Some small bugs and features of Deep learning
Last updated on：5 months ago
Sometimes, basic concepts are important for us to learn deep learning. I would collect the bugs and features of deep learning in this blog.
Can you check the under sampling methods and more precisely the parameter return_indices which by default is False and can be set to True. It will allow to return the associated indices as you need for most of the under sampler
torchvision.transforms.Resize(*size*, *interpolation=<InterpolationMode.BILINEAR: 'bilinear'>*, *max_size=None*, *antialias=None*)
Resize the input image to the given size. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions
x.size(0) means x.shape
Allows us to do fast and memory efficient reshaping, slicing and element-wise operations.
conda : The term ‘conda’ is not recognized as the name of a cmdlet, function, script file, or operable
conda : The term 'conda' is not recognized as the name of a cmdlet, function, script file, or operable program. Check the spelling of the name, or if a path was included, verify that the path is correct and
Waite a minute and try again.
from pytorchcv.model_provider import get_model as ptcv_get_model net = ptcv_get_model("efficientnet_b0", pretrained=True) get_model_complexity_info(net, (3, 224, 224), print_per_layer_stat=False) \# ('0.4 GMac', '5.29 M')
This implementation of efficient net uses F.conv2d to perform convs. Unfortunately ptflops can’t catch arbitrary F.* functions since it works via adding hooks to known children classes of nn.Module such as nn.Conv2d and so on. If you enable print_per_layer_stat you’ll see that Conv2dStaticSamePadding module is treated as a zero-op since there is no handler for this custom operation (which is actually implemented via call of F.conv2d). That’s why ptflops reports less operations than expected.
Must be import before other function call register. Otherwise, unimported function cannot be registered.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
remove mkl in anaconda.
本博客所有文章除特别声明外，均采用 CC BY-SA 4.0 协议 ，转载请注明出处！