# How to run image classification on image url
**URL:**
**Author:**  [@TheNoob3131](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTheNoob3131)%5C
**Post date:** [July 20, 2022, 5:59am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-run-image-classification-on-image-url%2F20604%2F1 "2022-07-20T05:59:53Z")
My dataset has all of its photos as jpg urls, which are all strings. How can I run an image classification model like base ViT or ResNet-50 to convert the string to images?
---
**Author:**  [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [July 20, 2022, 9:23am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-run-image-classification-on-image-url%2F20604%2F2 "2022-07-20T09:23:28Z")
I usually use the requests module for that (which is part of Python):
```auto
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
image
```
---
**Author:**  [@TheNoob3131](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTheNoob3131)%5C
**Post date:** [July 20, 2022, 5:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-run-image-classification-on-image-url%2F20604%2F3 "2022-07-20T17:19:45Z")
So would I have to define a function to go through all of the rows in the ‘Image’ column? How would I accomplish that?
---
**Author:**  [@TheNoob3131](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTheNoob3131)%5C
**Post date:** [July 20, 2022, 5:21pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-run-image-classification-on-image-url%2F20604%2F4 "2022-07-20T17:21:04Z")
Or is there a way to convert the column into the feature type for images?
---
**Author:**  [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [July 21, 2022, 10:52am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-run-image-classification-on-image-url%2F20604%2F5 "2022-07-21T10:52:27Z")
Yes you can probably map them all to Pillow images and then cast to the Image feature:
```auto
from datasets import load_dataset
import requests
from PIL import Image
def to_pillow(examples):
urls = examples['Photo']
images = []
for url in urls:
image = Image.open(requests.get(url, stream=True).raw)
images.append(image)
examples['image'] = images
return examples
dataset = load_dataset("TheNoob3131/mosquito-data")
dataset = dataset.map(to_pillow, batched=True)
from datasets import Image
dataset = dataset.cast_column('image', Image)
```
I’m going to cc @mariosasko here (`map` seems to very slow). Alternatively, you can do:
```auto
dataset.set_transform(to_pillow)
```
to do this on the fly.
---
**Author:**  [@lhoestq](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flhoestq)%5C
**Post date:** [July 21, 2022, 10:58am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-run-image-classification-on-image-url%2F20604%2F6 "2022-07-21T10:58:29Z")
You can make it much faster by doing it in parallel by the way 🙂
```python
dataset = dataset.map(to_pillow, batched=True, num_proc=4)
```