SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fall back to slow image processor in ImageProcessingAuto when no fast processor available (#34785)

Browse Source 
* refactor image_processing_auto logic

* fix fast image processor tests

* Fix tests fast vit image processor

* Add safeguard when use_fast True and torchvision not available

* change default use_fast back to None, add warnings

* remove debugging print

* call get_image_processor_class_from_name once
This commit is contained in:
Yoni Gozlan
2024-12-15 14:00:36 -05:00
committed by GitHub
parent ca03842cdc
commit 5615a39369
8 changed files with 72 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
docs/source/en/main_classes/image_processor.md
View File

@@ -27,6 +27,7 @@ from transformers import AutoImageProcessor
processor = AutoImageProcessor.from_pretrained("facebook/detr-resnet-50", use_fast=True)
```
Note that `use_fast` will be set to `True` by default in a future release.
When using a fast image processor, you can also set the `device` argument to specify the device on which the processing should be done. By default, the processing is done on the same device as the inputs if the inputs are tensors, or on the CPU otherwise.
@@ -42,21 +43,17 @@ images_processed = processor(images, return_tensors="pt", device="cuda")
Here are some speed comparisons between the base and fast image processors for the `DETR` and `RT-DETR` models, and how they impact overall inference time:
<div class="flex">
<div>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_detr_fast_padded.png" />
</div>
<div>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_detr_fast_batched_compiled.png" />
</div>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_detr_fast_padded.png" />
</div>
<div class="flex">
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_detr_fast_batched_compiled.png" />
</div>
<div class="flex">
<div>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_rt_detr_fast_single.png" />
</div>
<div>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_rt_detr_fast_batched.png" />
</div>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_rt_detr_fast_single.png" />
</div>
<div class="flex">
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/benchmark_results_full_pipeline_rt_detr_fast_batched.png" />
</div>
These benchmarks were run on an [AWS EC2 g5.2xlarge instance](https://aws.amazon.com/ec2/instance-types/g5/), utilizing an NVIDIA A10G Tensor Core GPU.