Jo_Lin

TypeError: rand() argument after * must be an iterable, not int

1

net = models.resnet50() summary(net, input_size=([3, 224, 224])) x = [torch.rand(2, *in_size).type(dtype) for in_size in input_size] TypeError: rand() argument after * must be an iterable, not int Thanks for help!

Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1], padding="VALID", strides=[1, 2, 2, 1]](activation/Relu)' with input shapes: [?,2,112,64].

15

I have run the train.py, but it show me that: ValueError: Negative dimension size caused by subtracting 3 from 2 for '{{node max_pooling2d/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", ksize=[1, 3, 3, 1],...

RuntimeError: size mismatch, m1: [12288 x 3], m2: [1024 x 196] at /pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:290 Thanks for your help！

Thanks for your work! I find that the pretrained model which trained on the Private Asia Face Data is working on my task. Could you tell me how to make...

请问Softmax Loss vs Softmax_Center Loss 这种聚类效果图如何绘制？

Question of the test.py?

3

def load_image(img_path): image = cv2.imread(img_path, 0) #image = cv2.resize(image, (112,112)).astype('float32') image = cv2.resize(image, (128,128)).astype('float32') if image is None: return None image = np.dstack((image, np.fliplr(image))) image = image.transpose((2, 0, 1)) image...

I have trained the vggface_48w in this project with the resnet18. And it is OK, the accruacy can be 90%. BUT when I try to change the model, such as...

``` { "name":"win_shengli", "real_pos":[530,200], "click_pos":[[820,480],[800,260]], "flag": "" }, ``` real_pos 如何确定？click_pos如何设置才不会超出图像范围？

最近win桌面版有重大更新，请问是否会对脚本使用造成影响？

Can you tell me the key of the Baidu Cloud?