diff --git a/GETTING_STARTED.md b/GETTING_STARTED.md index eeb3563d..a80ba9cc 100644 --- a/GETTING_STARTED.md +++ b/GETTING_STARTED.md @@ -29,7 +29,7 @@ to understand their behavior. Some common arguments are: * Prepare your dataset in YOLO format. If trained with COCO (YOLO format), prepare it from [yolov5](https://github.com/ultralytics/yolov5) or the darknet.
- + View More ``` coco/ {train,val}2017.txt diff --git a/README.md b/README.md index 3fbb09fb..c5c6bcb4 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ The following is the corresponding `mindyolo` versions and supported `mindspore` | mindyolo | mindspore | | :--: | :--: | | master | master | -| 0.4 | 2.3.0 | +| 0.4 | 2.3.1/2.3.0 | | 0.3 | 2.2.10 | | 0.2 | 2.0 | | 0.1 | 1.8 | diff --git a/configs/yolov3/README.md b/configs/yolov3/README.md index ff4959bf..2346ee98 100644 --- a/configs/yolov3/README.md +++ b/configs/yolov3/README.md @@ -9,22 +9,22 @@ We present some updates to YOLO! We made a bunch of little design changes to mak -## Results +## Performance
-performance tested on Ascend 910(8p) with graph mode +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | -| YOLOv3 | Darknet53 | 16 * 8 | 640 | MS COCO 2017 | 45.5 | 61.9M | [yaml](./yolov3.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov3/yolov3-darknet53_300e_mAP455-adfb27af.ckpt) | +| model name | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | +| YOLOv3 | 8 | 16 | 640x640 | O2 | 160.80s | 45.5% | 409.66 | 312.45 | [yaml](./yolov3.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov3/yolov3-darknet53_300e_mAP455-adfb27af.ckpt) | |
-performance tested on Ascend 910*(8p) +Experiments are tested on Ascend 910*(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | ms/step | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOv3 | Darknet53 | 16 * 8 | 640 | MS COCO 2017 | 46.6 | 396.60 | 61.9M | [yaml](./yolov3.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov3/yolov3-darknet53_300e_mAP455-81895f09-910v2.ckpt) | +| model name | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | +| YOLOv3 | 8 | 16 | 640x640 | O2 | 274.32s | 46.6% | 383.68 | 333.61 | [yaml](./yolov3.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov3/yolov3-darknet53_300e_mAP455-81895f09-910v2.ckpt) |

@@ -38,9 +38,16 @@ We present some updates to YOLO! We made a bunch of little design changes to mak Please refer to the [GETTING_STARTED](https://github.com/mindspore-lab/mindyolo/blob/master/GETTING_STARTED.md) in MindYOLO for details. +### Requirements + +| mindspore | ascend driver | firmware | cann toolkit/kernel +| :-------: | :-----------: | :----------: | :----------------: +| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 + ### Training -
+
+View More #### - Pretraining Model diff --git a/configs/yolov4/README.md b/configs/yolov4/README.md index d9255029..11e409b0 100644 --- a/configs/yolov4/README.md +++ b/configs/yolov4/README.md @@ -23,23 +23,23 @@ AP (65.7% AP50) for the MS COCO dataset at a realtime speed of 65 FPS on Tesla V -## Results +## Performance
-performance tested on Ascend 910(8p) with graph mode +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | -| YOLOv4 | CSPDarknet53 | 16 * 8 | 608 | MS COCO 2017 | 45.4 | 27.6M | [yaml](./yolov4.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov4/yolov4-cspdarknet53_320e_map454-50172f93.ckpt) | -| YOLOv4 | CSPDarknet53(silu) | 16 * 8 | 608 | MS COCO 2017 | 45.8 | 27.6M | [yaml](./yolov4-silu.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov4/yolov4-cspdarknet53_silu_320e_map458-bdfc3205.ckpt) | +| model name | backbone | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv4 | CSPDarknet53 | 8 | 16 | 608x608 | O2 | 188.52s | 45.4% | 505.98 | 252.97 ｜ [yaml](./yolov4.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov4/yolov4-cspdarknet53_320e_map454-50172f93.ckpt) | +| YOLOv4 | CSPDarknet53(silu) | 8 | 16 | 608x608 | O2 | 274.18s | 45.8% | 443.21 | 288.80 ｜ [yaml](./yolov4-silu.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov4/yolov4-cspdarknet53_silu_320e_map458-bdfc3205.ckpt) |
