search

NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Other
8.57k stars 1.2k forks source link

Problem in testing #125

Open mhmtsarigul opened 4 years ago

mhmtsarigul commented 4 years ago

Hello.

I train a model with my own dataset. But when i try to validate with test data i get the following error.

python test.py --name mytest_256 \ --input_nc 3 --loadSize 256 --n_scales_spatial 3 --n_downsample_G 2 --use_single_G --dataroot datasets/mytest --dataset_mode mytest

`------------ Options ------------- add_face_disc: False aspect_ratio: 1.0 basic_point_only: False batchSize: 1 checkpoints_dir: ./checkpoints dataroot: datasets/hyper dataset_mode: hyper debug: False densepose_only: False display_id: 0 display_winsize: 512 feat_num: 3 fg: False fg_labels: [26] fineSize: 512 fp16: False gpu_ids: [0] how_many: 300 input_nc: 3 isTrain: False label_feat: False label_nc: 0 loadSize: 256 load_features: False load_pretrain: local_rank: 0 max_dataset_size: inf model: vid2vid nThreads: 2 n_blocks: 9 n_blocks_local: 3 n_downsample_E: 3 n_downsample_G: 2 n_frames_G: 3 n_gpus_gen: 1 n_local_enhancers: 1 n_scales_spatial: 3 name: hyper_256 ndf: 64 nef: 32 netE: simple netG: composite ngf: 128 no_canny_edge: False no_dist_map: False no_first_img: False no_flip: False no_flow: False norm: batch ntest: inf openpose_only: False output_nc: 3 phase: test random_drop_prob: 0.05 random_scale_points: False remove_face_labels: False resize_or_crop: scaleWidth results_dir: ./results/ serial_batches: False start_frame: 0 tf_log: False use_instance: False use_real_img: False use_single_G: True which_epoch: latest -------------- End ---------------- CustomDatasetDataLoader dataset [HyperTestDataset] was created vid2vid ---------- Networks initialized -------------

