Closed zonghaofan closed 2 years ago
Could you provide more details you are using? The recommended setting is in experiments/coco/resnet/simdr/original/nmt_res50_256x192_d256x3_adam_lr1e-3_deconv3_split2.yaml. The parameter sigma should do nothing with the proposed method.
Could you provide more details you are using? The recommended setting is in experiments/coco/resnet/simdr/original/nmt_res50_256x192_d256x3_adam_lr1e-3_deconv3_split2.yaml. The parameter sigma should do nothing with the proposed method.
AUTO_RESUME: true CUDNN: BENCHMARK: true DETERMINISTIC: false ENABLED: true DATA_DIR: '' GPUS: (0,1,2,3) OUTPUT_DIR: 'output' LOG_DIR: 'log' WORKERS: 24 PRINT_FREQ: 20
DATASET: COLOR_RGB: false DATASET: 'coco' ROOT: '/share/public/coco-icp' TEST_SET: 'val2017' TRAIN_SET: 'train2017' FLIP: true ROT_FACTOR: 40 SCALE_FACTOR: 0.3 MODEL: NAME: 'pose_resnet_upfree' SIMDR_SPLIT_RATIO: 2.0 HEAD_INPUT: 1344 PRETRAINED: '/data/pretrained/imagenet/resnet50-19c8e357.pth' IMAGE_SIZE:
EXTRA: FINAL_CONV_KERNEL: 1 CHANNEL_PER_JOINT: 28 NUM_LAYERS: 50 LOSS: USE_TARGET_WEIGHT: true TYPE: 'KLDiscretLoss'
TRAIN: BATCH_SIZE_PER_GPU: 32 SHUFFLE: true BEGIN_EPOCH: 0 END_EPOCH: 140 OPTIMIZER: 'adam' LR: 0.001 LR_FACTOR: 0.1 LR_STEP:
The paper result 71.4 AP can be reproduced by using the recommended setting(experiments/coco/resnet/simdr/original/nmt_res50_256x192_d256x3_adam_lr1e-3_deconv3_split2.yaml), which keeps the three-layers deconvolutional modules.
It seems that the yaml file you are using has been changed a lot. For example, the FLIP_TEST should be set as TRUE, which may affect the performance. AND, if you want to reproduce the 70.8 AP(the version without any deconvolutional module), we recommend you to follow the setting in experiments/coco/resnet/simdr/upsample_free/nmt_res50_256x192_d256x3_adam_lr1e-3_split_2_cpj28.yaml
It seems that the yaml file you are using has been changed a lot. For example, the FLIP_TEST should be set as TRUE, which may affect the performance. AND, if you want to reproduce the 70.8 AP(the version without any deconvolutional module), we recommend you to follow the setting in experiments/coco/resnet/simdr/upsample_free/nmt_res50_256x192_d256x3_adam_lr1e-3_split_2_cpj28.yaml
ok thanks
Feel free to reopen this issue, if there is any problems in reproducing.
我用resnet50 kl loss 256*192 sigma=1训练出来ap是0.685,没有文章0.71高。