*Total -- 39,035.18kb -> 33,033.99kb (15.37%)

/TensorFlow/LanguageModeling/BERT/data/images/images_nvlamb.png -- 86.10kb -> 32.65kb (62.08%)
/TensorFlow2/LanguageModeling/BERT/data/images/images_nvlamb.png -- 86.10kb -> 32.65kb (62.08%)
/PyTorch/LanguageModeling/BERT/images/nvlamb.png -- 86.10kb -> 32.65kb (62.08%)
/TensorFlow/LanguageModeling/BERT/data/images/images_nvlamb_2.png -- 88.62kb -> 33.91kb (61.74%)
/PyTorch/Classification/GPUNet/figs/search_space.png -- 35.85kb -> 13.79kb (61.53%)
/TensorFlow/Classification/ConvNets/se-resnext101-32x4d/imgs/SEArch.png -- 76.28kb -> 29.41kb (61.44%)
/PyTorch/Classification/ConvNets/se-resnext101-32x4d/img/SEArch.png -- 76.28kb -> 29.41kb (61.44%)
/PyTorch/Detection/img/2_object-detection-figure-2.png -- 66.30kb -> 25.77kb (61.13%)
/TensorFlow/Detection/img/2_object-detection-figure-2.png -- 66.30kb -> 25.77kb (61.13%)
/CUDA-Optimized/FastSpeech/materials/loss.png -- 196.71kb -> 85.07kb (56.75%)
/TensorFlow2/Segmentation/UNet_Medical/images/training_throughput.png -- 13.55kb -> 5.95kb (56.07%)
/TensorFlow2/Segmentation/UNet_Medical/images/inference_throughput.png -- 13.83kb -> 6.08kb (56.06%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/TSPP_Architecture.png -- 74.71kb -> 38.26kb (48.79%)
/PyTorch/Detection/SSD/img/ssd_diagram.png -- 51.71kb -> 26.76kb (48.25%)
/PyTorch/Classification/ConvNets/img/ACCvsFLOPS.png -- 47.29kb -> 25.96kb (45.11%)
/PyTorch/Classification/ConvNets/resnext101-32x4d/img/top5_plot.png -- 29.02kb -> 16.65kb (42.63%)
/PyTorch/Classification/ConvNets/resnet50v1.5/img/loss_plot.png -- 30.31kb -> 17.47kb (42.36%)
/PyTorch/Classification/ConvNets/resnet50v1.5/img/top5_plot.png -- 31.19kb -> 18.02kb (42.24%)
/PyTorch/Classification/ConvNets/resnext101-32x4d/img/loss_plot.png -- 28.38kb -> 16.41kb (42.19%)
/PyTorch/Segmentation/nnUNet/images/unet3d.png -- 115.37kb -> 66.94kb (41.98%)
/TensorFlow2/Segmentation/nnUNet/images/unet3d.png -- 115.37kb -> 66.94kb (41.98%)
/PyTorch/Classification/ConvNets/se-resnext101-32x4d/img/loss_plot.png -- 30.72kb -> 17.90kb (41.71%)
/PyTorch/Classification/ConvNets/se-resnext101-32x4d/img/top1_plot.png -- 31.93kb -> 18.67kb (41.53%)
/PyTorch/Classification/ConvNets/resnext101-32x4d/img/top1_plot.png -- 32.02kb -> 18.74kb (41.47%)
/PyTorch/Classification/ConvNets/se-resnext101-32x4d/img/top5_plot.png -- 28.87kb -> 16.91kb (41.43%)
/PyTorch/Classification/ConvNets/resnet50v1.5/img/top1_plot.png -- 34.11kb -> 20.08kb (41.15%)
/DGLPyTorch/DrugDiscovery/SE3Transformer/images/se3-transformer.png -- 1,162.92kb -> 702.24kb (39.61%)
/PyTorch/Classification/ConvNets/img/LATvsTHR.png -- 61.13kb -> 37.66kb (38.39%)
/TensorFlow/LanguageModeling/BERT/data/images/bert_pipeline.png -- 207.54kb -> 133.29kb (35.77%)
/TensorFlow2/LanguageModeling/BERT/data/images/bert_pipeline.png -- 207.54kb -> 133.29kb (35.77%)
/PyTorch/SpeechSynthesis/FastPitch/img/fastpitch_model.png -- 29.18kb -> 19.11kb (34.5%)
/TensorFlow/Segmentation/UNet_Industrial/images/unet.png -- 668.53kb -> 447.82kb (33.01%)
/PyTorch/Translation/GNMT/img/diagram.png -- 347.25kb -> 248.60kb (28.41%)
/TensorFlow/Translation/GNMT/img/diagram.png -- 347.25kb -> 248.60kb (28.41%)
/PyTorch/SpeechRecognition/QuartzNet/img/tcs_conv.png -- 37.04kb -> 26.79kb (27.68%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_arch.png -- 88.12kb -> 65.50kb (25.68%)
/TensorFlow/Segmentation/UNet_3D_Medical/images/unet3d.png -- 19.52kb -> 14.60kb (25.24%)
/TensorFlow/LanguageModeling/Transformer-XL/tf/img/model.png -- 694.46kb -> 520.19kb (25.09%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/model.png -- 694.46kb -> 520.19kb (25.09%)
/TensorFlow/Segmentation/UNet_Medical/images/unet.png -- 100.85kb -> 75.65kb (24.98%)
/TensorFlow2/Segmentation/UNet_Medical/images/unet.png -- 100.85kb -> 75.65kb (24.98%)
/CUDA-Optimized/FastSpeech/materials/fastspeech_arch.png -- 324.90kb -> 243.95kb (24.91%)
/PyTorch/SpeechSynthesis/HiFiGAN/img/hifigan_model.png -- 58.82kb -> 44.30kb (24.68%)
/TensorFlow2/Detection/Efficientdet/testdata/loss.png -- 24.55kb -> 18.54kb (24.5%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_fp16_loss.png -- 28.16kb -> 21.59kb (23.34%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_a100_amp_loss.png -- 20.49kb -> 15.71kb (23.33%)
/MxNet/Classification/RN50v1.5/img/residual_diagram.png -- 25.23kb -> 19.35kb (23.32%)
/PyTorch/SpeechRecognition/Jasper/images/tensorrt_2s.png -- 149.27kb -> 114.63kb (23.21%)
/PyTorch/Translation/Transformer/decorrelation_threshold.png -- 173.12kb -> 133.51kb (22.88%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_a100_amp_loss.png -- 19.05kb -> 14.73kb (22.66%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_fp32_loss.png -- 50.44kb -> 39.14kb (22.39%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 159.60kb -> 123.93kb (22.35%)
/PyTorch/LanguageModeling/BERT/images/loss_curves.png -- 56.80kb -> 44.19kb (22.2%)
/TensorFlow/Recommendation/VAE-CF/images/autoencoder.png -- 80.94kb -> 63.05kb (22.11%)
