- Deep Learning with PyTorch
- Vishnu Subramanian
- 179字
- 2021-06-24 19:16:24
4-D tensors
One common example for four-dimensional tensor types is a batch of images. Modern CPUs and GPUs are optimized to perform the same operations on multiple examples faster. So, they take a similar time to process one image or a batch of images. So, it is common to use a batch of examples rather than use a single image at a time. Choosing the batch size is not straightforward; it depends on several factors. One major restriction for using a bigger batch or the complete dataset is GPU memory limitations—16, 32, and 64 are commonly used batch sizes.
Let's look at an example where we load a batch of cat images of size 64 x 224 x 224 x 3 where 64 represents the batch size or the number of images, 244 represents height and width, and 3 represents channels:
#Read cat images from disk
cats = glob(data_path+'*.jpg')
#Convert images into numpy arrays
cat_imgs = np.array([np.array(Image.open(cat).resize((224,224))) for cat in cats[:64]])
cat_imgs = cat_imgs.reshape(-1,224,224,3)
cat_tensors = torch.from_numpy(cat_imgs)
cat_tensors.size()
Output - torch.Size([64, 224, 224, 3])
- Cortex-M3 + μC/OS-II嵌入式系統開發入門與應用
- Windows phone 7.5 application development with F#
- Intel FPGA/CPLD設計(高級篇)
- 電腦軟硬件維修從入門到精通
- Apple Motion 5 Cookbook
- 分布式系統與一致性
- Creating Flat Design Websites
- 電腦高級維修及故障排除實戰
- Internet of Things Projects with ESP32
- RISC-V處理器與片上系統設計:基于FPGA與云平臺的實驗教程
- Java Deep Learning Cookbook
- Blender Game Engine:Beginner's Guide
- FL Studio Cookbook
- Practical Artificial Intelligence and Blockchain
- 快·易·通:2天學會電腦組裝·系統安裝·日常維護與故障排除