Swin Transformer on a CUSTOM dataset? how to train it
my cuda is 11.0 and i have DIr :/usr/local/cuda-11.0/bin/nvcc what is wrong
the postprocess code in yolov5 of tnn is the same as ncnn? the model convert of tnn and ncnn is different? but the preprocess of image and postprocess codes are...
help how to solve it tks /torch/nn/modules/module.py", line 772, in __getattr__ type(self).__name__, name)) torch.nn.modules.module.ModuleAttributeError: 'Crowd_locator' object has no attribute 'loss'
onnx to tnn model successed??
the ""map"" op is supported? def forward(self, x): qkv = self.to_qkv(x).chunk(3, dim = -1) q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d',...
请问A 的生成为什么这样操作呢？不是很懂？哪里有原理解释？感谢感谢！
for hop in valid_hop: a_root = np.zeros((self.num_node, self.num_node)) a_close = np.zeros((self.num_node, self.num_node)) a_further = np.zeros((self.num_node, self.num_node)) for i in range(self.num_node): for j in range(self.num_node): if self.hop_dis[j, i] == hop: if...
me too,why A is got by this way?
pytorch is 1.1？ 1.4？@h @heyitsguay