This resource is using open-source code maintained in github (see the quick-start-guide section) and available for download from NGC

The ResNet50 v1.5 model is a modified version of the original ResNet50 v1 model.

The difference between v1 and v1.5 is that, in the bottleneck blocks which requires downsampling, v1 has stride = 2 in the first 1x1 convolution, whereas v1.5 has stride = 2 in the 3x3 convolution.

This difference makes ResNet50 v1.5 slightly more accurate (~0.5% top1) than v1, but comes with a smallperformance drawback (~5% imgs/sec).

The model is initialized as described in Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification

This model is trained with mixed precision using Tensor Cores on Volta, Turing, and the NVIDIA Ampere GPU architectures. Therefore, researchers can get results over 2x faster than training without Tensor Cores, while experiencing the benefits of mixed precision training. This model is tested against each NGC monthly container release to ensure consistent accuracy and performance over time.

We are currently working on adding NHWC data layout support for Mixed Precision training.

Default configuration

The following sections highlight the default configurations for the ResNet50 model.

Optimizer

This model uses SGD with momentum optimizer with the following hyperparameters:

• Momentum (0.875)
• Learning rate (LR) = 0.256 for 256 batch size, for other batch sizes we linearly scale the learning rate.
• Learning rate schedule - we use cosine LR schedule
• For bigger batch sizes (512 and up) we use linear warmup of the learning rate during the first couple of epochs according to Training ImageNet in 1 hour. Warmup length depends on the total training length.
• Weight decay (WD)= 3.0517578125e-05 (1/32768).
• We do not apply WD on Batch Norm trainable parameters (gamma/bias)
• Label smoothing = 0.1
• We train for:
  • 50 Epochs -> configuration that reaches 75.9% top1 accuracy
  • 90 Epochs -> 90 epochs is a standard for ImageNet networks
  • 250 Epochs -> best possible accuracy.
• For 250 epoch training we also use MixUp regularization.

Data augmentation

This model uses the following data augmentation:

• For training:
  • Normalization
  • Random resized crop to 224x224
    • Scale from 8% to 100%
    • Aspect ratio from 3/4 to 4/3
  • Random horizontal flip
• For inference:
  • Normalization
  • Scale to 256x256
  • Center crop to 224x224

Other training recipes

This script does not target any specific benchmark. There are changes that others have made which can speed up convergence and/or increase accuracy.

One of the more popular training recipes is provided by fast.ai.

The fast.ai recipe introduces many changes to the training procedure, one of which is progressive resizing of the training images.

The first part of training uses 128px images, the middle part uses 224px images, and the last part uses 288px images. The final validation is performed on 288px images.

Training script in this repository performs validation on 224px images, just like the original paper described.

These two approaches can't be directly compared, since the fast.ai recipe requires validation on 288px images, and this recipe keeps the original assumption that validation is done on 224px images.

Using 288px images means that a lot more FLOPs are needed during inference to reach the same accuracy.

Feature support matrix

The following features are supported by this model:

Features

• NVIDIA DALI - DALI is a library accelerating data preparation pipeline. To accelerate your input pipeline, you only need to define your data loader with the DALI library. For more information about DALI, refer to the DALI product documentation.

• APEX is a PyTorch extension that contains utility libraries, such as Automatic Mixed Precision (AMP), which require minimal network code changes to leverage Tensor Cores performance. Refer to the Enabling mixed precision section for more details.

DALI

We use NVIDIA DALI, which speeds up data loading when CPU becomes a bottleneck. DALI can use CPU or GPU, and outperforms the PyTorch native dataloader.

Run training with --data-backends dali-gpu or --data-backends dali-cpu to enable DALI. For DGXA100 and DGX1 we recommend --data-backends dali-cpu, for DGX2 we recommend --data-backends dali-gpu.

Mixed precision training

Mixed precision is the combined use of different numerical precisions in a computational method. Mixed precision training offers significant computational speedup by performing operations in half-precision format, while storing minimal information in single-precision to retain as much information as possible in critical parts of the network. Since the introduction of Tensor Cores in Volta, and following with both the Turing and Ampere architectures, significant training speedups are experienced by switching to mixed precision -- up to 3x overall speedup on the most arithmetically intense model architectures. Using mixed precision training requires two steps:

1. Porting the model to use the FP16 data type where appropriate.
2. Adding loss scaling to preserve small gradient values.

The ability to train deep learning networks with lower precision was introduced in the Pascal architecture and first supported in CUDA 8 in the NVIDIA Deep Learning SDK.

For information about:

• How to train using mixed precision, see the Mixed Precision Training paper and Training With Mixed Precision documentation.
• Techniques used for mixed precision training, see the Mixed-Precision Training of Deep Neural Networks blog.
• APEX tools for mixed precision training, see the NVIDIA Apex: Tools for Easy Mixed-Precision Training in PyTorch.

Enabling mixed precision

Mixed precision is enabled in PyTorch by using the Automatic Mixed Precision (AMP), a library from APEX that casts variables to half-precision upon retrieval, while storing variables in single-precision format. Furthermore, to preserve small gradient magnitudes in backpropagation, a loss scaling step must be included when applying gradients. In PyTorch, loss scaling can be easily applied by using scale_loss() method provided by AMP. The scaling value to be used can be dynamic or fixed.

For an in-depth walk through on AMP, check out sample usage here. APEX is a PyTorch extension that contains utility libraries, such as AMP, which require minimal network code changes to leverage tensor cores performance.

To enable mixed precision, you can:

• Import AMP from APEX:

  from apex import amp
  

• Wrap model and optimizer in amp.initialize:

  model, optimizer = amp.initialize(model, optimizer, opt_level="O1", loss_scale="dynamic")
  

• Scale loss before backpropagation:

  with amp.scale_loss(loss, optimizer) as scaled_loss:
    scaled_loss.backward()
  

Enabling TF32

TensorFloat-32 (TF32) is the new math mode in NVIDIA A100 GPUs for handling the matrix math also called tensor operations. TF32 running on Tensor Cores in A100 GPUs can provide up to 10x speedups compared to single-precision floating-point math (FP32) on Volta GPUs.

TF32 Tensor Cores can speed up networks using FP32, typically with no loss of accuracy. It is more robust than FP16 for models which require high dynamic range for weights or activations.

For more information, refer to the TensorFloat-32 in the A100 GPU Accelerates AI Training, HPC up to 20x blog post.

TF32 is supported in the NVIDIA Ampere GPU architecture and is enabled by default.