chensnathan
Hi, could you provide a detailed log of the multi-scale training(R50_C5)?
Hi, sorry for the late reply.
I don't have log files for multi-scale training now. You can train it for yourself. By following the settings in the paper, you can achieve comparable results with those reported in the paper.
Hi, I want to run a demo using YOLOF. And, I wrote these files. However, I can't recognize any objects in the image. Could you get me some advances?
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年7月2日(星期五) 中午12:14 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
Hi, sorry for the late reply.
I don't have log files for multi-scale training now. You can train it for yourself. By following the settings in the paper, you can achieve comparable results with those reported in the paper.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
I don't understand that what files did you write. Could you provide more details about how you run a demo with YOLOF?
Hi, the logit of these files is as follows. First, following https://github.com/facebookresearch/detectron2/blob/master/GETTING_STARTED.md, we download demo.py and perdictor.py. Then, we write default params(e.g. --config-file and --input). Finally, we write the YOLOF_predictor. Compared with default, we modifiy the checkpointer and pre-processing of image（YOLOFCheckpointer，T.AugmentationList(build_augmentation(cfg, False))).
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年7月11日(星期天) 晚上6:46 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
I don't understand that what files did you write. Could you provide more details about how you run a demo with YOLOF?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
For the demo, you can use the "DefaultPredictor" directly. Could you debug the output of the predictor? I will help with it when I got time this week.
Thanks!!!
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年7月12日(星期一) 晚上6:15 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
For the demo, you can use the "DefaultPredictor" directly. Could you debug the output of the predictor? I will help with it when I got time this week.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
Hi, we use the "DefaultPredictor" and get the result. However, I get different performances. When I modify the "SCORE_THRESH_TEST" to 0.3, we can get right, meanwhile, the Map reduces to 35.49(base 37.5). Could you give me some direction?
0.3(Map 35.49)
0.05(Map 37.5)
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年7月12日(星期一) 晚上6:15 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
For the demo, you can use the "DefaultPredictor" directly. Could you debug the output of the predictor? I will help with it when I got time this week.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
Hi, sorry for the late reply.
It's normal that the performance drops when you set a higher threshold (e.g., 0.3). A higher threshold means that you remove several valid predictions compared with the original setting (threshold=0.05). In YOLOF, we set the threshold as 0.05 by default.
Hi, maybe these pictures are not shown on GitHub. Please see the email. The problem is that I obtain many low score boxes when setting the threshold to 0.05, but I can get a clear result when setting the threshold to 0.3. But, setting the threshold to 0.3, we only get 35.49 mAP and to 0.05 get 37.5. I have put these pictures in the attachment.
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年8月3日(星期二) 晚上8:54 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
Hi, sorry for the late reply.
It's normal that the performance drops when you set a higher threshold (e.g., 0.3). A higher threshold means that you remove several valid predictions compared with the original setting (threshold=0.05). In YOLOF, we set the threshold as 0.05 by default.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
There exist many TPs (True Positives) between 0.05 and 0.3. Thus the mAP is lower than the original one when you set the threshold to 0.3. A detailed analysis on TPs and FPs may be helpful to understand why the performance drops.
Hello, when setting the threshold to 0.3, we can get the picture named 0.3.jpg(35.5mAP, true result) and to 0.05, we can get the picture named 0.05.png(37.5mAP, false result). The mAP is high but gets a false result. why?
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年8月4日(星期三) 晚上9:06 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
There exist many TPs (True Positives) between 0.05 and 0.3. Thus the mAP is lower than the original one when you set the threshold to 0.3. A detailed analysis on TPs and FPs may be helpful to understand why the performance drops.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
Hi, we use the coco2017 val dataset. In the attachment we submit 3 json files (improved result (our), original result (your), official result) and a simple test script. The script shows that we are able to get a good result but the detection image shows a messy frame. Why?
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年8月5日(星期四) 中午11:31 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
You should check the whole validation set instead of one single image.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
从QQ邮箱发来的超大附件
test.zip (35.69M, 无限期)进入下载页面：http://mail.qq.com/cgi-bin/ftnExs_download?k=0b6537634c35a1ca598f3dc81033561853515453075052551b545452541e505403001a5a5751561a525153515057510254500654363b64435316434d4c5a14370b&t=exs_ftn_download&code=6e7c63d7
I check several visualizations. There indeed exists low score bounding boxes in some images, which may be wrong predictions. While for the performance calculation, you need to do the counting for TPs, FPs, and FNs, which is more intuitive to understand why the mAP is higher with a threshold of 0.05.
