[EfficientNet/TF2] Fix inference numbers and calculations
Co-authored-by: Subhankar Ghosh <subhankarg@nvidia.com>
This commit is contained in:
Subhankar Ghosh
GitHub
parent
da18e57a91
commit
ec2bef8444
|
|
@ -577,20 +577,20 @@ FP16 Inference Latency
|
|||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) |Latency 95% (ms) |Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 224x224 | 111 | 8.97 | 8.88 | 8.92 | 8.96 |
|
||||
| 2 | 224x224 | 233 | 4.28 | 4.22 | 4.25 | 4.27 |
|
||||
| 4 | 224x224 | 432 | 2.31 | 2.28 | 2.29 | 2.30 |
|
||||
| 8 | 224x224 | 771 | 1.29 | 1.27 | 1.28 | 1.28 |
|
||||
| 1024 | 224x224 | 10269 | 0.10 | 0.10 | 0.10 | 0.10 |
|
||||
| 2 | 224x224 | 233 | 8.56 | 8.44 | 8.5 | 8.54 |
|
||||
| 4 | 224x224 | 432 | 9.24 | 9.12 | 9.16 | 9.2 |
|
||||
| 8 | 224x224 | 771 | 10.32 | 10.16 | 10.24 | 10.24 |
|
||||
| 1024 | 224x224 | 10269 | 102.4 | 102.4 | 102.4 | 102.4 |
|
||||
|
||||
TF32 Inference Latency
|
||||
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) | Latency 95% (ms) | Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 224x224 | 101 | 9.87 | 9.78 | 9.82 | 9.86 |
|
||||
| 2 | 224x224 | 204 | 4.89 | 4.83 | 4.85 | 4.88 |
|
||||
| 4 | 224x224 | 381 | 2.62 | 2.59 | 2.60 | 2.61 |
|
||||
| 8 | 224x224 | 584 | 1.71 | 1.69 | 1.70 | 1.71 |
|
||||
| 512 | 224x224 | 5480 | 0.18 | 0.18 | 0.18 | 0.18 |
|
||||
| 2 | 224x224 | 204 | 9.78 | 9.66 | 9.7 | 9.76 |
|
||||
| 4 | 224x224 | 381 | 10.48 | 10.36 | 10.4 | 10.44 |
|
||||
| 8 | 224x224 | 584 | 13.68 | 13.52 | 13.6 | 13.68 |
|
||||
| 512 | 224x224 | 5480 | 92.16 | 92.16 | 92.16 | 92.16 |
|
||||
|
||||
To achieve these same results, follow the steps in the [Quick Start Guide](#quick-start-guide).
|
||||
|
||||
|
|
@ -602,23 +602,22 @@ Our results were obtained by running the `inference-script-name.sh` inferencing
|
|||
|
||||
FP16 Inference Latency
|
||||
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg | Latency 90% |Latency 95% |Latency 99% |
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) |Latency 95% (ms) |Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 224x224 | 98.8 | 10.12 | 10.03 | 10.06 | 10.10 |
|
||||
| 2 | 224x224 | 199.3 | 5.01 | 4.95 | 4.97 | 5.00 |
|
||||
| 4 | 224x224 | 382.5 | 2.61 | 2.57 | 2.59 | 2.60 |
|
||||
| 8 | 224x224 | 681.2 | 1.46 | 1.44 | 1.45 | 1.46 |
|
||||
| 256 | 224x224 | 5271 | 0.19 | 0.18 | 0.18 | 0.19 |
|
||||
|
||||
| 2 | 224x224 | 199.3 | 10.02 | 9.9 | 9.94 | 10.0 |
|
||||
| 4 | 224x224 | 382.5 | 10.44 | 10.28 | 10.36 | 10.4 |
|
||||
| 8 | 224x224 | 681.2 | 11.68 | 11.52 | 11.6 | 11.68 |
|
||||
| 256 | 224x224 | 5271 | 48.64 | 46.08 | 46.08 | 48.64 |
|
||||
FP32 Inference Latency
|
||||
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg | Latency 90% | Latency 95% | Latency 99% |
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) | Latency 95% (ms) | Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 224x224 | 68.39 | 14.62 | 14.45 | 14.51 | 14.56 |
|
||||
| 2 | 224x224 | 125.62 | 7.96 | 7.89 | 7.91 | 7.94 |
|
||||
| 4 | 224x224 | 216.41 | 4.62 | 4.56 | 4.60 | 4.61 |
|
||||
| 8 | 224x224 | 401.60 | 2.49 | 2.45 | 2.47 | 2.48 |
|
||||
| 128 | 224x224 | 2713 | 0.37 | 0.36 | 0.36 | 0.37 |
|
||||
| 2 | 224x224 | 125.62 | 15.92 | 15.78 | 15.82 | 15.82 |
|
||||
| 4 | 224x224 | 216.41 | 18.48 | 18.24 | 18.4 | 18.44 |
|
||||
| 8 | 224x224 | 401.60 | 19.92 | 19.6 | 19.76 | 19.84 |
|
||||
| 128 | 224x224 | 2713 | 47.36 | 46.08 | 46.08 | 47.36 |
|
||||
|
||||
To achieve these same results, follow the steps in the [Quick Start Guide](#quick-start-guide).
