Gebixiaochen

Results 3 issues of Gebixiaochen

line 109 in "Model_utils.py" : mean_sizes = tf.expand_dims(tf.constant(g_mean_size_arr, dtype=tf.float32), 0) + size_residuals #(B,NS,1) 1) the shape of mean_sizes shouldn't be #(B,NS,3)? 2) I do not understand why "mean_sizes" would be...

My computer is poor that I can't run the training process, I hope someone can send me a pretrained AVOD-FPN checkpoint so that I can run the inference on the...

My test code is as below: ``` class SparseBasicBlock(spconv.SparseModule): expansion = 1 def __init__(self, in_planes, out_planes, stride=1, downsample=None): spconv.SparseModule.__init__(self) self.conv1 = spconv.SubMConv2d(in_planes, out_planes, 3, stride, 1, bias=False) self.conv2 = spconv.SubMConv2d(out_planes,...