yangt1013
yangt1013
@jy03168805 Hi，I want to know if your problem is solved, Index"idx" out of the range ，how is it solved, thank you！
The problems is GPU memory usage can not find working file,GPU-Util occupancy 2% Default ，the operating environment is required in your paper is satisfied.Using top inquire CPU working very well...
Nvidia driver version: NVIDIA UNIX x86_64 Kernel Module 440.33.01 Wed Nov 13 00:00:22 UTC 2019 GCC version: gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.12) cudnn version：7.1.4 #define CUDNN_MAJOR 7 #define CUDNN_MINOR...
{'base_lr': 0.01, 'dataset': 'MiniImageNet', 'dataset_dir': './data/mini/', 'eval_weights': None, 'gamma': 0.5, 'gpu': '1', 'init_weights': None, 'max_epoch': 100, 'meta_label': 'exp1', 'meta_lr1': 0.0001, 'meta_lr2': 0.001, 'model_type': 'ResNet', 'num_batch': 100, 'phase': 'pre_train', 'pre_batch_size': 128,...
top - 16:41:40 up 5:18, 1 user, load average: 6.07, 3.99, 1.91 Tasks: 318 total, 1 running, 235 sleeping, 0 stopped, 0 zombie %Cpu(s): 44.6 us, 6.1 sy, 0.0 ni,...
Looking forward to your reply, I think I can't solve this problem，Thanks a lot！
+-----------------------------------------------------------------------------+ | NVIDIA-SMI 440.33.01 Driver Version: 440.33.01 CUDA Version: 9.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage |...
if erode: with torch.cuda.device(self.current_gpu): rendered_images = self.renderer(vertices_ori_normal, self.faces_use, texs) # rendered_images: batch * 3 * h * w, masks: batch * h * w rendered_images, depths, masks = self.renderer(vertices_ori_normal, self.faces_use,...
renderer.py images = nr.rasterize( faces, textures, self.image_size, self.anti_aliasing, self.near, self.far, self.rasterizer_eps, self.background_color) I am waiting for your reply! thans a lot. return images
Hello,I haven't changed the parameters. The network precision is 76,releationnet+resnet18