|
||||
|
||||
|
|
@ -634,19 +633,19 @@ FP16 Inference Latency
|
|||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) |Latency 95% (ms) |Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 380x380 | 57.54 | 17.37 | 17.24 | 17.30 | 17.35 |
|
||||
| 2 | 380x380 | 112.06 | 8.92 | 8.85 | 8.88 | 8.91 |
|
||||
| 4 | 380x380 | 219.71 | 4.55 | 4.52 | 4.53 | 4.54 |
|
||||
| 8 | 380x380 | 383.39 | 2.60 | 2.58 | 2.59 | 2.60 |
|
||||
| 128 | 380x380 | 1470 | 0.68 | 0.67 | 0.67 | 0.68 |
|
||||
| 2 | 380x380 | 112.06 | 17.84 | 17.7 | 17.76 | 17.82 |
|
||||
| 4 | 380x380 | 219.71 | 18.2 | 18.08 | 18.12 | 18.16 |
|
||||
| 8 | 380x380 | 383.39 | 20.8 | 20.64 | 20.72 | 20.8 |
|
||||
| 128 | 380x380 | 1470 | 87.04 | 85.76 | 85.76 | 87.04 |
|
||||
|
||||
TF32 Inference Latency
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) | Latency 95% (ms) | Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 380x380 | 52.68 | 18.98 | 18.86 | 18.91 | 18.96 |
|
||||
| 2 | 380x380 | 95.32 | 10.49 | 10.42 | 10.45 | 10.48 |
|
||||
| 4 | 380x380 | 182.14 | 5.49 | 5.46 | 5.47 | 5.48 |
|
||||
| 8 | 380x380 | 325.72 | 3.07 | 3.05 | 3.05 | 3.06 |
|
||||
| 64 | 380x380 | 694 | 1.43 | 1.42 | 1.43 | 1.43 |
|
||||
| 2 | 380x380 | 95.32 | 20.98 | 20.84 | 20.9 | 20.96 |
|
||||
| 4 | 380x380 | 182.14 | 21.96 | 21.84 | 21.88 | 21.92 |
|
||||
| 8 | 380x380 | 325.72 | 24.56 | 24.4 | 24.4 | 24.48 |
|
||||
| 64 | 380x380 | 694 | 91.52 | 90.88 | 91.52 | 91.52 |
|
||||
|
||||
To achieve these same results, follow the steps in the [Quick Start Guide](#quick-start-guide).