./checkpoints/hyper_256/latest_net_G1.pth not exists yet! ./checkpoints/hyper_256/latest_net_G2.pth not exists yet! Traceback (most recent call last): File "test.py", line 27, in model = create_model(opt) File "/home/msg/vid2vid/models/models.py", line 76, in create_model modelG.initialize(opt) File "/home/msg/vid2vid/models/vid2vid_model_G.py", line 53, in initialize self.netG_i = self.load_single_G() if self.use_single_G else None File "/home/msg/vid2vid/models/vid2vid_model_G.py", line 295, in load_single_G netG.load_state_dict(torch.load(load_path))
File "/home/msg/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 777, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for GlobalGenerator: Missing key(s) in state_dict: "model.1.weight", "model.1.bias", "model.2.running_mean", "model.2.running_var", "model.4.weight", "model.4.bias", "model.5.running_mean", "model.5.running_var", "model.7.weight", "model.7.bias", "model.8.running_mean", "model.8.running_var", "model.10.conv_block.1.weight", "model.10.conv_block.1.bias", "model.10.conv_block.2.running_mean", "model.10.conv_block.2.running_var", "model.10.conv_block.5.weight", "model.10.conv_block.5.bias", "model.10.conv_block.6.running_mean", "model.10.conv_block.6.running_var", "model.11.conv_block.1.weight", "model.11.conv_block.1.bias", "model.11.conv_block.2.running_mean", "model.11.conv_block.2.running_var", "model.11.conv_block.5.weight", "model.11.conv_block.5.bias", "model.11.conv_block.6.running_mean", "model.11.conv_block.6.running_var", "model.12.conv_block.1.weight", "model.12.conv_block.1.bias", "model.12.conv_block.2.running_mean", "model.12.conv_block.2.running_var", "model.12.conv_block.5.weight", "model.12.conv_block.5.bias", "model.12.conv_block.6.running_mean", "model.12.conv_block.6.running_var", "model.13.conv_block.1.weight", "model.13.conv_block.1.bias", "model.13.conv_block.2.running_mean", "model.13.conv_block.2.running_var", "model.13.conv_block.5.weight", "model.13.conv_block.5.bias", "model.13.conv_block.6.running_mean", "model.13.conv_block.6.running_var", "model.14.conv_block.1.weight", "model.14.conv_block.1.bias", "model.14.conv_block.2.running_mean", "model.14.conv_block.2.running_var", "model.14.conv_block.5.weight", "model.14.conv_block.5.bias", "model.14.conv_block.6.running_mean", "model.14.conv_block.6.running_var", "model.15.conv_block.1.weight", "model.15.conv_block.1.bias", "model.15.conv_block.2.running_mean", "model.15.conv_block.2.running_var", "model.15.conv_block.5.weight", "model.15.conv_block.5.bias", "model.15.conv_block.6.running_mean", "model.15.conv_block.6.running_var", "model.16.conv_block.1.weight", "model.16.conv_block.1.bias", "model.16.conv_block.2.running_mean", "model.16.conv_block.2.running_var", "model.16.conv_block.5.weight", "model.16.conv_block.5.bias", "model.16.conv_block.6.running_mean", "model.16.conv_block.6.running_var", "model.17.conv_block.1.weight", "model.17.conv_block.1.bias", "model.17.conv_block.2.running_mean", "model.17.conv_block.2.running_var", "model.17.conv_block.5.weight", "model.17.conv_block.5.bias", "model.17.conv_block.6.running_mean", "model.17.conv_block.6.running_var", "model.18.conv_block.1.weight", "model.18.conv_block.1.bias", "model.18.conv_block.2.running_mean", "model.18.conv_block.2.running_var", "model.18.conv_block.5.weight", "model.18.conv_block.5.bias", "model.18.conv_block.6.running_mean", "model.18.conv_block.6.running_var", "model.19.weight", "model.19.bias", "model.20.running_mean", "model.20.running_var", "model.22.weight", "model.22.bias", "model.23.running_mean", "model.23.running_var", "model.26.weight", "model.26.bias". Unexpected key(s) in state_dict: "model_down_seg.1.weight", "model_down_seg.1.bias", "model_down_seg.2.weight", "model_down_seg.2.bias", "model_down_seg.2.running_mean", "model_down_seg.2.running_var", "model_down_seg.2.num_batches_tracked", "model_down_seg.4.weight", "model_down_seg.4.bias", "model_down_seg.5.weight", "model_down_seg.5.bias", "model_down_seg.5.running_mean", "model_down_seg.5.running_var", "model_down_seg.5.num_batches_tracked", "model_down_seg.7.weight", "model_down_seg.7.bias", "model_down_seg.8.weight", "model_down_seg.8.bias", "model_down_seg.8.running_mean", "model_down_seg.8.running_var", "model_down_seg.8.num_batches_tracked", "model_down_seg.10.conv_block.1.weight", "model_down_seg.10.conv_block.1.bias", "model_down_seg.10.conv_block.2.weight", "model_down_seg.10.conv_block.2.bias", "model_down_seg.10.conv_block.2.running_mean", "model_down_seg.10.conv_block.2.running_var", "model_down_seg.10.conv_block.2.num_batches_tracked", "model_down_seg.10.conv_block.5.weight", "model_down_seg.10.conv_block.5.bias", "model_down_seg.10.conv_block.6.weight", "model_down_seg.10.conv_block.6.bias", "model_down_seg.10.conv_block.6.running_mean", "model_down_seg.10.conv_block.6.running_var", "model_down_seg.10.conv_block.6.num_batches_tracked", "model_down_seg.11.conv_block.1.weight", "model_down_seg.11.conv_block.1.bias", "model_down_seg.11.conv_block.2.weight", "model_down_seg.11.conv_block.2.bias", "model_down_seg.11.conv_block.2.running_mean", "model_down_seg.11.conv_block.2.running_var", "model_down_seg.11.conv_block.2.num_batches_tracked", "model_down_seg.11.conv_block.5.weight", "model_down_seg.11.conv_block.5.bias", "model_down_seg.11.conv_block.6.weight", "model_down_seg.11.conv_block.6.bias", "model_down_seg.11.conv_block.6.running_mean", "model_down_seg.11.conv_block.6.running_var", "model_down_seg.11.conv_block.6.num_batches_tracked", "model_down_seg.12.conv_block.1.weight", "model_down_seg.12.conv_block.1.bias", "model_down_seg.12.conv_block.2.weight", "model_down_seg.12.conv_block.2.bias", "model_down_seg.12.conv_block.2.running_mean", "model_down_seg.12.conv_block.2.running_var", "model_down_seg.12.conv_block.2.num_batches_tracked", "model_down_seg.12.conv_block.5.weight", "model_down_seg.12.conv_block.5.bias", "model_down_seg.12.conv_block.6.weight", "model_down_seg.12.conv_block.6.bias", "model_down_seg.12.conv_block.6.running_mean", "model_down_seg.12.conv_block.6.running_var", "model_down_seg.12.conv_block.6.num_batches_tracked", "model_down_seg.13.conv_block.1.weight", "model_down_seg.13.conv_block.1.bias", "model_down_seg.13.conv_block.2.weight", "model_down_seg.13.conv_block.2.bias", "model_down_seg.13.conv_block.2.running_mean", "model_down_seg.13.conv_block.2.running_var", "model_down_seg.13.conv_block.2.num_batches_tracked", "model_down_seg.13.conv_block.5.weight", "model_down_seg.13.conv_block.5.bias", "model_down_seg.13.conv_block.6.weight", "model_down_seg.13.conv_block.6.bias", "model_down_seg.13.conv_block.6.running_mean", "model_down_seg.13.conv_block.6.running_var", "model_down_seg.13.conv_block.6.num_batches_tracked", "model_down_seg.14.conv_block.1.weight", "model_down_seg.14.conv_block.1.bias", "model_down_seg.14.conv_block.2.weight", "model_down_seg.14.conv_block.2.bias", "model_down_seg.14.conv_block.2.running_mean", "model_down_seg.14.conv_block.2.running_var", "model_down_seg.14.conv_block.2.num_batches_tracked", "model_down_seg.14.conv_block.5.weight", "model_down_seg.14.conv_block.5.bias", "model_down_seg.14.conv_block.6.weight", "model_down_seg.14.conv_block.6.bias", "model_down_seg.14.conv_block.6.running_mean", "model_down_seg.14.conv_block.6.running_var", "model_down_seg.14.conv_block.6.num_batches_tracked", "model_down_img.1.weight", "model_down_img.1.bias", "model_down_img.2.weight", "model_down_img.2.bias", "model_down_img.2.running_mean", "model_down_img.2.running_var", "model_down_img.2.num_batches_tracked", "model_down_img.4.weight", "model_down_img.4.bias", "model_down_img.5.weight", "model_down_img.5.bias", "model_down_img.5.running_mean", "model_down_img.5.running_var", "model_down_img.5.num_batches_tracked", "model_down_img.7.weight", "model_down_img.7.bias", "model_down_img.8.weight", "model_down_img.8.bias", "model_down_img.8.running_mean", "model_down_img.8.running_var", "model_down_img.8.num_batches_tracked", "model_down_img.10.conv_block.1.weight", "model_down_img.10.conv_block.1.bias", "model_down_img.10.conv_block.2.weight", "model_down_img.10.conv_block.2.bias", "model_down_img.10.conv_block.2.running_mean", "model_down_img.10.conv_block.2.running_var", "model_down_img.10.conv_block.2.num_batches_tracked", "model_down_img.10.conv_block.5.weight", "model_down_img.10.conv_block.5.bias", "model_down_img.10.conv_block.6.weight", "model_down_img.10.conv_block.6.bias", "model_down_img.10.conv_block.6.running_mean", "model_down_img.10.conv_block.6.running_var", "model_down_img.10.conv_block.