/TensorFlow/Segmentation/VNet/images/V-Net_TF1_conv.png -- 44.48kb -> 34.67kb (22.04%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 162.73kb -> 127.20kb (21.83%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 41.14kb -> 32.18kb (21.8%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_a100_tf32_loss.png -- 19.39kb -> 15.19kb (21.66%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_a100_tf32_loss.png -- 18.48kb -> 14.49kb (21.61%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 40.81kb -> 32.47kb (20.43%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 158.28kb -> 126.06kb (20.35%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 156.35kb -> 124.61kb (20.3%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 167.13kb -> 133.31kb (20.24%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 37.07kb -> 29.57kb (20.23%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 149.75kb -> 119.50kb (20.2%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 152.15kb -> 121.66kb (20.04%)
/PyTorch/Recommendation/NCF/img/box_plots.png -- 38.03kb -> 30.44kb (19.96%)
/TensorFlow2/Recommendation/WideAndDeep/img/amp_influence.svg -- 52.96kb -> 42.44kb (19.87%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/training_loss_large_multinode.png -- 49.23kb -> 39.47kb (19.82%)
/PyTorch/SpeechSynthesis/Tacotron2/img/Taco2WG_train_loss.png -- 52.14kb -> 41.82kb (19.8%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 181.25kb -> 145.77kb (19.57%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 171.17kb -> 137.70kb (19.55%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 42.50kb -> 34.21kb (19.51%)
/TensorFlow/Segmentation/VNet/images/vnet.png -- 166.44kb -> 134.18kb (19.38%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 184.25kb -> 148.63kb (19.34%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_27_triton_performance_offline_27/plots/throughput_vs_batch.png -- 43.40kb -> 35.01kb (19.33%)
/TensorFlow/Segmentation/UNet_Medical/images/U-NetMed_TF1_conv.png -- 42.79kb -> 34.53kb (19.3%)
/TensorFlow2/Segmentation/MaskRCNN/documentation/learning_curves.png -- 53.90kb -> 43.51kb (19.27%)
/PyTorch/Translation/Transformer/transformer.png -- 191.70kb -> 154.77kb (19.27%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_6_triton_performance_offline_6/plots/latency_vs_batch.png -- 42.60kb -> 34.44kb (19.16%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_28_triton_performance_offline_28/plots/throughput_vs_batch.png -- 42.98kb -> 34.78kb (19.1%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 38.26kb -> 30.96kb (19.07%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 38.12kb -> 30.86kb (19.04%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 38.35kb -> 31.05kb (19.03%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 187.18kb -> 151.84kb (18.88%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 39.36kb -> 31.95kb (18.82%)
/TensorFlow2/Segmentation/UNet_Medical/images/U-NetMed_TF2_conv.png -- 34.60kb -> 28.12kb (18.75%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 45.70kb -> 37.24kb (18.52%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 45.70kb -> 37.24kb (18.52%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 35.90kb -> 29.26kb (18.49%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 181.18kb -> 147.95kb (18.34%)
/PyTorch/SpeechRecognition/Jasper/images/jasper_dense_residual.png -- 246.20kb -> 201.10kb (18.32%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_18_triton_performance_offline_18/plots/throughput_vs_batch.png -- 42.16kb -> 34.46kb (18.27%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_17_triton_performance_offline_17/plots/throughput_vs_batch.png -- 41.74kb -> 34.16kb (18.17%)
/PyTorch/Classification/ConvNets/efficientnet/img/loss_plot.png -- 20.13kb -> 16.48kb (18.15%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 35.94kb -> 29.43kb (18.12%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 38.62kb -> 31.62kb (18.12%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_offline_28/plots/throughput_vs_batch.png -- 41.38kb -> 33.89kb (18.11%)
/TensorFlow/Recommendation/NCF/img/hr_histogram.png -- 27.49kb -> 22.52kb (18.1%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_18_triton_performance_offline_18/plots/throughput_vs_batch.png -- 40.79kb -> 33.42kb (18.07%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_offline_27/plots/throughput_vs_batch.png -- 41.31kb -> 33.86kb (18.04%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 187.80kb -> 153.92kb (18.04%)
/PyTorch/SpeechSynthesis/HiFiGAN/img/loss_seeds.png -- 60.56kb -> 49.67kb (17.98%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 44.72kb -> 36.70kb (17.94%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 44.72kb -> 36.70kb (17.94%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 37.97kb -> 31.18kb (17.89%)
