Description
Pretrained Swin model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.image_classifier_swin_swin_base_patch4_window7_224_in22k_finetuned_eurosat_by_erikejw is a English model originally trained by erikejw.
How to use
image_assembler = ImageAssembler() \
.setInputCol("image") \
.setOutputCol("image_assembler")
imageClassifier = SwinForImageClassification \
.pretrained("image_classifier_swin_swin_base_patch4_window7_224_in22k_finetuned_eurosat_by_erikejw", "en") \
.setInputCols("image_assembler") \
.setOutputCol("class")
pipeline = Pipeline(stages=[
image_assembler,
imageClassifier,
])
pipelineModel = pipeline.fit(imageDF)
pipelineDF = pipelineModel.transform(imageDF)
val image_assembler = new ImageAssembler()
.setInputCol("image")
.setOutputCol("image_assembler")
val imageClassifier = SwinForImageClassification
.pretrained("image_classifier_swin_swin_base_patch4_window7_224_in22k_finetuned_eurosat_by_erikejw", "en")
.setInputCols("image_assembler")
.setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(image_assembler, imageClassifier))
val pipelineModel = pipeline.fit(imageDF)
val pipelineDF = pipelineModel.transform(imageDF)
Model Information
| Model Name: | image_classifier_swin_swin_base_patch4_window7_224_in22k_finetuned_eurosat_by_erikejw |
| Compatibility: | Spark NLP 4.4.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [image_assembler] |
| Output Labels: | [class] |
| Language: | en |
| Size: | 657.9 MB |