-performance tested on Ascend 910*(8p) +Experiments are tested on Ascend 910*(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | ms/step | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOv4 | CSPDarknet53 | 16 * 8 | 608 | MS COCO 2017 | 46.1 | 337.25 | 27.6M | [yaml](./yolov4.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov4/yolov4-cspdarknet53_320e_map454-64b8506f-910v2.ckpt) | +| model name | backbone | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv4 | CSPDarknet53 | 8 | 16 | 608x608 | O2 | 467.47s | 46.1% | 308.43 | 415.01 ｜ [yaml](./yolov4.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov4/yolov4-cspdarknet53_320e_map454-64b8506f-910v2.ckpt) |

@@ -52,9 +52,16 @@ AP (65.7% AP50) for the MS COCO dataset at a realtime speed of 65 FPS on Tesla V Please refer to the [GETTING_STARTED](https://github.com/mindspore-lab/mindyolo/blob/master/GETTING_STARTED.md) in MindYOLO for details. +### Requirements + +| mindspore | ascend driver | firmware | cann toolkit/kernel +| :-------: | :-----------: | :----------: | :----------------: +| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 + ### Training
+View More #### - Pretraining Model diff --git a/configs/yolov5/README.md b/configs/yolov5/README.md index a80b2589..572a9c05 100644 --- a/configs/yolov5/README.md +++ b/configs/yolov5/README.md @@ -6,27 +6,27 @@ YOLOv5 is a family of object detection architectures and models pretrained on th -## Results +## Performance
-performance tested on Ascend 910(8p) with graph mode - -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | -| YOLOv5 | N | 32 * 8 | 640 | MS COCO 2017 | 27.3 | 1.9M | [yaml](./yolov5n.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5n_300e_mAP273-9b16bd7b.ckpt) | -| YOLOv5 | S | 32 * 8 | 640 | MS COCO 2017 | 37.6 | 7.2M | [yaml](./yolov5s.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5s_300e_mAP376-860bcf3b.ckpt) | -| YOLOv5 | M | 32 * 8 | 640 | MS COCO 2017 | 44.9 | 21.2M | [yaml](./yolov5m.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5m_300e_mAP449-e7bbf695.ckpt) | -| YOLOv5 | L | 32 * 8 | 640 | MS COCO 2017 | 48.5 | 46.5M | [yaml](./yolov5l.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5l_300e_mAP485-a28bce73.ckpt) | -| YOLOv5 | X | 16 * 8 | 640 | MS COCO 2017 | 50.5 | 86.7M | [yaml](./yolov5x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5x_300e_mAP505-97d36ddc.ckpt) | +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode + +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv5 | N | 8 | 32 | 640x640 | O2 | 233.25s | 27.3% | 650.57 | 393.50 ｜ [yaml](./yolov5n.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5n_300e_mAP273-9b16bd7b.ckpt) | +| YOLOv5 | S | 8 | 32 | 640x640 | O2 | 166.00s | 37.6% | 650.14 | 393.76 ｜ [yaml](./yolov5s.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5s_300e_mAP376-860bcf3b.ckpt) | +| YOLOv5 | M | 8 | 32 | 640x640 | O2 | 256.51s | 44.9% | 712.31 | 359.39 ｜ [yaml](./yolov5m.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5m_300e_mAP449-e7bbf695.ckpt) | +| YOLOv5 | L | 8 | 32 | 640x640 | O2 | 274.15s | 48.5% | 723.35 | 353.91 ｜ [yaml](./yolov5l.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5l_300e_mAP485-a28bce73.ckpt) | +| YOLOv5 | X | 8 | 16 | 640x640 | O2 | 436.18s | 50.5% | 569.96 | 224.58 ｜ [yaml](./yolov5x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov5/yolov5x_300e_mAP505-97d36ddc.ckpt) |
-performance tested on Ascend 910*(8p) +Experiments are tested on Ascend 910*(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | ms/step | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOv5 | N | 32 * 8 | 640 | MS COCO 2017 | 27.4 | 736.08 | 1.9M | [yaml](./yolov5n.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov5/yolov5n_300e_mAP273-bedf9a93-910v2.ckpt) | -| YOLOv5 | S | 32 * 8 | 640 | MS COCO 2017 | 37.6 | 787.34 | 7.2M | [yaml](./yolov5s.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov5/yolov5s_300e_mAP376-df4a45b6-910v2.ckpt) | +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv5 | N | 8 | 32 | 640x640 | O2 | 377.81s | 27.4% | 520.79 | 491.56 ｜ [yaml](./yolov5n.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov5/yolov5n_300e_mAP273-bedf9a93-910v2.ckpt) | +| YOLOv5 | S | 8 | 32 | 640x640 | O2 | 378.18s | 37.6% | 526.49 | 486.30 ｜ [yaml](./yolov5s.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov5/yolov5s_300e_mAP376-df4a45b6-910v2.ckpt) |

