ docker run -p 3306:3306 -e MYSQL_ROOT_PASSWORD=123456 -d mysql:5.7

### 2. Start Server

The next step is to start the system server. It provides HTTP backend services, and there are two ways to start: running with Docker or source code.
The next step is to start the system server. It provides HTTP backend services, and there are two ways to start: running with Docker OR source code.

#### 2.1 Run server with Docker
#### Option 1: Run server with Docker

- **Set parameters**

Expand Down Expand Up @@ -74,7 +74,7 @@ milvusbootcamp/imgsearch-with-objdet:2.0

> **Note:** -v ${DATAPATH1}:${DATAPATH1} means that you can mount the directory into the container. If needed, you can load the parent directory or more directories.
#### 2.2 Run source code
#### Option 2: Run source code

- **Install the Python packages**

Expand Down Expand Up @@ -111,7 +111,7 @@ $ python main.py
```
- **API docs**

Vist 127.0.0.1:5010/docs in your browser to use all the APIs.
Visit 127.0.0.1:5010/docs in your browser to use all the APIs.

![fastapi](pic/fastapi.png)

Expand Down Expand Up @@ -139,7 +139,7 @@ If you are interested in our code or would like to contribute code, feel free to
│ │
│ └───src
│ │ config.py # Configuration file.
│ │ encode.py # Covert image/video/questions/... to embeddings.
│ │ encode.py # Convert image/video/questions/... to embeddings.
│ │ milvus.py # Connect to Milvus server and insert/drop/query vectors in Milvus.
│ │ mysql.py # Connect to MySQL server, and add/delete/query IDs and object information.
│ │
Expand Down

0 comments on commit 71e99ce

Please sign in to comment.