/TensorFlow2/Recommendation/WideAndDeep/img/training_stability.svg -- 54.13kb -> 44.45kb (17.89%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_offline_27/plots/throughput_vs_batch.png -- 40.29kb -> 33.10kb (17.83%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_offline_17/plots/throughput_vs_batch.png -- 38.54kb -> 31.68kb (17.81%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 37.10kb -> 30.50kb (17.79%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_t4_experiment_6_triton_performance_offline_6/plots/latency_vs_batch.png -- 41.37kb -> 34.02kb (17.77%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_10_triton_performance_offline_10/plots/throughput_vs_batch.png -- 45.01kb -> 37.02kb (17.76%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_a30_experiment_10_triton_performance_offline_10/plots/throughput_vs_batch.png -- 44.97kb -> 36.99kb (17.73%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_batch.png -- 38.16kb -> 31.46kb (17.58%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_27_triton_performance_offline_27/plots/throughput_vs_batch.png -- 41.08kb -> 33.87kb (17.55%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_17_triton_performance_offline_17/plots/throughput_vs_batch.png -- 39.53kb -> 32.60kb (17.52%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_28_triton_performance_offline_28/plots/throughput_vs_batch.png -- 40.51kb -> 33.42kb (17.5%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 114.30kb -> 94.34kb (17.46%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_offline_18/plots/throughput_vs_batch.png -- 38.91kb -> 32.14kb (17.41%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_offline_28/plots/throughput_vs_batch.png -- 40.17kb -> 33.19kb (17.37%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_6_triton_performance_offline_6/plots/latency_vs_batch.png -- 41.09kb -> 33.96kb (17.35%)
/PyTorch/Classification/ConvNets/efficientnet/img/top1_plot.png -- 24.33kb -> 20.15kb (17.17%)
/PyTorch/Classification/GPUNet/figs/gpunet_performance.png -- 46.86kb -> 38.84kb (17.12%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_a30_experiment_6_triton_performance_offline_6/plots/latency_vs_batch.png -- 40.22kb -> 33.36kb (17.04%)
/PyTorch/Recommendation/NCF/img/ncf_diagram.png -- 174.41kb -> 144.95kb (16.89%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_offline_18/plots/throughput_vs_batch.png -- 39.96kb -> 33.21kb (16.88%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 105.36kb -> 87.58kb (16.87%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_offline_17/plots/throughput_vs_batch.png -- 39.60kb -> 32.93kb (16.85%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_10_triton_performance_offline_10/plots/throughput_vs_batch.png -- 43.96kb -> 36.60kb (16.74%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 111.36kb -> 92.75kb (16.72%)
/PyTorch/Classification/ConvNets/efficientnet/img/top5_plot.png -- 19.71kb -> 16.42kb (16.69%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 42.43kb -> 35.35kb (16.67%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 42.43kb -> 35.35kb (16.67%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 113.45kb -> 94.76kb (16.48%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 42.37kb -> 35.40kb (16.46%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 42.37kb -> 35.40kb (16.46%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 113.02kb -> 94.42kb (16.46%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 107.46kb -> 89.80kb (16.43%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 40.32kb -> 33.70kb (16.42%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 40.32kb -> 33.70kb (16.42%)
/PyTorch/SpeechSynthesis/HiFiGAN/img/loss.png -- 66.24kb -> 55.43kb (16.33%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 105.30kb -> 88.13kb (16.31%)
/PyTorch/Recommendation/NCF/img/val_curves.png -- 77.99kb -> 65.27kb (16.3%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_fp16_loss.png -- 69.51kb -> 58.21kb (16.27%)
/PyTorch/SpeechRecognition/Jasper/images/jasper_model.png -- 295.17kb -> 247.51kb (16.15%)
/TensorFlow/Recommendation/NCF/img/ncf_diagram.png -- 128.24kb -> 107.53kb (16.15%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 39.75kb -> 33.33kb (16.15%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 39.75kb -> 33.33kb (16.15%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.89kb -> 28.43kb (16.12%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/training_loss_large.png -- 76.38kb -> 64.13kb (16.04%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 187.73kb -> 157.70kb (16%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_10_triton_performance_offline_10/plots/latency_vs_batch.png -- 40.06kb -> 33.66kb (15.97%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.40kb -> 28.08kb (15.92%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 105.45kb -> 88.67kb (15.92%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_10_triton_performance_offline_10/plots/latency_vs_batch.png -- 40.25kb -> 33.86kb (15.88%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.80kb -> 28.44kb (15.86%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 43.11kb -> 36.29kb (15.82%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 43.11kb -> 36.29kb (15.82%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 105.13kb -> 88.53kb (15.79%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 107.81kb -> 90.83kb (15.75%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 109.73kb -> 92.50kb (15.7%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_6_triton_performance_online_6/plots/latency_vs_concurrency.png -- 106.01kb -> 89.52kb (15.56%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 191.38kb -> 161.62kb (15.55%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 43.17kb -> 36.46kb (15.54%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 43.17kb -> 36.46kb (15.54%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 41.82kb -> 35.34kb (15.49%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 41.82kb -> 35.34kb (15.49%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_t4_experiment_10_triton_performance_offline_10/plots/throughput_vs_batch.png -- 44.53kb -> 37.63kb (15.49%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 115.22kb -> 97.39kb (15.47%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 128.09kb -> 108.28kb (15.47%)