@@ -41,9 +41,16 @@ YOLOv5 is a family of object detection architectures and models pretrained on th Please refer to the [GETTING_STARTED](https://github.com/mindspore-lab/mindyolo/blob/master/GETTING_STARTED.md) in MindYOLO for details. +### Requirements + +| mindspore | ascend driver | firmware | cann toolkit/kernel +| :-------: | :-----------: | :----------: | :----------------: +| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 + ### Training
+View More #### - Distributed Training diff --git a/configs/yolov7/README.md b/configs/yolov7/README.md index ba7a91df..80777fc1 100644 --- a/configs/yolov7/README.md +++ b/configs/yolov7/README.md @@ -9,24 +9,24 @@ YOLOv7 surpasses all known object detectors in both speed and accuracy in the ra -## Results +## Performance
-performance tested on Ascend 910(8p) with graph mode +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | -| YOLOv7 | Tiny | 16 * 8 | 640 | MS COCO 2017 | 37.5 | 6.2M | [yaml](./yolov7-tiny.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov7/yolov7-tiny_300e_mAP375-d8972c94.ckpt) | -| YOLOv7 | L | 16 * 8 | 640 | MS COCO 2017 | 50.8 | 36.9M | [yaml](./yolov7.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov7/yolov7_300e_mAP508-734ac919.ckpt) | -| YOLOv7 | X | 12 * 8 | 640 | MS COCO 2017 | 52.4 | 71.3M | [yaml](./yolov7-x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov7/yolov7-x_300e_mAP524-e2f58741.ckpt) | +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv7 | Tiny | 8 | 16 | 640x640 | O2 | 232.63s | 37.5% | 472.37 | 270.97｜ [yaml](./yolov7-tiny.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov7/yolov7-tiny_300e_mAP375-d8972c94.ckpt) | +| YOLOv7 | L | 8 | 16 | 640x640 | O2 | 290.93s | 50.8% | 678.07 | 188.77｜ [yaml](./yolov7.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov7/yolov7_300e_mAP508-734ac919.ckpt) | +| YOLOv7 | X | 8 | 12 | 640x640 | O2 | 404.77s | 52.4% | 636.36 | 150.86｜ [yaml](./yolov7-x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov7/yolov7-x_300e_mAP524-e2f58741.ckpt) |
-performance tested on Ascend 910*(8p) +Experiments are tested on Ascend 910*(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | ms/step | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOv7 | Tiny | 16 * 8 | 640 | MS COCO 2017 | 37.5 | 496.21 | 6.2M | [yaml](./yolov7-tiny.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov7/yolov7-tiny_300e_mAP375-1d2ddf4b-910v2.ckpt) | +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: +| YOLOv7 | Tiny | 8 | 16 | 640x640 | O2 | 363.74s | 37.5% | 352.92 | 362.69｜ [yaml](./yolov7-tiny.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov7/yolov7-tiny_300e_mAP375-1d2ddf4b-910v2.ckpt) |

@@ -42,9 +42,16 @@ YOLOv7 surpasses all known object detectors in both speed and accuracy in the ra Please refer to the [GETTING_STARTED](https://github.com/mindspore-lab/mindyolo/blob/master/GETTING_STARTED.md) in MindYOLO for details. +### Requirements + +| mindspore | ascend driver | firmware | cann toolkit/kernel +| :-------: | :-----------: | :----------: | :----------------: +| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 + ### Training
+View More #### - Distributed Training diff --git a/configs/yolov8/README.md b/configs/yolov8/README.md index 1ea0386e..f8b22b4d 100644 --- a/configs/yolov8/README.md +++ b/configs/yolov8/README.md @@ -7,39 +7,39 @@ Ultralytics YOLOv8, developed by Ultralytics, is a cutting-edge, state-of-the-ar -## Results +## Performance ### Detection