BTW, you can do a visualization with different thresholds for other detectors' results. And you can get similar visualization results.
Hi, I want to use your data of YOLOF(R50C5) in our paper. GFLOPs are 86 in your paper, but I got 85 when evalution the GFLOPs in Detectron2. Could you give me some adviance?
[32m[08/23 20:06:35 d2.data.datasets.coco]: [0mLoaded 5000 images in COCO format from /mnt/disk2/dataset/coco/annotations/instances_val2017.json [32m[08/23 20:06:35 d2.data.build]: [0mDistribution of instances among all 80 categories: [36m| category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 10777 | bicycle | 314 | car | 1918 | | motorcycle | 367 | airplane | 143 | bus | 283 | | train | 190 | truck | 414 | boat | 424 | | traffic light | 634 | fire hydrant | 101 | stop sign | 75 | | parking meter | 60 | bench | 411 | bird | 427 | | cat | 202 | dog | 218 | horse | 272 | | sheep | 354 | cow | 372 | elephant | 252 | | bear | 71 | zebra | 266 | giraffe | 232 | | backpack | 371 | umbrella | 407 | handbag | 540 | | tie | 252 | suitcase | 299 | frisbee | 115 | | skis | 241 | snowboard | 69 | sports ball | 260 | | kite | 327 | baseball bat | 145 | baseball gl.. | 148 | | skateboard | 179 | surfboard | 267 | tennis racket | 225 | | bottle | 1013 | wine glass | 341 | cup | 895 | | fork | 215 | knife | 325 | spoon | 253 | | bowl | 623 | banana | 370 | apple | 236 | | sandwich | 177 | orange | 285 | broccoli | 312 | | carrot | 365 | hot dog | 125 | pizza | 284 | | donut | 328 | cake | 310 | chair | 1771 | | couch | 261 | potted plant | 342 | bed | 163 | | dining table | 695 | toilet | 179 | tv | 288 | | laptop | 231 | mouse | 106 | remote | 283 | | keyboard | 153 | cell phone | 262 | microwave | 55 | | oven | 143 | toaster | 9 | sink | 225 | | refrigerator | 126 | book | 1129 | clock | 267 | | vase | 274 | scissors | 36 | teddy bear | 190 | | hair drier | 11 | toothbrush | 57 | | | | total | 36335 | | | | |[0m [32m[08/23 20:06:35 d2.data.dataset_mapper]: [0m[DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(800, 800), max_size=1333, sample_style='choice')] [32m[08/23 20:06:35 d2.data.common]: [0mSerializing 5000 elements to byte tensors and concatenating them all ... [32m[08/23 20:06:35 d2.data.common]: [0mSerialized dataset takes 19.15 MiB [32m[08/23 20:06:39 fvcore.common.checkpoint]: [0mLoading checkpoint from ../weights/YOLOF_R50_C5_1x.pth [32m[08/23 20:06:39 fvcore.common.checkpoint]: [0mThe checkpoint state_dict contains keys that are not used by the model: [35manchor_generator.cell_anchors.0[0m [5m[31mWARNING[0m [32m[08/23 20:06:39 fvcore.nn.jit_analysis]: [0mUnsupported operator aten::log encountered 1 time(s) [5m[31mWARNING[0m [32m[08/23 20:06:39 fvcore.nn.jit_analysis]: [0mThe following submodules of the model were never called during the trace of the graph. They may be unused, or they were accessed by direct calls to .forward() or via other python methods. In the latter case they will have zeros for statistics, though their statistics will still contribute to their parent calling module. model.anchor_matcher [32m[08/23 20:07:07 detectron2]: [0mFlops table computed from only one input sample:
| module | #parameters or shape | #flops |
|---|---|---|
| model | 44.113M | 84.517G |
| backbone | 23.455M | 66.945G |
| backbone.stem.conv1 | 9.408K | 2.078G |
| backbone.stem.conv1.weight | (64, 3, 7, 7) | |
| backbone.stem.conv1.norm | 68.352M | |
| backbone.res2 | 0.213M | 11.75G |
| backbone.res2.0 | 73.728K | 4.108G |
| backbone.res2.1 | 69.632K | 3.821G |
| backbone.res2.2 | 69.632K | 3.821G |
| backbone.res3 | 1.212M | 16.487G |
| backbone.res3.0 | 0.377M | 5.135G |
| backbone.res3.1 | 0.279M | 3.784G |
| backbone.res3.2 | 0.279M | 3.784G |