6.num_batches_tracked", "model_down_img.11.conv_block.1.weight", "model_down_img.11.conv_block.1.bias", "model_down_img.11.conv_block.2.weight", "model_down_img.11.conv_block.2.bias", "model_down_img.11.conv_block.2.running_mean", "model_down_img.11.conv_block.2.running_var", "model_down_img.11.conv_block.2.num_batches_tracked", "model_down_img.11.conv_block.5.weight", "model_down_img.11.conv_block.5.bias", "model_down_img.11.conv_block.6.weight", "model_down_img.11.conv_block.6.bias", "model_down_img.11.conv_block.6.running_mean", "model_down_img.11.conv_block.6.running_var", "model_down_img.11.conv_block.6.num_batches_tracked", "model_down_img.12.conv_block.1.weight", "model_down_img.12.conv_block.1.bias", "model_down_img.12.conv_block.2.weight", "model_down_img.12.conv_block.2.bias", "model_down_img.12.conv_block.2.running_mean", "model_down_img.12.conv_block.2.running_var", "model_down_img.12.conv_block.2.num_batches_tracked", "model_down_img.12.conv_block.5.weight", "model_down_img.12.conv_block.5.bias", "model_down_img.12.conv_block.6.weight", "model_down_img.12.conv_block.6.bias", "model_down_img.12.conv_block.6.running_mean", "model_down_img.12.conv_block.6.running_var", "model_down_img.12.conv_block.6.num_batches_tracked", "model_down_img.13.conv_block.1.weight", "model_down_img.13.conv_block.1.bias", "model_down_img.13.conv_block.2.weight", "model_down_img.13.conv_block.2.bias", "model_down_img.13.conv_block.2.running_mean", "model_down_img.13.conv_block.2.running_var", "model_down_img.13.conv_block.2.num_batches_tracked", "model_down_img.13.conv_block.5.weight", "model_down_img.13.conv_block.5.bias", "model_down_img.13.conv_block.6.weight", "model_down_img.13.conv_block.6.bias", "model_down_img.13.conv_block.6.running_mean", "model_down_img.13.conv_block.6.running_var", "model_down_img.13.conv_block.6.num_batches_tracked", "model_down_img.14.conv_block.1.weight", "model_down_img.14.conv_block.1.bias", "model_down_img.14.conv_block.2.weight", "model_down_img.14.conv_block.2.bias", "model_down_img.14.conv_block.2.running_mean", "model_down_img.14.conv_block.2.running_var", "model_down_img.14.conv_block.2.num_batches_tracked", "model_down_img.14.conv_block.5.weight", "model_down_img.14.conv_block.5.bias", "model_down_img.14.conv_block.6.weight", "model_down_img.14.conv_block.6.bias", "model_down_img.14.conv_block.6.running_mean", "model_down_img.14.conv_block.6.running_var", "model_down_img.14.conv_block.6.num_batches_tracked", "model_res_img.0.conv_block.1.weight", "model_res_img.0.conv_block.1.bias", "model_res_img.0.conv_block.2.weight", "model_res_img.0.conv_block.2.bias", "model_res_img.0.conv_block.2.running_mean", "model_res_img.0.conv_block.2.running_var", "model_res_img.0.conv_block.2.num_batches_tracked", "model_res_img.0.conv_block.5.weight", "model_res_img.0.conv_block.5.bias", "model_res_img.0.conv_block.6.weight", "model_res_img.0.conv_block.6.bias", "model_res_img.0.conv_block.6.running_mean", "model_res_img.0.conv_block.6.running_var", "model_res_img.0.conv_block.6.num_batches_tracked", "model_res_img.1.conv_block.1.weight", "model_res_img.1.conv_block.1.bias", "model_res_img.1.conv_block.2.weight", "model_res_img.1.conv_block.2.bias", "model_res_img.1.conv_block.2.running_mean", "model_res_img.1.conv_block.2.running_var", "model_res_img.1.conv_block.2.num_batches_tracked", "model_res_img.1.conv_block.5.weight", "model_res_img.1.conv_block.5.bias", "model_res_img.1.conv_block.6.weight", "model_res_img.1.conv_block.6.bias", "model_res_img.1.conv_block.6.running_mean", "model_res_img.1.conv_block.6.running_var", "model_res_img.1.conv_block.6.num_batches_tracked", "model_res_img.2.conv_block.1.weight", "model_res_img.2.conv_block.1.bias", "model_res_img.2.conv_block.2.weight", "model_res_img.2.conv_block.2.bias", "model_res_img.2.conv_block.2.running_mean", "model_res_img.2.conv_block.2.running_var", "model_res_img.2.conv_block.2.num_batches_tracked", "model_res_img.2.conv_block.5.weight", "model_res_img.2.conv_block.5.bias", "model_res_img.2.conv_block.6.weight", "model_res_img.2.conv_block.6.bias", "model_res_img.2.conv_block.6.running_mean", "model_res_img.2.conv_block.6.running_var", "model_res_img.2.conv_block.6.num_batches_tracked", "model_res_img.3.conv_block.1.weight", "model_res_img.3.conv_