1. The **gpus** indicates the number of gpu (32G V100) we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8x4 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
3. The values in columns named after "reference" are the results got by training on the original repo, using the same model settings.
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
@@ -33,7 +33,7 @@ The [AverageMeter issue](https://github.com/deepcs233/TIN/issues/4) will lead to
2. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
3. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
3. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
4. The values in columns named after "reference" are the results got by training on the original repo, using the same model settings.
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
3. The values in columns named after "reference" are the results got by training on the original repo, using the same model settings.
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
3. The values in columns named after "reference" are the results got by training on the original repo, using the same model settings.
@@ -519,7 +519,7 @@ average iter time: 0.9330 s/iter
We provide a script adapted from [flops-counter.pytorch](https://github.com/sovrasov/flops-counter.pytorch) to compute the FLOPs and params of a given model.
