Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
pre-train_cpp – AI Model by koba-jon | AlphaNeural AI
You can deploy this model and start earning money today!
koba-jon
/
pre-train_cpp
like
0
image-classification
en
ILSVRC/imagenet-1k
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ImageNet Pre-trained Model C++
These are the models pre-trained with ImageNet-1k in C++.
1. Dataset
ImageNet-1k
data: 1,281,167
class: 1,000
2. Model
(1) vgg11_bn.pth
model:
VGGNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 11
BN: true
epochs: 50
size: 224
batch_size: 64
nc: 3
(2) vgg13_bn.pth
model:
VGGNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 13
BN: true
epochs: 50
size: 224
batch_size: 64
nc: 3
(3) vgg16_bn.pth
model:
VGGNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 16
BN: true
epochs: 50
size: 224
batch_size: 64
nc: 3
(4) vgg19_bn.pth
model:
VGGNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 19
BN: true
epochs: 50
size: 224
batch_size: 64
nc: 3
(5) resnet18.pth
model:
ResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 18
epochs: 50
size: 224
batch_size: 64
nc: 3
(6) resnet34.pth
model:
ResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 34
epochs: 50
size: 224
batch_size: 64
nc: 3
(7) resnet50.pth
model:
ResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 50
epochs: 50
size: 224
batch_size: 64
nc: 3
(8) resnet101.pth
model:
ResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 101
epochs: 50
size: 224
batch_size: 64
nc: 3
(9) resnet152.pth
model:
ResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 152
epochs: 50
size: 224
batch_size: 64
nc: 3
(10) wide_resnet50_2.pth
model:
WideResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 50
epochs: 50
size: 224
batch_size: 64
nc: 3
(11) wide_resnet101_2.pth
model:
WideResNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
n_layers: 101
epochs: 50
size: 224
batch_size: 64
nc: 3
(12) efficientnet_b0.pth
model:
EfficientNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(224, 224), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
network: B0
epochs: 50
batch_size: 64
nc: 3
(13) efficientnet_b1.pth
model:
EfficientNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(240, 240), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
network: B1
epochs: 50
batch_size: 64
nc: 3
(14) efficientnet_b2.pth
model:
EfficientNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(260, 260), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
network: B2
epochs: 50
batch_size: 64
nc: 3
(15) efficientnet_b3.pth
model:
EfficientNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(300, 300), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
network: B3
epochs: 50
batch_size: 64
nc: 3
(16) efficientnet_b4.pth
model:
EfficientNet
optimizer: Adam (lr: 1e-4, beta1: 0.9, beta2: 0.999)
transform: Resize(380, 380), ToTensor, Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
network: B4
epochs: 50
batch_size: 32
nc: 3
