nanodet
nanodet copied to clipboard
I trained nanodet-plus-m-1.5x_416 on my own data set, and the verification during the training was normal, but the test after the training output information I did not understand, is this normal?
The environment is a cloud GPU server without a graphical interface 1.Why is the output of hyperparams empty? 2.Why does the dataloader output 0 test results?
(nanodet) root@container-085311853c-778288ec:~/autodl-tmp/nanodet# python tools/test.py --task val --config config/nanodet_custom_xml_dataset.yml --model workspace/custom_nanodet-plus-m-1.5x_416/model_best/model_best.ckpt
[NanoDet][05-08 11:51:24]INFO:Setting up data...
datasets/AAAS/voc/val/Annotations
creating index...
index created!
[NanoDet][05-08 11:51:24]INFO:Creating model...
INFO:NanoDet:Creating model...
model size is 1.5x
init weights...
Finish initialize NanoDet-Plus Head.
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
[NanoDet][05-08 11:51:28]INFO:Starting testing...
INFO:NanoDet:Starting testing...
initializing ddp: GLOBAL_RANK: 0, MEMBER: 1/1
----------------------------------------------------------------------------------------------------
distributed_backend=nccl
All DDP processes registered. Starting ddp with 1 processes
----------------------------------------------------------------------------------------------------
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
[NanoDet][05-08 11:51:29]INFO:hyperparams:
INFO:NanoDet:hyperparams:
Testing: 0it [00:00, ?it/s][NanoDet][05-08 11:51:29]INFO:Loaded average state from checkpoint.
INFO:NanoDet:Loaded average state from checkpoint.
/root/miniconda3/envs/nanodet/lib/python3.8/site-packages/torch/nn/functional.py:3060: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
warnings.warn("Default upsampling behavior when mode={} is changed "
Testing: 95%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 36/38 [00:07<00:00, 16.93it/s]Loading and preparing results...
DONE (t=0.53s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
Testing: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 38/38 [00:20<00:00, 16.93it/s]DONE (t=11.96s).
Accumulating evaluation results...
DONE (t=0.73s).
[NanoDet][05-08 11:51:54]INFO:
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.454
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.785
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.431
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.161
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.481
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.287
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.495
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.598
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.278
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.628
INFO:NanoDet:
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.454
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.785
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.431
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.161
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.481
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.287
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.495
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.598
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.278
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.628
[NanoDet][05-08 11:51:54]INFO:
| class | AP50 | mAP | class | AP50 | mAP |
|:--------|:-------|:------|:--------|:-------|:------|
| 20124 | 82.2 | 39.8 | 20125 | 65.1 | 28.7 |
| 20133 | 77.6 | 43.2 | 20144 | 79.8 | 54.4 |
| 20207 | 73.1 | 53.0 | 20208 | 73.0 | 43.5 |
| 20209 | 62.1 | 30.2 | 20210 | 82.9 | 44.5 |
| 20232 | 84.8 | 40.5 | 20240 | 66.4 | 27.3 |
| 20257 | 75.9 | 33.4 | 20261 | 76.6 | 33.9 |
| 20325 | 88.0 | 53.8 | 20326 | 94.6 | 71.1 |
| 30070 | 95.3 | 84.3 | | | |
INFO:NanoDet:
| class | AP50 | mAP | class | AP50 | mAP |
|:--------|:-------|:------|:--------|:-------|:------|
| 20124 | 82.2 | 39.8 | 20125 | 65.1 | 28.7 |
| 20133 | 77.6 | 43.2 | 20144 | 79.8 | 54.4 |
| 20207 | 73.1 | 53.0 | 20208 | 73.0 | 43.5 |
| 20209 | 62.1 | 30.2 | 20210 | 82.9 | 44.5 |
| 20232 | 84.8 | 40.5 | 20240 | 66.4 | 27.3 |
| 20257 | 75.9 | 33.4 | 20261 | 76.6 | 33.9 |
| 20325 | 88.0 | 53.8 | 20326 | 94.6 | 71.1 |
| 30070 | 95.3 | 84.3 | | | |
--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{}
--------------------------------------------------------------------------------
Testing: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 38/38 [00:25<00:00, 1.50it/s]