| backbone.res3.3 | 0.279M | 3.784G |
| backbone.res4 | 7.078M | 23.882G |
| backbone.res4.0 | 1.507M | 5.092G |
| backbone.res4.1 | 1.114M | 3.758G |
| backbone.res4.2 | 1.114M | 3.758G |
| backbone.res4.3 | 1.114M | 3.758G |
| backbone.res4.4 | 1.114M | 3.758G |
| backbone.res4.5 | 1.114M | 3.758G |
| backbone.res5 | 14.942M | 12.749G |
| backbone.res5.0 | 6.029M | 5.147G |
| backbone.res5.1 | 4.456M | 3.801G |
| backbone.res5.2 | 4.456M | 3.801G |
| encoder | 4.534M | 3.861G |
| encoder.lateral_conv | 1.049M | 0.891G |
| encoder.lateral_conv.weight | (512, 2048, 1, 1) | |
| encoder.lateral_conv.bias | (512,) | |
| encoder.lateral_norm | 1.024K | 2.176M |
| encoder.lateral_norm.weight | (512,) | |
| encoder.lateral_norm.bias | (512,) | |
| encoder.fpn_conv | 2.36M | 2.005G |
| encoder.fpn_conv.weight | (512, 512, 3, 3) | |
| encoder.fpn_conv.bias | (512,) | |
| encoder.fpn_norm | 1.024K | 2.176M |
| encoder.fpn_norm.weight | (512,) | |
| encoder.fpn_norm.bias | (512,) | |
| encoder.dilated_encoder_blocks | 1.123M | 0.96G |
| encoder.dilated_encoder_blocks.0 | 0.281M | 0.24G |
| encoder.dilated_encoder_blocks.1 | 0.281M | 0.24G |
| encoder.dilated_encoder_blocks.2 | 0.281M | 0.24G |
| encoder.dilated_encoder_blocks.3 | 0.281M | 0.24G |
| decoder | 16.124M | 13.71G |
| decoder.cls_subnet | 4.722M | 4.015G |
| decoder.cls_subnet.0 | 2.36M | 2.005G |
| decoder.cls_subnet.1 | 1.024K | 2.176M |
| decoder.cls_subnet.3 | 2.36M | 2.005G |
| decoder.cls_subnet.4 | 1.024K | 2.176M |
| decoder.bbox_subnet | 9.443M | 8.03G |
| decoder.bbox_subnet.0 | 2.36M | 2.005G |
| decoder.bbox_subnet.1 | 1.024K | 2.176M |
| decoder.bbox_subnet.3 | 2.36M | 2.005G |
| decoder.bbox_subnet.4 | 1.024K | 2.176M |
| decoder.bbox_subnet.6 | 2.36M | 2.005G |
| decoder.bbox_subnet.7 | 1.024K | 2.176M |
| decoder.bbox_subnet.9 | 2.36M | 2.005G |
| decoder.bbox_subnet.10 | 1.024K | 2.176M |
| decoder.cls_score | 1.844M | 1.567G |
| decoder.cls_score.weight | (400, 512, 3, 3) | |
| decoder.cls_score.bias | (400,) | |
| decoder.bbox_pred | 92.18K | 78.336M |
| decoder.bbox_pred.weight | (20, 512, 3, 3) | |
| decoder.bbox_pred.bias | (20,) | |
| decoder.object_pred | 23.045K | 19.584M |
| decoder.object_pred.weight | (5, 512, 3, 3) | |
| decoder.object_pred.bias | (5,) | |
| [32m[08/23 20:07:07 detectron2]: [0mAverage GFlops for each type of operators: | ||
| [('conv', 86.96688461248), ('batch_norm', 0.9727329696)] | ||
| [32m[08/23 20:07:07 detectron2]: [0mTotal GFlops: 87.9±9.7 |
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年8月5日(星期四) 下午5:33 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
I check several visualizations. There indeed exists low score bounding boxes in some images, which may be wrong predictions. While for the performance calculation, you need to do the counting for TPs, FPs, and FNs, which is more intuitive to understand why the mAP is higher with a threshold of 0.05.
BTW, you can do a visualization with different thresholds for other detectors' results. And you can get similar visualization results.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
Sorry to bother you. The purpose of this letter is to inquire about the configuration or weight of multi-scale training (R50 or R101). During the past two years, we was committed to solving YOLOF's NMS problem. Recently we successfully implemented the YOLOF version of NMS-Free without any additional parameters (37.1 mAP vs 37.7 mAP). But because there is no weight of multi-scale training, we can not carry out multi-scale training. After following the Settings in the paper, we can only get ~40 maps. We hope that you can provide us with a weight of multi-scale training to complete our final experiment.
