convnext-base-224
Collection
21 items • Updated
How to use tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-classification", model="tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000")
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("tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000")
model = AutoModelForImageClassification.from_pretrained("tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000")# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000")
model = AutoModelForImageClassification.from_pretrained("tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000")Fine-tuned ResNet model on dataset eurosat.
This is a merged model created using fusion-bench.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
_recursive_: false
_target_: fusion_bench.method.classification.image_classification_finetune.ImageClassificationFineTuning
_usage_: null
_version_: 0.2.31.dev0
dataloader_kwargs:
batch_size: 64
num_workers: 8
pin_memory: true
label_smoothing: 0
lr_scheduler: null
max_epochs: -1
max_steps: 4000
optimizer:
_target_: torch.optim.SGD
lr: 0.01
momentum: 0.9
weight_decay: 0.0001
save_interval: 1000
save_on_train_epoch_end: false
save_top_k: -1
training_data_ratio: null
_recursive_: false
_target_: fusion_bench.modelpool.convnext_for_image_classification.ConvNextForImageClassificationPool
_usage_: null
_version_: 0.2.31.dev0
models:
_pretrained_:
config_path: facebook/convnext-base-224
dataset_name: eurosat
pretrained: true
test_datasets: null
train_datasets:
eurosat:
_target_: datasets.load_dataset
path: tanganke/eurosat
split: train
val_datasets:
eurosat:
_target_: datasets.load_dataset
path: tanganke/eurosat
split: test
Base model
facebook/convnext-base-224
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")