dawei-hao

Hello, have you solved it? I found a decompression error after downloading the model file。

Hello, could you please tell me that I made a mistake when retraining the model? Do you have any good solutions? load model init finish... ===========> training

您好请问您可以分享作者提供的预训练模型吗？因为链接失效了

run pytorch2onnx.py

@448357739 大佬您好，可以分享下您的代码嘛，我这边一直显示错误

@JanuszL Thank you, But I get a error TypeError: Invalid shape (3, 224, 224) for image data ``` img = batch_cpu.at(0) print(img.shape) # (3, 224, 224) plt.imshow(img) pylab.show() ``` maybe...

@JanuszL My code is the one above; In the model inference phase, I want to input an image and output a result; In order to ensure the accuracy of the...

@JanuszL hi，batch size=16, obtain 16 dimensions tensorgpulist, how to stack into 16X224X224X3 pytorch supported dimensions

@JanuszLHow to convert pipe_out directly to 16X224X224X3 parallelly 

@JanuszL  ``` crop_patch = fn.crop_mirror_normalize(decode, device="gpu", crop_h=224, crop_w=224, crop_pos_x=fn.random.uniform(range=(0., 1.)), crop_pos_y=fn.random.uniform(range=(0., 1.)), dtype=types.FLOAT, output_layout="CHW", mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ``` I found that the function did not normalize...