/PyTorch/Segmentation/nnUNet/images/unet-brats.jpg -- 63.92kb -> 54.06kb (15.42%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_offline_17/plots/latency_vs_batch.png -- 39.16kb -> 33.13kb (15.4%)
/PyTorch/Segmentation/nnUNet/images/unet-brats22.jpg -- 60.14kb -> 50.91kb (15.34%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.29kb -> 28.20kb (15.31%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.30kb -> 28.21kb (15.29%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 35.14kb -> 29.77kb (15.29%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 42.03kb -> 35.62kb (15.25%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 42.03kb -> 35.62kb (15.25%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_6_triton_performance_online_6/plots/latency_vs_concurrency.png -- 103.50kb -> 87.73kb (15.24%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 34.14kb -> 28.97kb (15.15%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 103.19kb -> 87.56kb (15.14%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 101.26kb -> 85.94kb (15.13%)
/TensorFlow2/Recommendation/WideAndDeep/img/learning_curve.svg -- 44.66kb -> 37.90kb (15.13%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_28_triton_performance_online_28/plots/latency_vs_concurrency.png -- 112.30kb -> 95.37kb (15.08%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_6_triton_performance_offline_6/plots/throughput_vs_batch.png -- 41.23kb -> 35.02kb (15.05%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 39.04kb -> 33.17kb (15.04%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_a30_experiment_6_triton_performance_online_6/plots/latency_vs_concurrency.png -- 107.83kb -> 91.69kb (14.96%)
/PyTorch/Recommendation/DLRM/img/learning_curve_FL3.svg -- 59.96kb -> 51.02kb (14.92%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.16kb -> 28.21kb (14.91%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 99.55kb -> 84.72kb (14.89%)
/PyTorch/Recommendation/DLRM/img/learning_curve_FL15.svg -- 53.63kb -> 45.65kb (14.89%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_10_triton_performance_online_10/plots/latency_vs_concurrency.png -- 103.34kb -> 87.96kb (14.88%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 33.52kb -> 28.54kb (14.86%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 36.97kb -> 31.48kb (14.85%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 196.79kb -> 167.62kb (14.82%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_28_triton_performance_offline_28/plots/latency_vs_batch.png -- 36.92kb -> 31.47kb (14.76%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_a30_experiment_10_triton_performance_offline_10/plots/latency_vs_batch.png -- 40.38kb -> 34.43kb (14.75%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_10_triton_performance_online_10/plots/latency_vs_concurrency.png -- 105.69kb -> 90.11kb (14.75%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_28_triton_performance_offline_28/plots/latency_vs_batch.png -- 35.88kb -> 30.59kb (14.74%)
/PyTorch/Translation/GNMT/img/training_loss.png -- 295.10kb -> 251.62kb (14.74%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_offline_27/plots/latency_vs_batch.png -- 37.21kb -> 31.73kb (14.73%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 32.18kb -> 27.44kb (14.72%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 123.53kb -> 105.38kb (14.7%)
/PyTorch/Recommendation/DLRM/img/amp_impact_fl3_21_10.svg -- 39.30kb -> 33.53kb (14.69%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_offline_17/plots/latency_vs_batch.png -- 33.76kb -> 28.83kb (14.59%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 36.94kb -> 31.56kb (14.58%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_a30_experiment_10_triton_performance_online_10/plots/latency_vs_concurrency.png -- 108.99kb -> 93.10kb (14.58%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_offline_28/plots/latency_vs_batch.png -- 35.68kb -> 30.48kb (14.57%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_27_triton_performance_offline_27/plots/latency_vs_batch.png -- 35.69kb -> 30.49kb (14.56%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_offline_27/plots/latency_vs_batch.png -- 35.86kb -> 30.64kb (14.56%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_offline_28/plots/latency_vs_batch.png -- 36.95kb -> 31.58kb (14.54%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 31.81kb -> 27.18kb (14.53%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_18_triton_performance_offline_18/plots/latency_vs_batch.png -- 37.25kb -> 31.84kb (14.52%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_offline_18/plots/latency_vs_batch.png -- 33.33kb -> 28.49kb (14.52%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_17_triton_performance_offline_17/plots/latency_vs_batch.png -- 35.39kb -> 30.25kb (14.51%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 38.00kb -> 32.49kb (14.5%)