------------------ 原始邮件 ------------------ 发件人: "Xx" @.>; 发送时间: 2021年8月23日(星期一) 晚上10:00 @.>;
主题: 回复： [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
Hi, I want to use your data of YOLOF(R50C5) in our paper. GFLOPs are 86 in your paper, but I got 85 when evalution the GFLOPs in Detectron2. Could you give me some adviance?
[32m[08/23 20:06:35 d2.data.datasets.coco]: [0mLoaded 5000 images in COCO format from /mnt/disk2/dataset/coco/annotations/instances_val2017.json [32m[08/23 20:06:35 d2.data.build]: [0mDistribution of instances among all 80 categories: [36m| category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 10777 | bicycle | 314 | car | 1918 | | motorcycle | 367 | airplane | 143 | bus | 283 | | train | 190 | truck | 414 | boat | 424 | | traffic light | 634 | fire hydrant | 101 | stop sign | 75 | | parking meter | 60 | bench | 411 | bird | 427 | | cat | 202 | dog | 218 | horse | 272 | | sheep | 354 | cow | 372 | elephant | 252 | | bear | 71 | zebra | 266 | giraffe | 232 | | backpack | 371 | umbrella | 407 | handbag | 540 | | tie | 252 | suitcase | 299 | frisbee | 115 | | skis | 241 | snowboard | 69 | sports ball | 260 | | kite | 327 | baseball bat | 145 | baseball gl.. | 148 | | skateboard | 179 | surfboard | 267 | tennis racket | 225 | | bottle | 1013 | wine glass | 341 | cup | 895 | | fork | 215 | knife | 325 | spoon | 253 | | bowl | 623 | banana | 370 | apple | 236 | | sandwich | 177 | orange | 285 | broccoli | 312 | | carrot | 365 | hot dog | 125 | pizza | 284 | | donut | 328 | cake | 310 | chair | 1771 | | couch | 261 | potted plant | 342 | bed | 163 | | dining table | 695 | toilet | 179 | tv | 288 | | laptop | 231 | mouse | 106 | remote | 283 | | keyboard | 153 | cell phone | 262 | microwave | 55 | | oven | 143 | toaster | 9 | sink | 225 | | refrigerator | 126 | book | 1129 | clock | 267 | | vase | 274 | scissors | 36 | teddy bear | 190 | | hair drier | 11 | toothbrush | 57 | | | | total | 36335 | | | | |[0m [32m[08/23 20:06:35 d2.data.dataset_mapper]: [0m[DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(800, 800), max_size=1333, sample_style='choice')] [32m[08/23 20:06:35 d2.data.common]: [0mSerializing 5000 elements to byte tensors and concatenating them all ... [32m[08/23 20:06:35 d2.data.common]: [0mSerialized dataset takes 19.15 MiB [32m[08/23 20:06:39 fvcore.common.checkpoint]: [0mLoading checkpoint from ../weights/YOLOF_R50_C5_1x.pth [32m[08/23 20:06:39 fvcore.common.checkpoint]: [0mThe checkpoint state_dict contains keys that are not used by the model: [35manchor_generator.cell_anchors.0[0m [5m[31mWARNING[0m [32m[08/23 20:06:39 fvcore.nn.jit_analysis]: [0mUnsupported operator aten::log encountered 1 time(s) [5m[31mWARNING[0m [32m[08/23 20:06:39 fvcore.nn.jit_analysis]: [0mThe following submodules of the model were never called during the trace of the graph. They may be unused, or they were accessed by direct calls to .forward() or via other python methods. In the latter case they will have zeros for statistics, though their statistics will still contribute to their parent calling module. model.anchor_matcher [32m[08/23 20:07:07 detectron2]: [0mFlops table computed from only one input sample:
| module | #parameters or shape | #flops |
|---|---|---|
| model | 44.113M | 84.517G |
| backbone | 23.455M | 66.945G |
| backbone.stem.conv1 | 9.408K | 2.078G |
| backbone.stem.conv1.weight | (64, 3, 7, 7) | |
| backbone.stem.conv1.norm | 68.352M | |
| backbone.res2 | 0.213M | 11.75G |
