*Total -- 8,855.05kb -> 7,174.65kb (18.98%)

/TensorFlow/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%)
/PyTorch/Classification/ConvNets/se-resnext101-32x4d/img/SEArch.png -- 76.28kb -> 29.02kb (61.95%)
/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%)
/TensorFlow2/Segmentation/UNet_Medical/images/score_histogram.png -- 10.79kb -> 5.13kb (52.44%)
/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/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%)
/PyTorch/Classification/ConvNets/img/LATvsTHR.png -- 61.13kb -> 37.66kb (38.39%)
/PyTorch/Translation/Transformer/BLEU.png -- 50.02kb -> 32.07kb (35.89%)
/TensorFlow/LanguageModeling/BERT/data/images/bert_pipeline.png -- 207.54kb -> 133.29kb (35.77%)
/TensorFlow/Segmentation/UNet_Industrial/images/unet.png -- 668.53kb -> 447.82kb (33.01%)
/PyTorch/Translation/GNMT/img/training_accuracy.png -- 114.66kb -> 81.28kb (29.11%)
/TensorFlow/Translation/GNMT/img/diagram.png -- 347.25kb -> 248.60kb (28.41%)
/PyTorch/Translation/GNMT/img/diagram.png -- 347.25kb -> 248.60kb (28.41%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_arch.png -- 88.12kb -> 65.50kb (25.68%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/model.png -- 694.46kb -> 519.75kb (25.16%)
/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%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_fp16_loss.png -- 28.16kb -> 21.59kb (23.34%)
/PyTorch/Segmentation/MaskRCNN/img/accuracy_curve.png -- 54.72kb -> 42.27kb (22.75%)
/PyTorch/SpeechSynthesis/Tacotron2/img/waveglow_fp32_loss.png -- 50.44kb -> 39.14kb (22.39%)
/TensorFlow/Recommendation/VAE-CF/images/autoencoder.png -- 80.94kb -> 63.05kb (22.11%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/training_loss_large_multinode.png -- 49.23kb -> 39.47kb (19.82%)
/TensorFlow/Segmentation/VNet/images/vnet.png -- 166.44kb -> 134.18kb (19.38%)
/PyTorch/Translation/Transformer/transformer.png -- 191.70kb -> 154.77kb (19.27%)
/PyTorch/SpeechRecognition/Jasper/images/jasper_dense_residual.png -- 246.20kb -> 201.10kb (18.32%)
/TensorFlow/Recommendation/NCF/img/hr_histogram.png -- 27.49kb -> 22.52kb (18.1%)
/PyTorch/Recommendation/NCF/img/ncf_diagram.png -- 174.41kb -> 144.95kb (16.89%)
/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/LanguageModeling/Transformer-XL/pytorch/img/training_loss_large.png -- 76.38kb -> 64.13kb (16.04%)
/PyTorch/Translation/GNMT/img/training_loss.png -- 295.10kb -> 251.62kb (14.74%)
/PyTorch/Segmentation/MaskRCNN/img/loss_curve.png -- 40.23kb -> 34.63kb (13.93%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_arch.png -- 196.83kb -> 171.84kb (12.7%)
/TensorFlow/Segmentation/UNet_Industrial/images/dagm2007.png -- 596.90kb -> 521.94kb (12.56%)
/TensorFlow/Recommendation/NCF/img/dgx1v16_curve.png -- 41.65kb -> 36.54kb (12.27%)
/PyTorch/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/Recommendation/NCF/img/dgx2_curve.png -- 39.15kb -> 34.70kb (11.37%)
/PyTorch/Recommendation/NCF/img/dgx2_curve.png -- 39.15kb -> 34.70kb (11.37%)
/PyTorch/LanguageModeling/Transformer-XL/pytorch/img/training_loss_base.png -- 254.14kb -> 226.64kb (10.82%)
/PyTorch/SpeechSynthesis/Tacotron2/img/tacotron2_amp_loss.png -- 30.52kb -> 27.33kb (10.44%)
/PyTorch/Recommendation/NCF/img/hr_histogram.png -- 29.36kb -> 27.51kb (6.29%)
/PyTorch/Recommendation/NCF/img/dgx1v_32_curve.png -- 40.93kb -> 38.79kb (5.23%)
/PyTorch/Classification/ConvNets/resnext101-32x4d/img/ResNeXtArch.png -- 78.06kb -> 74.24kb (4.9%)
/PyTorch/LanguageModeling/BERT/images/model.png -- 56.50kb -> 55.15kb (2.39%)
/PyTorch/SpeechRecognition/Jasper/images/trtis_dynamic_batching.png -- 19.97kb -> 19.57kb (2%)
/TensorFlow/Segmentation/VNet/images/8gpu_p_vs_v.png -- 14.73kb -> 14.50kb (1.56%)
/TensorFlow/Segmentation/VNet/images/1gpu_p_vs_v.png -- 13.89kb -> 13.70kb (1.39%)
/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%)
/TensorFlow/LanguageModeling/BERT/data/images/trtis_bs_8.png -- 16.95kb -> 16.83kb (0.7%)
/TensorFlow/LanguageModeling/BERT/data/images/trtis_dynamic.png -- 20.43kb -> 20.34kb (0.42%)
/PyTorch/SpeechRecognition/Jasper/images/trtis_throughput_latency_summary.png -- 32.47kb -> 32.36kb (0.33%)
/PyTorch/SpeechRecognition/Jasper/images/trtis_static_batching_bs8.png -- 20.07kb -> 20.01kb (0.28%)
/PyTorch/SpeechRecognition/Jasper/images/trtis_static_batching_bs1.png -- 20.15kb -> 20.11kb (0.2%)

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