apache#7058 [Tutorial] Import errors in deploy_detection.py and deplo…

…y_classification.py (apache#7059)

* Update deploy_classification.py

Changed import paths

* Update deploy_detection.py

changed import paths and stop layer id

* Update deploy_classification.py

Set working directory to TVM base.

* Update deploy_detection.py

Set working directory to TVM base. Changed layer id in comment to 186.

* reverse changes in deploy_classification.py

Reversed changes in import path. Imports working as expected.

* Reverse change in import paths

Imports working as expected.

* Update deploy_detection.py

Duplicated graph_runtime import removed.

vta/tutorials/frontend/legacy/deploy_detection.py

@@ -58,7 +58,7 @@
 from tvm import rpc, autotvm, relay
 from tvm.relay.testing import yolo_detection, darknet
 from tvm.relay.testing.darknet import __darknetffi__
-from tvm.contrib import graph_runtime, graph_runtime, util
+from tvm.contrib import graph_runtime, utils
 from tvm.contrib.download import download_testdata
 from vta.testing import simulator
 from vta.top import graph_pack
@@ -123,15 +123,15 @@
 target = env.target if device == "vta" else env.target_vta_cpu
 
 pack_dict = {
-    "yolov3-tiny": ["nn.max_pool2d", "cast", 4, 185],
+    "yolov3-tiny": ["nn.max_pool2d", "cast", 4, 186],
 }
 
 # Name of Darknet model to compile
 # The ``start_pack`` and ``stop_pack`` labels indicate where
 # to start and end the graph packing relay pass: in other words
 # where to start and finish offloading to VTA.
 # the number 4 indicate the the ``start_pack`` index is 4, the
-# number 185 indicate the ``stop_pack index`` is 185, by using
+# number 186 indicate the ``stop_pack index`` is 186, by using
 # name and index number, here we can located to correct place
 # where to start/end when there are multiple ``nn.max_pool2d``
 # or ``cast``, print(mod.astext(show_meta_data=False)) can help