| backbone.res2.0 | 73.728K | 4.108G |
| backbone.res2.1 | 69.632K | 3.821G |
| backbone.res2.2 | 69.632K | 3.821G |
| backbone.res3 | 1.212M | 16.487G |
| backbone.res3.0 | 0.377M | 5.135G |
| backbone.res3.1 | 0.279M | 3.784G |
| backbone.res3.2 | 0.279M | 3.784G |
| backbone.res3.3 | 0.279M | 3.784G |
| backbone.res4 | 7.078M | 23.882G |
| backbone.res4.0 | 1.507M | 5.092G |
| backbone.res4.1 | 1.114M | 3.758G |
| backbone.res4.2 | 1.114M | 3.758G |
| backbone.res4.3 | 1.114M | 3.758G |
| backbone.res4.4 | 1.114M | 3.758G |
| backbone.res4.5 | 1.114M | 3.758G |
| backbone.res5 | 14.942M | 12.749G |
| backbone.res5.0 | 6.029M | 5.147G |
| backbone.res5.1 | 4.456M | 3.801G |
| backbone.res5.2 | 4.456M | 3.801G |
| encoder | 4.534M | 3.861G |
| encoder.lateral_conv | 1.049M | 0.891G |
| encoder.lateral_conv.weight | (512, 2048, 1, 1) | |
| encoder.lateral_conv.bias | (512,) | |
| encoder.lateral_norm | 1.024K | 2.176M |
| encoder.lateral_norm.weight | (512,) | |
| encoder.lateral_norm.bias | (512,) | |
| encoder.fpn_conv | 2.36M | 2.005G |
| encoder.fpn_conv.weight | (512, 512, 3, 3) | |
| encoder.fpn_conv.bias | (512,) | |
| encoder.fpn_norm | 1.024K | 2.176M |
| encoder.fpn_norm.weight | (512,) | |
| encoder.fpn_norm.bias | (512,) | |
| encoder.dilated_encoder_blocks | 1.123M | 0.96G |
| encoder.dilated_encoder_blocks.0 | 0.281M | 0.24G |
| encoder.dilated_encoder_blocks.1 | 0.281M | 0.24G |
| encoder.dilated_encoder_blocks.2 | 0.281M | 0.24G |
| encoder.dilated_encoder_blocks.3 | 0.281M | 0.24G |
| decoder | 16.124M | 13.71G |
| decoder.cls_subnet | 4.722M | 4.015G |
| decoder.cls_subnet.0 | 2.36M | 2.005G |
| decoder.cls_subnet.1 | 1.024K | 2.176M |
| decoder.cls_subnet.3 | 2.36M | 2.005G |
| decoder.cls_subnet.4 | 1.024K | 2.176M |
| decoder.bbox_subnet | 9.443M | 8.03G |
| decoder.bbox_subnet.0 | 2.36M | 2.005G |
| decoder.bbox_subnet.1 | 1.024K | 2.176M |
| decoder.bbox_subnet.3 | 2.36M | 2.005G |
| decoder.bbox_subnet.4 | 1.024K | 2.176M |
| decoder.bbox_subnet.6 | 2.36M | 2.005G |
| decoder.bbox_subnet.7 | 1.024K | 2.176M |
| decoder.bbox_subnet.9 | 2.36M | 2.005G |
| decoder.bbox_subnet.10 | 1.024K | 2.176M |
| decoder.cls_score | 1.844M | 1.567G |
| decoder.cls_score.weight | (400, 512, 3, 3) | |
| decoder.cls_score.bias | (400,) | |
| decoder.bbox_pred | 92.18K | 78.336M |
| decoder.bbox_pred.weight | (20, 512, 3, 3) | |
| decoder.bbox_pred.bias | (20,) | |
| decoder.object_pred | 23.045K | 19.584M |
| decoder.object_pred.weight | (5, 512, 3, 3) | |
| decoder.object_pred.bias | (5,) | |
| [32m[08/23 20:07:07 detectron2]: [0mAverage GFlops for each type of operators: | ||
| [('conv', 86.96688461248), ('batch_norm', 0.9727329696)] | ||
| [32m[08/23 20:07:07 detectron2]: [0mTotal GFlops: 87.9±9.7 |
------------------ 原始邮件 ------------------ 发件人: "chensnathan/YOLOF" @.>; 发送时间: 2021年8月5日(星期四) 下午5:33 @.>; @.@.>; 主题: Re: [chensnathan/YOLOF] Hi, could you provide a detailed log of the multi-scale training(R50_C5)? (#27)
I check several visualizations. There indeed exists low score bounding boxes in some images, which may be wrong predictions. While for the performance calculation, you need to do the counting for TPs, FPs, and FNs, which is more intuitive to understand why the mAP is higher with a threshold of 0.05.
BTW, you can do a visualization with different thresholds for other detectors' results. And you can get similar visualization results.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.