/TensorFlow2/Recommendation/DLRM/img/dlrm_histograms.svg -- 149.63kb -> 127.96kb (14.48%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 100.99kb -> 86.39kb (14.45%)
/PyTorch/Classification/GPUNet/triton/065ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 38.44kb -> 32.89kb (14.44%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_6_triton_performance_offline_6/plots/throughput_vs_batch.png -- 38.31kb -> 32.78kb (14.44%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 116.10kb -> 99.35kb (14.43%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_17_triton_performance_offline_17/plots/latency_vs_batch.png -- 37.04kb -> 31.69kb (14.43%)
/PyTorch/Recommendation/DLRM/img/training_stability_FL3_21_10.svg -- 32.63kb -> 27.92kb (14.43%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 32.98kb -> 28.23kb (14.39%)
/PyTorch/Recommendation/DLRM/img/amp_impact_fl15_21_10.svg -- 37.74kb -> 32.31kb (14.39%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_a30_experiment_6_triton_performance_offline_6/plots/throughput_vs_batch.png -- 39.55kb -> 33.86kb (14.38%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_18_triton_performance_offline_18/plots/latency_vs_batch.png -- 35.78kb -> 30.65kb (14.34%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_t4_experiment_10_triton_performance_offline_10/plots/latency_vs_batch.png -- 40.24kb -> 34.47kb (14.33%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 36.86kb -> 31.58kb (14.3%)
/PyTorch/Detection/Efficientdet/img/loss.png -- 20.39kb -> 17.48kb (14.28%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_27_triton_performance_offline_27/plots/latency_vs_batch.png -- 36.55kb -> 31.34kb (14.27%)
/PyTorch/Recommendation/DLRM/img/training_stability_FL15_21_10.svg -- 31.99kb -> 27.43kb (14.26%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 120.55kb -> 103.36kb (14.26%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 38.46kb -> 32.98kb (14.25%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 31.83kb -> 27.31kb (14.22%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_t4_experiment_6_triton_performance_offline_6/plots/throughput_vs_batch.png -- 39.43kb -> 33.83kb (14.21%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/latency_vs_batch.png -- 32.24kb -> 27.66kb (14.2%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 33.72kb -> 28.93kb (14.2%)
/PyTorch/Translation/img/6_machine-translation-figure-2.png -- 163.76kb -> 140.52kb (14.19%)
/TensorFlow/Translation/img/6_machine-translation-figure-2.png -- 163.76kb -> 140.52kb (14.19%)
/PaddlePaddle/LanguageModeling/BERT/images/bert_loss.png -- 149.60kb -> 128.40kb (14.17%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 36.47kb -> 31.32kb (14.12%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 42.85kb -> 36.83kb (14.06%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 42.85kb -> 36.83kb (14.06%)
/PyTorch/Classification/GPUNet/triton/125ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 37.48kb -> 32.22kb (14.04%)
/PyTorch/Classification/GPUNet/triton/085ms/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 36.35kb -> 31.25kb (14.02%)
/PyTorch/Classification/GPUNet/triton/05ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 36.21kb -> 31.16kb (13.95%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 34.63kb -> 29.80kb (13.95%)
/PyTorch/Segmentation/MaskRCNN/img/loss_curve.png -- 23.96kb -> 20.64kb (13.87%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_offline_18/plots/latency_vs_batch.png -- 36.78kb -> 31.68kb (13.86%)
/PyTorch/Classification/GPUNet/triton/175ms/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots/throughput_vs_latency.png -- 38.06kb -> 32.80kb (13.84%)
/PyTorch/Classification/GPUNet/triton/08ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 96.36kb -> 83.16kb (13.7%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 42.31kb -> 36.53kb (13.67%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_18_triton_performance_offline_18/plots/throughput_vs_latency.png -- 42.31kb -> 36.53kb (13.67%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 125.92kb -> 108.74kb (13.64%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 42.78kb -> 36.96kb (13.62%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_17_triton_performance_offline_17/plots/throughput_vs_latency.png -- 42.78kb -> 36.96kb (13.62%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 40.84kb -> 35.28kb (13.61%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 40.84kb -> 35.28kb (13.61%)
/TensorFlow/Segmentation/UNet_3D_Medical/images/U-Net3D_TF1_conv.png -- 104.63kb -> 90.56kb (13.45%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_a30_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 41.99kb -> 36.37kb (13.4%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_a30_experiment_27_triton_performance_offline_27/plots/throughput_vs_latency.png -- 41.99kb -> 36.37kb (13.4%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 121.51kb -> 105.26kb (13.37%)
