Downloads · 30 days
3
1% of all-time downloads
MHanzl/DF23M-mobilenetv2_100.ra_in1k_224
DF23M-mobilenetv2_100.ra_in1k_224 is a image classification model from MHanzl. Use it when you need a label for an image. It is set up for DanishFungi. The card lists the license as cc-by-nc-4.0.
- Model Type: Danish Fungi Classification - Model Stats: - Params (M): ?? - Image size: [224, 224] x [224, 224] - Papers: - Original: ?? - Train Dataset: DF23M -- https://sites.google.com/view/danish-fungi-dataset
Downloads · 30 days
3
1% of all-time downloads
All-time downloads
211
Public
Repo size
20.1 MB
Likes
0
Public
Click a slice to open those files.
.bin10.1 MB · 100%
From the Hugging Face model README
import timm
import torch
import torchvision.transforms as T
from PIL import Image
from urllib.request import urlopen
model = timm.create_model("hf-hub:MHanzl/DF23M-mobilenetv2_100.ra_in1k_224", pretrained=True)
model = model.eval()
train_transforms = T.Compose([T.Resize([224, 224]),
T.ToTensor(),
T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
img = Image.open(PATH_TO_YOUR_IMAGE)
output = model(train_transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# output is a (1, num_features) shaped tensor