|
||||
|
||||
|
|
@ -658,24 +657,24 @@ Our results were obtained by running the `inference-script-name.sh` inferencing
|
|||
|
||||
FP16 Inference Latency
|
||||
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg | Latency 90% | Latency 95% | Latency 99% |
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) | Latency 95% (ms) | Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 380x380 | 54.27 | 18.35 | 18.20 | 18.25 | 18.32 |
|
||||
| 2 | 380x380 | 104.27 | 9.59 | 9.51 | 9.54 | 9.58 |
|
||||
| 4 | 380x380 | 182.61 | 5.47 | 5.41 | 5.43 | 5.46 |
|
||||
| 8 | 380x380 | 234.06 | 4.27 | 4.24 | 4.25 | 4.26 |
|
||||
| 64 | 380x380 | 782.47 | 1.28 | 1.25 | 1.26 | 1.27 |
|
||||
| 2 | 380x380 | 104.27 | 19.18 | 19.02 | 19.08 | 19.16 |
|
||||
| 4 | 380x380 | 182.61 | 21.88 | 21.64 | 21.72 | 21.84 |
|
||||
| 8 | 380x380 | 234.06 | 34.16 | 33.92 | 34.0 | 34.08 |
|
||||
| 64 | 380x380 | 782.47 | 81.92 | 80.0 | 80.64 | 81.28 |
|
||||
|
||||
|
||||
FP32 Inference Latency
|
||||
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg | Latency 90% |Latency 95% |Latency 99% |
|
||||
| Batch size | Resolution | Throughput Avg | Latency Avg (ms) | Latency 90% (ms) |Latency 95% (ms) |Latency 99% (ms) |
|
||||
|------------|-----------------|-----|-----|-----|-----|-----|
|
||||
| 1 | 380x380 | 30.48 | 32.80 | 32.86 | 31.83 | 32.60 |
|
||||
| 2 | 380x380 | 58.59 | 17.06 | 15.96 | 16.51 | 16.95 |
|
||||
| 4 | 380x380 | 111.35 | 8.98 | 8.75 | 8.78 | 8.92 |
|
||||
| 8 | 380x380 | 199.00 | 5.03 | 4.84 | 4.88 | 5.00 |
|
||||
| 32 | 380x380 | 307.04 | 3.25 | 3.25 | 3.25 | 3.25 |
|
||||
| 2 | 380x380 | 58.59 | 34.12 | 31.92 | 33.02 | 33.9 |
|
||||
| 4 | 380x380 | 111.35 | 35.92 | 35.0 | 35.12 | 35.68 |
|
||||
| 8 | 380x380 | 199.00 | 40.24 | 38.72 | 39.04 | 40.0 |
|
||||
| 32 | 380x380 | 307.04 | 104.0 | 104.0 | 104.0 | 104.0 |
|
||||
|
||||
To achieve these same results, follow the steps in the [Quick Start Guide](#quick-start-guide).
|
||||
|
||||
|
|
|
|||
|
|
@ -219,12 +219,14 @@ def build_stats(history, validation_output, train_callbacks, eval_callback, logg
|
|||
stats['avg_time_per_exp_eval'] = 1000./stats['avg_exp_per_second_eval']
|
||||
batch_time = eval_callback.batch_time
|
||||
batch_time.sort()
|
||||
latency_pct_per_batch = sum( batch_time[:-1] ) / int( len(batch_time) - 1 )
|
||||
stats['latency_pct'] = 1000.0 * latency_pct_per_batch
|
||||
latency_90pct_per_batch = sum( batch_time[:int( 0.9 * len(batch_time) )] ) / int( 0.9 * len(batch_time) )
|
||||
stats['latency_90pct'] = 1000.0 * latency_90pct_per_batch / eval_callback.batch_size
|
||||
stats['latency_90pct'] = 1000.0 * latency_90pct_per_batch
|
||||
latency_95pct_per_batch = sum( batch_time[:int( 0.95 * len(batch_time) )] ) / int( 0.95 * len(batch_time) )
|
||||
stats['latency_95pct'] = 1000.0 * latency_95pct_per_batch / eval_callback.batch_size
|
||||
stats['latency_95pct'] = 1000.0 * latency_95pct_per_batch
|
||||
latency_99pct_per_batch = sum( batch_time[:int( 0.99 * len(batch_time) )] ) / int( 0.99 * len(batch_time) )
|
||||
stats['latency_99pct'] = 1000.0 * latency_99pct_per_batch / eval_callback.batch_size
|
||||
stats['latency_99pct'] = 1000.0 * latency_99pct_per_batch
|
||||
|
||||
if not hvd_utils.is_using_hvd() or hvd.rank() == 0:
|
||||
logger.log(step=(), data=stats)
|
||||
|
|
|
|||
Loading…
Reference in a new issue