/TensorFlow2/Recommendation/SIM/images/sim.png -- 154.10kb -> 133.51kb (13.36%)
/PyTorch/Recommendation/DLRM/triton/img/lat_vs_thr.png -- 550.26kb -> 477.27kb (13.26%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_t4_experiment_6_triton_performance_online_6/plots/latency_vs_concurrency.png -- 104.02kb -> 90.27kb (13.22%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 40.95kb -> 35.54kb (13.22%)
/Tools/PyTorch/TimeSeriesPredictionPlatform/models/tft_pyt/triton/reports/nvidia_t4_experiment_28_triton_performance_offline_28/plots/throughput_vs_latency.png -- 40.95kb -> 35.54kb (13.22%)
/PyTorch/Classification/GPUNet/triton/225ms-D/reports/nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots/latency_vs_concurrency.png -- 116.00kb -> 100.83kb (13.08%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_online_10.svg -- 95.45kb -> 83.17kb (12.87%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_online_18.svg -- 94.86kb -> 82.70kb (12.82%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_3.svg -- 94.04kb -> 82.00kb (12.8%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_online_22.svg -- 93.47kb -> 81.58kb (12.71%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_online_2.svg -- 93.58kb -> 81.68kb (12.71%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_2.svg -- 75.81kb -> 66.18kb (12.71%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_arch.png -- 196.83kb -> 171.84kb (12.7%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_online_30.svg -- 93.65kb -> 81.76kb (12.69%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_2.svg -- 93.17kb -> 81.34kb (12.69%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_7.svg -- 92.81kb -> 81.03kb (12.69%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_6.svg -- 92.58kb -> 80.88kb (12.63%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_online_6.svg -- 93.17kb -> 81.41kb (12.62%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_online_26.svg -- 92.37kb -> 80.75kb (12.58%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_online_14.svg -- 92.44kb -> 80.82kb (12.57%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 121.54kb -> 106.28kb (12.56%)
/TensorFlow/Segmentation/UNet_Industrial/images/dagm2007.png -- 596.90kb -> 521.94kb (12.56%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_6.svg -- 74.43kb -> 65.09kb (12.56%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_4.svg -- 74.79kb -> 65.40kb (12.55%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_8.svg -- 76.69kb -> 67.10kb (12.5%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_8.svg -- 91.06kb -> 79.68kb (12.5%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_7.svg -- 74.20kb -> 64.94kb (12.48%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_5.svg -- 90.85kb -> 79.54kb (12.45%)
/PyTorch/Recommendation/NCF/img/layout_example.png -- 45.84kb -> 40.14kb (12.44%)
/TensorFlow2/Recommendation/SIM/images/layout_example.png -- 45.84kb -> 40.14kb (12.44%)
/TensorFlow2/Recommendation/WideAndDeep/img/layout_example.png -- 45.84kb -> 40.14kb (12.44%)
/TensorFlow2/Recommendation/DLRM/img/layout_example.png -- 45.84kb -> 40.14kb (12.44%)
/PyTorch/Recommendation/DLRM/img/layout_example.png -- 45.84kb -> 40.14kb (12.44%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_1.svg -- 76.24kb -> 66.76kb (12.43%)
/PyTorch/SpeechSynthesis/FastPitch/img/loss_fp32.png -- 32.30kb -> 28.29kb (12.42%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_1.svg -- 90.08kb -> 78.91kb (12.39%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_5.svg -- 76.01kb -> 66.59kb (12.39%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_online_4.svg -- 90.03kb -> 78.88kb (12.39%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_performance_online_3.svg -- 75.16kb -> 65.88kb (12.34%)
/TensorFlow2/Recommendation/WideAndDeep/triton/reports/nvidia_t4_experiment_10_triton_performance_online_10/plots/latency_vs_concurrency.png -- 108.54kb -> 95.17kb (12.32%)
/TensorFlow/Recommendation/NCF/img/dgx1v16_curve.png -- 41.65kb -> 36.54kb (12.27%)
/TensorFlow/Recommendation/NCF/img/dgx1v_32_curve.png -- 41.58kb -> 36.57kb (12.05%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_7l.svg -- 33.54kb -> 29.50kb (12.03%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 126.84kb -> 111.70kb (11.93%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_27_triton_performance_online_27/plots/latency_vs_concurrency.png -- 131.12kb -> 115.53kb (11.89%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_13l.svg -- 32.96kb -> 29.05kb (11.86%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_3l.svg -- 32.37kb -> 28.58kb (11.71%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_17_triton_performance_online_17/plots/latency_vs_concurrency.png -- 133.36kb -> 117.77kb (11.69%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_3r.svg -- 30.95kb -> 27.34kb (11.67%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_5l.svg -- 33.35kb -> 29.48kb (11.61%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_11r.svg -- 32.03kb -> 28.33kb (11.56%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_11l.svg -- 31.79kb -> 28.12kb (11.56%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_15l.svg -- 32.98kb -> 29.17kb (11.55%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_1r.svg -- 31.90kb -> 28.25kb (11.44%)