block.1.bias", "model_res_img.3.conv_block.2.weight", "model_res_img.3.conv_block.2.bias", "model_res_img.3.conv_block.2.running_mean", "model_res_img.3.conv_block.2.running_var", "model_res_img.3.conv_block.2.num_batches_tracked", "model_res_img.3.conv_block.5.weight", "model_res_img.3.conv_block.5.bias", "model_res_img.3.conv_block.6.weight", "model_res_img.3.conv_block.6.bias", "model_res_img.3.conv_block.6.running_mean", "model_res_img.3.conv_block.6.running_var", "model_res_img.3.conv_block.6.num_batches_tracked", "model_up_img.0.weight", "model_up_img.0.bias", "model_up_img.1.weight", "model_up_img.1.bias", "model_up_img.1.running_mean", "model_up_img.1.running_var", "model_up_img.1.num_batches_tracked", "model_up_img.3.weight", "model_up_img.3.bias", "model_up_img.4.weight", "model_up_img.4.bias", "model_up_img.4.running_mean", "model_up_img.4.running_var", "model_up_img.4.num_batches_tracked", "model_final_img.1.weight", "model_final_img.1.bias", "model_res_flow.0.conv_block.1.weight", "model_res_flow.0.conv_block.1.bias", "model_res_flow.0.conv_block.2.weight", "model_res_flow.0.conv_block.2.bias", "model_res_flow.0.conv_block.2.running_mean", "model_res_flow.0.conv_block.2.running_var", "model_res_flow.0.conv_block.2.num_batches_tracked", "model_res_flow.0.conv_block.5.weight", "model_res_flow.0.conv_block.5.bias", "model_res_flow.0.conv_block.6.weight", "model_res_flow.0.conv_block.6.bias", "model_res_flow.0.conv_block.6.running_mean", "model_res_flow.0.conv_block.6.running_var", "model_res_flow.0.conv_block.6.num_batches_tracked", "model_res_flow.1.conv_block.1.weight", "model_res_flow.1.conv_block.1.bias", "model_res_flow.1.conv_block.2.weight", "model_res_flow.1.conv_block.2.bias", "model_res_flow.1.conv_block.2.running_mean", "model_res_flow.1.conv_block.2.running_var", "model_res_flow.1.conv_block.2.num_batches_tracked", "model_res_flow.1.conv_block.5.weight", "model_res_flow.1.conv_block.5.bias", "model_res_flow.1.conv_block.6.weight", "model_res_flow.1.conv_block.6.bias", "model_res_flow.1.conv_block.6.running_mean", "model_res_flow.1.conv_block.6.running_var", "model_res_flow.1.conv_block.6.num_batches_tracked", "model_res_flow.2.conv_block.1.weight", "model_res_flow.2.conv_block.1.bias", "model_res_flow.2.conv_block.2.weight", "model_res_flow.2.conv_block.2.bias", "model_res_flow.2.conv_block.2.running_mean", "model_res_flow.2.conv_block.2.running_var", "model_res_flow.2.conv_block.2.num_batches_tracked", "model_res_flow.2.conv_block.5.weight", "model_res_flow.2.conv_block.5.bias", "model_res_flow.2.conv_block.6.weight", "model_res_flow.2.conv_block.6.bias", "model_res_flow.2.conv_block.6.running_mean", "model_res_flow.2.conv_block.6.running_var", "model_res_flow.2.conv_block.6.num_batches_tracked", "model_res_flow.3.conv_block.1.weight", "model_res_flow.3.conv_block.1.bias", "model_res_flow.3.conv_block.2.weight", "model_res_flow.3.conv_block.2.bias", "model_res_flow.3.conv_block.2.running_mean", "model_res_flow.3.conv_block.2.running_var", "model_res_flow.3.conv_block.2.num_batches_tracked", "model_res_flow.3.conv_block.5.weight", "model_res_flow.3.conv_block.5.bias", "model_res_flow.3.conv_block.6.weight", "model_res_flow.3.conv_block.6.bias", "model_res_flow.3.conv_block.6.running_mean", "model_res_flow.3.conv_block.6.running_var", "model_res_flow.3.conv_block.6.num_batches_tracked", "model_up_flow.0.weight", "model_up_flow.0.bias", "model_up_flow.1.weight", "model_up_flow.1.bias", "model_up_flow.1.running_mean", "model_up_flow.1.running_var", "model_up_flow.1.num_batches_tracked", "model_up_flow.3.weight", "model_up_flow.3.bias", "model_up_flow.4.weight", "model_up_flow.4.bias", "model_up_flow.4.running_mean", "model_up_flow.4.running_var", "model_up_flow.4.num_batches_tracked", "model_final_flow.1.weight", "model_final_flow.1.bias", "model_final_w.1.weight", "model_final_w.1.bias". `

jiangzhubo commented 4 years ago

i have same issue, do you solve it @mhmtsarigul

pranavraikote commented 3 years ago

@mhmtsarigul @jiaxianhua The way to solve this is, giving the path which has all the checkpoints, the error at the beginning says, latest checkpoints not found, the parameter --name path/to/checckpoints/ should point correctly to the folder where the checkpoints are present (stored while training)