Instructions to use microsoft/cvt-21-384-22k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/cvt-21-384-22k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="microsoft/cvt-21-384-22k") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("microsoft/cvt-21-384-22k") model = AutoModelForImageClassification.from_pretrained("microsoft/cvt-21-384-22k") - Notebooks
- Google Colab
- Kaggle
Add TF weights
Browse filesModel converted by the [`transformers`' `pt_to_tf` CLI](https://github.com/huggingface/transformers/blob/main/src/transformers/commands/pt_to_tf.py). All converted model outputs and hidden layers were validated against its Pytorch counterpart.
Maximum crossload output difference=4.902e-04; Maximum crossload hidden layer difference=1.125e-01;
Maximum conversion output difference=4.902e-04; Maximum conversion hidden layer difference=1.125e-01;
CAUTION: The maximum admissible error was manually increased to 0.15!
- tf_model.h5 +3 -0
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e49dd31400a7d6ee7d3f4180c3f49111da200714c00aa0b055fdcf29fca8a6db
|
| 3 |
+
size 127615848
|