maskrcnn & detr model logs

FlagOpen · Mar 4, 2024 · bcea674 · bcea674
1 parent 97f6883
commit bcea674
Show file tree

Hide file tree

Showing 7 changed files with 12 additions and 11 deletions.
diff --git a/training/metax/detr-pytorch/config/requirements.txt b/training/metax/detr-pytorch/config/requirements.txt
@@ -1,5 +1,3 @@
-/root/.cache/torch/hub/checkpoints/torchvision-0.15.1+mc2.19.0.2-cp38-cp38-linux_x86_64.whl
-/root/.cache/torch/hub/checkpoints/torch-2.0.0+gite544b36-cp38-cp38-linux_x86_64.whl
 cython
 git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI&egg=pycocotools
 submitit

diff --git a/training/metax/mask_rcnn-pytorch/README.md b/training/metax/mask_rcnn-pytorch/README.md
@@ -45,6 +45,6 @@
 
 | 配置                | precision | fix_hp         | e2e_time | p_whole | p_train | p_core | mAP   | mem       |
 | ------------------- | --------- | -------------- | -------- | ------- | ------- | ------ | ----- | --------- |
-| MXC500 单机8卡（1x8） | fp32      | bs=8,lr=0.0001 |          |         |         |        |0.382 && 0.343| 39.6/64.0 |
-| MXC500 单机单卡（1x1）| fp32      | /              |           |         |         |         |        | 30.5/64.0  |
-| MXC500 两机16卡（2x8） | fp32      | /              |            |         |         |         |        | 31.5/64.0  |
+| MXC500 单机8卡（1x8） | fp32      | bs=8,lr=0.0001 |          |         |         |        |0.382 && 0.343| 37.1/64.0 |
+| MXC500 单机单卡（1x1）| fp32      | /              |           |         |         |         |        | 36.2/64.0  |
+| MXC500 两机16卡（2x8） | fp32      | /              |            |         |         |         |        | 37.1/64.0  |
diff --git a/training/metax/mask_rcnn-pytorch/config/config_C500x1x1.py b/training/metax/mask_rcnn-pytorch/config/config_C500x1x1.py
@@ -1,4 +1,5 @@
 vendor: str = "metax"
 train_batch_size = 16
 eval_batch_size = 16
-lr = 0.16
+lr = 0.16
+max_epoch: int = 1
diff --git a/training/metax/mask_rcnn-pytorch/config/config_C500x1x8.py b/training/metax/mask_rcnn-pytorch/config/config_C500x1x8.py
@@ -1,3 +1,4 @@
 vendor: str = "metax"
-train_batch_size = 2
-eval_batch_size = 2
+train_batch_size = 16
+eval_batch_size = 16
+lr = 0.16
diff --git a/training/metax/mask_rcnn-pytorch/config/config_C500x2x8.py b/training/metax/mask_rcnn-pytorch/config/config_C500x2x8.py
@@ -1,4 +1,5 @@
 vendor: str = "metax"
 train_batch_size = 16
 eval_batch_size = 16
-lr = 0.08
+lr = 0.016
+max_epoch: int = 4
diff --git a/training/metax/mask_rcnn-pytorch/config/requirements.txt b/training/metax/mask_rcnn-pytorch/config/requirements.txt
@@ -1,5 +1,3 @@
-/root/.cache/torch/hub/checkpoints/torchvision-0.15.1+mc2.19.0.2-cp38-cp38-linux_x86_64.whl
-/root/.cache/torch/hub/checkpoints/torch-2.0.0+gite544b36-cp38-cp38-linux_x86_64.whl
 pycocotools
 numpy
 tqdm

diff --git a/training/run_benchmarks/config/test_conf.py b/training/run_benchmarks/config/test_conf.py
@@ -157,5 +157,7 @@
     # "bert_hf:pytorch_2.0:C500:1:8:1": "/raid/dataset/bert_hf_train",
     # "glm:pytorch_2.0:C500:1:8:1": "/raid/home_datasets_ckpt/glm/train/",
     # "mobilenetv2:pytorch_2.0:C500:1:8:1": "/raid/dataset/ImageNet_1k_2012/",
+    # "mask_rcnn:pytorch_2.0:C500:1:8:1": "/raid/dataset/coco2017/",
+    # "detr:pytorch_2.0:C500:1:8:1": "/raid/dataset/coco2017/",
 }