/PyTorch/Recommendation/NCF/img/dgx2_curve.png -- 39.15kb -> 34.70kb (11.37%)
/TensorFlow/Recommendation/NCF/img/dgx2_curve.png -- 39.15kb -> 34.70kb (11.37%)
/PyTorch/Forecasting/TFT/triton/reports/nvidia_t4_experiment_18_triton_performance_online_18/plots/latency_vs_concurrency.png -- 136.37kb -> 120.89kb (11.36%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_13r.svg -- 29.92kb -> 26.52kb (11.35%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_A10080GB_right.svg -- 35.49kb -> 31.48kb (11.31%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_9l.svg -- 32.19kb -> 28.56kb (11.28%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_1l.svg -- 32.18kb -> 28.55kb (11.28%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_4l.svg -- 27.99kb -> 24.84kb (11.27%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_7l.svg -- 27.99kb -> 24.84kb (11.27%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_2l.svg -- 27.99kb -> 24.84kb (11.27%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_3l.svg -- 27.99kb -> 24.84kb (11.27%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_1l.svg -- 27.99kb -> 24.84kb (11.26%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_8l.svg -- 27.99kb -> 24.84kb (11.26%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_6l.svg -- 27.99kb -> 24.84kb (11.26%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_5l.svg -- 27.99kb -> 24.84kb (11.26%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_TeslaV10032GB_right.svg -- 34.70kb -> 30.81kb (11.23%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_A40_right.svg -- 34.70kb -> 30.81kb (11.23%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_7r.svg -- 29.40kb -> 26.11kb (11.18%)
/PyTorch/SpeechSynthesis/FastPitch/img/loss_fp16.png -- 32.05kb -> 28.48kb (11.14%)
/TensorFlow/Classification/ConvNets/triton/plots/graph_performance_offline_15r.svg -- 30.38kb -> 27.01kb (11.09%)
/PyTorch/Translation/Transformer/bleu_relationship.png -- 10.21kb -> 9.08kb (11.09%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_A40_left.svg -- 37.38kb -> 33.24kb (11.07%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_2r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_6r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_8r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_TeslaT4_right.svg -- 34.97kb -> 31.12kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_1r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_3r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_7r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_4r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/SpeechSynthesis/FastPitch/triton/plots/graph_performance_offline_5r.svg -- 29.71kb -> 26.44kb (11%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_5r.svg -- 30.29kb -> 26.97kb (10.99%)
/PyTorch/Classification/ConvNets/triton/resnet50/plots/graph_performance_offline_9r.svg -- 29.02kb -> 25.83kb (10.97%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_TeslaV10032GB_left.svg -- 36.93kb -> 32.89kb (10.95%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_A10080GB_left.svg -- 36.53kb -> 32.57kb (10.83%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/training_loss_base.png -- 254.14kb -> 226.64kb (10.82%)
/PyTorch/Segmentation/nnUNet/triton/plots/graph_TeslaT4_left.svg -- 36.96kb -> 33.03kb (10.65%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_fp32_loss.png -- 29.15kb -> 26.11kb (10.45%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_amp_loss.png -- 30.52kb -> 27.33kb (10.44%)
/PyTorch/Translation/img/6_machine-translation-figure-3.png -- 171.55kb -> 154.73kb (9.8%)
/TensorFlow/Translation/img/6_machine-translation-figure-3.png -- 171.55kb -> 154.73kb (9.8%)
/TensorFlow/Translation/img/6_machine-translation-figure-1.png -- 17.00kb -> 15.77kb (7.26%)
/PyTorch/Translation/img/6_machine-translation-figure-1.png -- 17.00kb -> 15.77kb (7.26%)
/PyTorch/SpeechSynthesis/FastPitch/img/pitch.png -- 23.55kb -> 21.91kb (6.97%)
/PyTorch/SpeechRecognition/Jasper/images/static_fp16_7s.png -- 76.90kb -> 71.61kb (6.88%)
/PyTorch/SpeechRecognition/Jasper/images/static_fp16_2s.png -- 77.23kb -> 72.10kb (6.65%)
/TensorFlow2/Recommendation/SIM/images/auc_amp_impact_xla.png -- 57.20kb -> 53.52kb (6.43%)
/TensorFlow/LanguageModeling/BERT/data/images/bert_triton_dynamic_batching_a100.png -- 26.09kb -> 24.58kb (5.81%)
/PyTorch/SpeechRecognition/Jasper/images/tensorrt_16.7s.png -- 111.73kb -> 105.36kb (5.7%)
/PyTorch/SpeechRecognition/Jasper/images/tensorrt_7s.png -- 112.51kb -> 106.10kb (5.69%)
/PyTorch/Recommendation/DLRM/img/df_diagram.png -- 98.29kb -> 92.80kb (5.59%)
/PyTorch/Recommendation/NCF/img/df_diagram.png -- 98.29kb -> 92.80kb (5.59%)
/TensorFlow2/Recommendation/SIM/images/df_diagram.png -- 98.29kb -> 92.80kb (5.59%)
/TensorFlow2/Recommendation/SIM/images/sim_roc.png -- 81.19kb -> 76.72kb (5.5%)
/TensorFlow2/Recommendation/SIM/images/auc_amp_impact_no_xla.png -- 52.18kb -> 49.45kb (5.23%)