-performance tested on Ascend 910(8p) with graph mode - -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | -| YOLOv8 | N | 16 * 8 | 640 | MS COCO 2017 | 37.2 | 3.2M | [yaml](./yolov8n.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-n_500e_mAP372-cc07f5bd.ckpt) | -| YOLOv8 | S | 16 * 8 | 640 | MS COCO 2017 | 44.6 | 11.2M | [yaml](./yolov8s.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-s_500e_mAP446-3086f0c9.ckpt) | -| YOLOv8 | M | 16 * 8 | 640 | MS COCO 2017 | 50.5 | 25.9M | [yaml](./yolov8m.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-m_500e_mAP505-8ff7a728.ckpt) | -| YOLOv8 | L | 16 * 8 | 640 | MS COCO 2017 | 52.8 | 43.7M | [yaml](./yolov8l.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-l_500e_mAP528-6e96d6bb.ckpt) | -| YOLOv8 | X | 16 * 8 | 640 | MS COCO 2017 | 53.7 | 68.2M | [yaml](./yolov8x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-x_500e_mAP537-b958e1c7.ckpt) | +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode + +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv8 | N | 8 | 16 | 640x640 | O2 | 195.63s | 37.2% | 265.13 | 482.78｜ [yaml](./yolov8n.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-n_500e_mAP372-cc07f5bd.ckpt) | +| YOLOv8 | S | 8 | 16 | 640x640 | O2 | 115.60s | 44.6% | 292.68 | 437.34｜ [yaml](./yolov8s.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-s_500e_mAP446-3086f0c9.ckpt) | +| YOLOv8 | M | 8 | 16 | 640x640 | O2 | 185.25s | 50.5% | 383.72 | 333.58｜ [yaml](./yolov8m.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-m_500e_mAP505-8ff7a728.ckpt) | +| YOLOv8 | L | 8 | 16 | 640x640 | O2 | 175.08s | 52.8% | 429.02 | 298.35｜ [yaml](./yolov8l.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-l_500e_mAP528-6e96d6bb.ckpt) | +| YOLOv8 | X | 8 | 16 | 640x640 | O2 | 183.68s | 53.7% | 521.97 | 245.22｜ [yaml](./yolov8x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-x_500e_mAP537-b958e1c7.ckpt) |
-performance tested on Ascend 910*(8p) +Experiments are tested on Ascend 910*(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | ms/step | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOv8 | N | 16 * 8 | 640 | MS COCO 2017 | 37.3 | 373.55 | 3.2M | [yaml](./yolov8n.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov8/yolov8-n_500e_mAP372-0e737186-910v2.ckpt) | -| YOLOv8 | S | 16 * 8 | 640 | MS COCO 2017 | 44.7 | 365.53 | 11.2M | [yaml](./yolov8s.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov8/yolov8-s_500e_mAP446-fae4983f-910v2.ckpt) | +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv8 | N | 8 | 16 | 640x640 | O2 | 145.89s | 37.3% | 252.79 | 506.35｜ [yaml](./yolov8n.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov8/yolov8-n_500e_mAP372-0e737186-910v2.ckpt) | +| YOLOv8 | S | 8 | 16 | 640x640 | O2 | 172.22s | 44.7% | 251.30 | 509.35｜ [yaml](./yolov8s.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolov8/yolov8-s_500e_mAP446-fae4983f-910v2.ckpt) |
### Segmentation
-performance tested on Ascend 910(8p) with graph mode +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Mask mAP (%) | Params | Recipe | Download | -|------------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOv8-seg | X | 16 * 8 | 640 | MS COCO 2017 | 52.5 | 42.9 | 71.8M | [yaml](./seg/yolov8x-seg.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-x-seg_300e_mAP_mask_429-b4920557.ckpt) | +| model Name | scale | cards | batch size | resolution | jit level | graph compile | mAP | Mask mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOv8-seg | X | 8 | 16 | 640x640 | O2 | 183.68s | 52.5% | 42.9% | 641.25 | 199.61｜ [yaml](./seg/yolov8x-seg.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolov8/yolov8-x-seg_300e_mAP_mask_429-b4920557.ckpt) |
### Notes @@ -51,9 +51,16 @@ Ultralytics YOLOv8, developed by Ultralytics, is a cutting-edge, state-of-the-ar Please refer to the [GETTING_STARTED](https://github.com/mindspore-lab/mindyolo/blob/master/GETTING_STARTED.md) in MindYOLO for details. +### Requirements + +| mindspore | ascend driver | firmware | cann toolkit/kernel +| :-------: | :-----------: | :----------: | :----------------: +| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 + ### Training
+View More #### - Distributed Training diff --git a/configs/yolox/README.md b/configs/yolox/README.md index 18d8a8c2..42e8b1cd 100644 --- a/configs/yolox/README.md +++ b/configs/yolox/README.md @@ -6,28 +6,28 @@ YOLOX is a new high-performance detector with some experienced improvements to Y -## Results +## Performance
