This Operator generates feature vectors from the pytorch pretrained **Resnet50** mode, which is trained on [COCO dataset](https://cocodataset.org/#download).
This Operator generates feature vectors from the pytorch pretrained **Resnet50** mode, which is trained on [imagenet dataset](https://image-net.org/download.php).
**Resnet** models were proposed in “[Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)”, this model was the winner of ImageNet challenge in 2015. The fundamental breakthrough with ResNet was it allowed us to train extremely deep neural networks with 150+layers successfully. Prior to ResNet training very deep neural networks was difficult due to the problem of vanishing gradients.
**Resnet** models were proposed in “[Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)”, this model was the winner of ImageNet challenge in 2015. "The fundamental breakthrough with ResNet was it allowed us to train extremely deep neural networks with 150+layers successfully. Prior to ResNet training very deep neural networks was difficult due to the problem of vanishing gradients"[1].
## Interface
@ -32,7 +32,7 @@ This Operator generates feature vectors from the pytorch pretrained **Resnet50**
### Requirements
You can get the required python package by [requirements.txt](./requirements.txt) and [pytorch/requirements.txt](./pytorch/requirements.txt). In fact, Towhee will automatically install these packages when you first load the Operator Repo, so you don't need to install them manually, here is just a list.
You can get the required python package by [requirements.txt](./requirements.txt) and [pytorch/requirements.txt](./pytorch/requirements.txt). Towhee will automatically install these packages when you first load the Operator Repo, so you don't need to install them manually, here is just a list.
- towhee
- torch
@ -45,7 +45,7 @@ The `towhee/resnet50-image-embedding` Operator implements the function of image
When using this Operator to write Pipline's Yaml file, you need to declare the following content according to the interface of Resnet50ImageEmbedding class:
When using this Operator to write Pipeline's Yaml file, you need to declare the following content according to the interface of Resnet50ImageEmbedding class:
```yaml
operators:
@ -80,7 +80,7 @@ dataframes:
vtype: 'numpy.ndarray'
```
We can see that in yaml, the **operator** part declares the `init_args` of the class and the` input` and `output`dataframe, and the **dataframe** declares the parameter `name` and `vtype`.
We can see that in yaml, the **operator** part declares the `init_args` of the class and the` input` and `output`dataframe, and the **dataframe** declares the parameter `name` and `vtype`.