/TensorFlow/Translation/GNMT/img/bleu_score.png -- 19.62kb -> 18.66kb (4.89%)
/TensorFlow2/Recommendation/SIM/images/stability_no_xla.png -- 47.53kb -> 45.33kb (4.65%)
/PyTorch/Detection/SSD/img/training_loss.png -- 23.55kb -> 22.47kb (4.6%)
/TensorFlow/Classification/ConvNets/resnext101-32x4d/imgs/ResNeXtArch.png -- 78.06kb -> 74.62kb (4.4%)
/PyTorch/Classification/ConvNets/resnext101-32x4d/img/ResNeXtArch.png -- 78.06kb -> 74.62kb (4.4%)
/PyTorch/Recommendation/DLRM/triton/img/dyn_batch_concurrency.png -- 27.34kb -> 26.16kb (4.31%)
/TensorFlow/Segmentation/VNet/images/infer_p_vs_v.png -- 13.64kb -> 13.09kb (3.97%)
/TensorFlow2/Recommendation/SIM/images/stability_xla.png -- 46.23kb -> 44.40kb (3.96%)
/TensorFlow2/Detection/Efficientdet/testdata/img1-d1.jpg -- 103.24kb -> 99.17kb (3.94%)
/PyTorch/SpeechRecognition/img/8_speech-to-text-figure-2.png -- 47.03kb -> 45.25kb (3.79%)
/TensorFlow/LanguageModeling/Transformer-XL/tf/img/training_loss_base.png -- 16.86kb -> 16.28kb (3.46%)
/PyTorch/SpeechRecognition/Jasper/images/static_fp16_16.7s.png -- 80.60kb -> 77.81kb (3.46%)
/PaddlePaddle/Classification/RN50v1.5/img/loss.png -- 57.62kb -> 55.68kb (3.37%)
/PaddlePaddle/Classification/RN50v1.5/img/top5.png -- 60.82kb -> 58.78kb (3.36%)
/PaddlePaddle/Classification/RN50v1.5/img/top1.png -- 64.25kb -> 62.12kb (3.32%)
/PyTorch/Segmentation/img/3_image-segmentation-figure-4.png -- 43.21kb -> 41.80kb (3.24%)
/TensorFlow/Segmentation/img/3_image-segmentation-figure-4.png -- 43.21kb -> 41.80kb (3.24%)
/TensorFlow2/Segmentation/img/3_image-segmentation-figure-4.png -- 43.21kb -> 41.80kb (3.24%)
/TensorFlow2/Segmentation/img/3_image-segmentation-figure-3.png -- 373.66kb -> 362.00kb (3.12%)
/PyTorch/Segmentation/img/3_image-segmentation-figure-3.png -- 373.66kb -> 362.00kb (3.12%)
/TensorFlow/Segmentation/img/3_image-segmentation-figure-3.png -- 373.66kb -> 362.00kb (3.12%)
/PyTorch/Classification/ConvNets/triton/resnext101-32x4d/Latency-vs-Throughput-TensorRT.png -- 17.97kb -> 17.54kb (2.44%)
/PyTorch/LanguageModeling/BERT/images/model.png -- 56.50kb -> 55.15kb (2.39%)
/PaddlePaddle/LanguageModeling/BERT/images/model.png -- 56.50kb -> 55.15kb (2.39%)
/TensorFlow/Classification/ConvNets/resnet50v1.5/imgs/train_loss.png -- 31.61kb -> 30.89kb (2.27%)
/TensorFlow/LanguageModeling/BERT/data/images/bert_trt_throughput_vs_latency.png -- 29.61kb -> 28.96kb (2.21%)
/TensorFlow/Detection/SSD/img/training_loss.png -- 16.71kb -> 16.36kb (2.08%)
/TensorFlow/Classification/ConvNets/se-resnext101-32x4d/imgs/train_loss.png -- 35.06kb -> 34.39kb (1.91%)
/PyTorch/Segmentation/img/3_image-segmentation-figure-5.png -- 413.51kb -> 405.93kb (1.83%)
/TensorFlow/Segmentation/img/3_image-segmentation-figure-5.png -- 413.51kb -> 405.93kb (1.83%)
/TensorFlow2/Segmentation/img/3_image-segmentation-figure-5.png -- 413.51kb -> 405.93kb (1.83%)
/PyTorch/SpeechRecognition/QuartzNet/img/model.png -- 117.35kb -> 115.42kb (1.65%)
/TensorFlow/Classification/ConvNets/resnext101-32x4d/imgs/train_loss.png -- 34.87kb -> 34.32kb (1.58%)
/TensorFlow/Segmentation/VNet/images/8gpu_p_vs_v.png -- 14.73kb -> 14.50kb (1.56%)
/TensorFlow/Recommendation/WideAndDeep/img/lc20.06.png -- 25.08kb -> 24.73kb (1.42%)
/TensorFlow/Segmentation/VNet/images/1gpu_p_vs_v.png -- 13.89kb -> 13.70kb (1.39%)
/TensorFlow2/Recommendation/WideAndDeep/img/model.svg -- 30.63kb -> 30.21kb (1.36%)
/PyTorch/SpeechSynthesis/FastPitch/img/loss.png -- 122.79kb -> 121.26kb (1.25%)
/TensorFlow2/LanguageModeling/ELECTRA/images/total_loss.svg -- 140.75kb -> 139.03kb (1.23%)
/TensorFlow2/Detection/Efficientdet/testdata/img1.jpg -- 126.82kb -> 125.34kb (1.16%)
/PyTorch/Classification/ConvNets/triton/se-resnext101-32x4d/Performance-analysis-TensorRT-FP32.png -- 21.02kb -> 20.79kb (1.11%)
/PyTorch/Segmentation/MaskRCNN/pytorch/demo/demo_e2e_mask_rcnn_X_101_32x8d_FPN_1x.png -- 894.07kb -> 886.23kb (0.88%)
/PyTorch/Segmentation/MaskRCNN/pytorch/demo/demo_e2e_mask_rcnn_R_50_FPN_1x.png -- 898.65kb -> 890.92kb (0.86%)
/PyTorch/Segmentation/img/3_image-segmentation-figure-2.png -- 86.92kb -> 86.32kb (0.68%)
/TensorFlow2/Segmentation/img/3_image-segmentation-figure-2.png -- 86.92kb -> 86.32kb (0.68%)
/TensorFlow/Segmentation/img/3_image-segmentation-figure-2.png -- 86.92kb -> 86.32kb (0.68%)
/PyTorch/Detection/img/2_object-detection-figure-1.png -- 592.86kb -> 588.88kb (0.67%)
/TensorFlow/Detection/img/2_object-detection-figure-1.png -- 592.86kb -> 588.88kb (0.67%)
/TensorFlow2/Detection/img/2_object-detection-figure-1.png -- 592.86kb -> 588.88kb (0.67%)
/TensorFlow2/Recommendation/DLRM/img/singlegpu_architecture.svg -- 131.00kb -> 130.54kb (0.35%)
/PyTorch/Classification/ConvNets/triton/se-resnext101-32x4d/Latency-vs-Throughput-TensorRT.png -- 17.55kb -> 17.51kb (0.24%)
/TensorFlow2/Recommendation/DLRM/img/columnwise_split.svg -- 489.32kb -> 488.18kb (0.23%)
/TensorFlow2/Recommendation/DLRM/img/hybrid_parallel.svg -- 507.90kb -> 506.84kb (0.21%)
/PyTorch/SpeechSynthesis/img/9_text-to-speech-figure-2.png -- 162.89kb -> 162.73kb (0.1%)
/PyTorch/Translation/Transformer/average_valid_loss.png -- 18.42kb -> 18.40kb (0.09%)

Signed-off-by: ImgBotApp <ImgBotHelp@gmail.com>