-performance tested on Ascend 910(8p) with graph mode - -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | -| YOLOX | N | 8 * 8 | 416 | MS COCO 2017 | 24.1 | 0.9M | [yaml](./yolox-nano.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-n_300e_map241-ec9815e3.ckpt) | -| YOLOX | Tiny | 8 * 8 | 416 | MS COCO 2017 | 33.3 | 5.1M | [yaml](./yolox-tiny.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-tiny_300e_map333-e5ae3a2e.ckpt) | -| YOLOX | S | 8 * 8 | 640 | MS COCO 2017 | 40.7 | 9.0M | [yaml](./yolox-s.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-s_300e_map407-0983e07f.ckpt) | -| YOLOX | M | 8 * 8 | 640 | MS COCO 2017 | 46.7 | 25.3M | [yaml](./yolox-m.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-m_300e_map467-1db321ee.ckpt) | -| YOLOX | L | 8 * 8 | 640 | MS COCO 2017 | 49.2 | 54.2M | [yaml](./yolox-l.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-l_300e_map492-52a4ab80.ckpt) | -| YOLOX | X | 8 * 8 | 640 | MS COCO 2017 | 51.6 | 99.1M | [yaml](./yolox-x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-x_300e_map516-52216d90.ckpt) | -| YOLOX | Darknet53 | 8 * 8 | 640 | MS COCO 2017 | 47.7 | 63.7M | [yaml](./yolox-darknet53.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-darknet53_300e_map477-b5fcaba9.ckpt) | +Experiments are tested on Ascend 910(8p) with mindspore 2.3.1 graph mode + +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe |weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: ｜ :---: | :---: | +| YOLOX | N | 8 | 8 | 416x416 | O2 | 202.49s | 24.1% | 138.84 | 460.96 ｜ [yaml](./yolox-nano.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-n_300e_map241-ec9815e3.ckpt) | +| YOLOX | Tiny | 8 | 8 | 416x416 | O2 | 169.71s | 33.3% | 126.85 | 504.53 ｜ [yaml](./yolox-tiny.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-tiny_300e_map333-e5ae3a2e.ckpt) | +| YOLOX | S | 8 | 8 | 640x640 | O2 | 202.46s | 40.7% | 243.99 | 262.31 ｜ [yaml](./yolox-s.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-s_300e_map407-0983e07f.ckpt) | +| YOLOX | M | 8 | 8 | 640x640 | O2 | 212.78s | 46.7% | 267.68 | 239.09 ｜ [yaml](./yolox-m.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-m_300e_map467-1db321ee.ckpt) | +| YOLOX | L | 8 | 8 | 640x640 | O2 | 262.52s | 49.2% | 316.78 | 202.03 ｜ [yaml](./yolox-l.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-l_300e_map492-52a4ab80.ckpt) | +| YOLOX | X | 8 | 8 | 640x640 | O2 | 341.33s | 51.6% | 415.67 | 153.97 ｜ [yaml](./yolox-x.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-x_300e_map516-52216d90.ckpt) | +| YOLOX |Darknet53| 8 | 8 | 640x640 | O2 | 198.15s | 47.7% | 407.53 | 157.04 ｜ [yaml](./yolox-darknet53.yaml) | [weights](https://download.mindspore.cn/toolkits/mindyolo/yolox/yolox-darknet53_300e_map477-b5fcaba9.ckpt) |
-performance tested on Ascend 910*(8p) +Experiments are tested on Ascend 910*(8p) with mindspore 2.3.1 graph mode -| Name | Scale | BatchSize | ImageSize | Dataset | Box mAP (%) | ms/step | Params | Recipe | Download | -|--------| :---: | :---: | :---: |--------------| :---: | :---: | :---: | :---: | :---: | -| YOLOX | S | 8 * 8 | 640 | MS COCO 2017 | 41.0 | 242.15 | 9.0M | [yaml](./yolox-s.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolox/yolox-s_300e_map407-cebd0183-910v2.ckpt) | +| model name | scale | cards | batch size | resolution | jit level | graph compile | mAP | ms/step | img/s | recipe | weight | +| :--------: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:｜ :---: | :---: | +| YOLOX | S | 8 | 8 | 640x640 | O2 | 299.01s | 41.0% | 177.65 | 360.26｜ [yaml](./yolox-s.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindyolo/yolox/yolox-s_300e_map407-cebd0183-910v2.ckpt) |

@@ -41,9 +41,16 @@ YOLOX is a new high-performance detector with some experienced improvements to Y Please refer to the [GETTING_STARTED](https://github.com/mindspore-lab/mindyolo/blob/master/GETTING_STARTED.md) in MindYOLO for details. +### Requirements + +| mindspore | ascend driver | firmware | cann toolkit/kernel +| :-------: | :-----------: | :----------: | :----------------: +| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 + ### Training
+View More #### - Distributed Training