Upload README.md with huggingface_hub

README.md

@@ -53,8 +53,8 @@ video_input = torch.cat(video_frames)
 with torch.no_grad():
     outputs = model(**video_input)
 
-# model predicts class_queries_logits of shape `(batch_size, num_queries)`
-# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
+# model predicts class_queries_logits of shape `(batch_size, num_queries, num_classes)`
+# and masks_queries_logits of shape `(num_queries, batch_size, height, width)`
 class_queries_logits = outputs.class_queries_logits
 masks_queries_logits = outputs.masks_queries_logits