resnet101d.ra2_in1k

Model card for resnet101d.ra2_in1k

A ResNet-D image classification model.

This model features:

• ReLU activations
• 3-layer stem of 3x3 convolutions with pooling
• 2x2 average pool + 1x1 convolution shortcut downsample

Trained on ImageNet-1k in timm using recipe template described below.

Recipe details:

• RandAugment RA2 recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back.
• RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
• Step (exponential decay w/ staircase) LR schedule with warmup

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 44.6
  • GMACs: 10.5
  • Activations (M): 22.3
  • Image size: train = 256 x 256, test = 320 x 320
• Papers:
  • ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
  • Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
  • Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
• Original: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

from urllib.request import urlopen
from PIL import Image
import jax

import jaxnn

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg'
))

model = jaxnn.create_model('resnet101d.ra2_in1k', pretrained=True)
model.eval()

# get model specific transforms (normalization, resize)
data_config = jaxnn.data.resolve_model_data_config(model)
transforms = jaxnn.data.create_transform(**data_config, is_training=False)

output = model(jax.numpy.expand_dims(transforms(img), 0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = jax.lax.top_k(jax.nn.softmax(output, axis=-1) * 100, k=5)

Feature Map Extraction

from urllib.request import urlopen
from PIL import Image
import jax

import jaxnn

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg'
))

model = jaxnn.create_model(
    'resnet101d.ra2_in1k',
    pretrained=True,
    features_only=True,
)
model.eval()

# get model specific transforms (normalization, resize)
data_config = jaxnn.data.resolve_model_data_config(model)
transforms = jaxnn.data.create_transform(**data_config, is_training=False)

output = model(jax.numpy.expand_dims(transforms(img), 0))  # jax.numpy.expand_dims single image into batch of 1

for o in output:
    # print shape of each feature map in output in format [Batch, Height, Width, Channels]
    # e.g.:
    #  (1, 112, 112, 64)
    #  (1, 56, 56, 64)
    #  (1, 28, 28, 128)
    #  (1, 14, 14, 256)
    #  (1, 7, 7, 512)

    print(o.shape)

Image Embeddings

from urllib.request import urlopen
from PIL import Image
import jax

import jaxnn

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg'
))

model = jaxnn.create_model(
    'resnet101d.ra2_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model.eval()

# get model specific transforms (normalization, resize)
data_config = jaxnn.data.resolve_model_data_config(model)
transforms = jaxnn.data.create_transform(**data_config, is_training=False)

output = model(jax.numpy.expand_dims(transforms(img), 0))   # output is (batch_size, num_features) shaped Array

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(jax.numpy.expand_dims(transforms(img), 0))
# output is unpooled, a (1, 7, 7, 512) shaped tensor