Open hhxdestiny opened 2 years ago
MPR_Net deraining单卡训练loss下降不明显,且psnr一直是inf,而ssim几乎恒定不变。但是原作的MPR可以正常训练,几乎同样的配置,不确定是PaddleGAN/ppgan/metrics/psnr_ssim.py/calculate_psnr.py:96的calculate_psnr有问题还是paddle的问题。
PaddleGAN/ppgan/metrics/psnr_ssim.py/calculate_psnr.py:96
calculate_psnr
运行环境:AI Studio最新版本GPU32G(BML Codelab) paddle-gpu: develop2.2.2 代码:PaddleGAN最新版本(develop v2.1.0) 配置文件(mprnet_deraining.yaml):
total_iters: 100000 output_dir: output/mprnet enable_visualdl: True model: name: MPRModel generator: name: MPRNet n_feat: 40 scale_unetfeats: 20 scale_orsnetfeats: 16 char_criterion: name: CharbonnierLoss edge_criterion: name: EdgeLoss dataset: train: name: MPRTrain rgb_dir: data/mydata/train num_workers: 0 batch_size: 1 img_options: patch_size: 16 test: name: MPRTrain rgb_dir: data/mydata/val num_workers: 0 batch_size: 1 img_options: patch_size: 16 lr_scheduler: name: CosineAnnealingRestartLR learning_rate: !!float 1.25e-5 periods: [25000, 25000, 25000, 25000] restart_weights: [1, 1, 1, 1] eta_min: !!float 1e-6 validate: interval: 2000 save_img: false metrics: psnr: # metric name, can be arbitrary name: PSNR crop_border: 4 test_y_channel: True ssim: name: SSIM crop_border: 4 test_y_channel: True optimizer: name: Adam # add parameters of net_name to optim # name should in self.nets net_names: - generator beta1: 0.9 beta2: 0.999 epsilon: 1e-8 log_config: interval: 50 visiual_interval: 200 snapshot_config: interval: 2000
运行过程忘记截图了
inf大概是因为验证集里恰好截图到了近乎纯色的,导致去雨后和原来完全一样,loss不下降我也遇到了,还有loss突然上升到很大,然后就不下来了
您好,请问问题还是否需要解决,目前相关图像生成能力集成在PaddleMIX中,https://github.com/PaddlePaddle/PaddleMIX/tree/develop 可以在这个repo下提出您的需求
MPR_Net deraining单卡训练loss下降不明显,且psnr一直是inf,而ssim几乎恒定不变。但是原作的MPR可以正常训练,几乎同样的配置,不确定是
PaddleGAN/ppgan/metrics/psnr_ssim.py/calculate_psnr.py:96
的calculate_psnr
有问题还是paddle的问题。运行环境:AI Studio最新版本GPU32G(BML Codelab) paddle-gpu: develop2.2.2 代码:PaddleGAN最新版本(develop v2.1.0) 配置文件(mprnet_deraining.yaml):
运行过程忘记截图了